@ 5d4b6c8d:8a1c1ee3

Is the housing market going to crash for real this time?

https://primal.net/e/nevent1qvzqqqqqqypzp6dtxy5uz5yu5vzxdtcv7du9qm9574u5kqcqha58efshkkwz6zmdqqs8dqr35dc0npsc8cuulqm4m7gxrgqq3ytphtja9nx534a592gztzsuzsrja

https://stacker.news/items/990316

@ c1e9ab3a:9cb56b43

I. Introduction: Money as a Function of Efficiency and Preference

Money is not defined by law, but by power over productivity. In any open economy, the most economically efficient actors—those who control the most valuable goods, services, and knowledge—ultimately dictate the medium of exchange. Their preferences signal to the broader market what form of money is required to access the highest-value goods, from durable commodities to intangibles like intellectual property and skilled labor.

Whatever money these actors prefer becomes the de facto unit of account and store of value, regardless of its legal status. This emergent behavior is natural and reflects a hierarchy of monetary utility.

II. Classical Gresham’s Law: A Product of Market Distortion

Gresham’s Law, famously stated as:

"Bad money drives out good"

is only valid under coercive monetary conditions, specifically: - Legal tender laws that force the acceptance of inferior money at par with superior money. - Fixed exchange rates imposed by decree, not market valuation. - Governments or central banks backing elastic fiduciary media with promises of redemption. - Institutional structures that mandate debt and tax payments in the favored currency.

Under these conditions, superior money (hard money) is hoarded, while inferior money (soft, elastic, inflationary) circulates. This is not an expression of free market behavior—it is the result of suppressed price discovery and legal coercion.

Gresham’s Law, therefore, is not a natural law of money, but a law of distortion under forced parity and artificial elasticity.

III. The Collapse of Coercion: Inversion of Gresham’s Law

When coercive structures weaken or are bypassed—through technological exit, jurisdictional arbitrage, monetary breakdown, or political disintegration—Gresham’s Law inverts:

Good money drives out bad.

This occurs because: - Market actors regain the freedom to select money based on utility, scarcity, and credibility. - Legal parity collapses, exposing the true economic hierarchy of monetary forms. - Trustless systems (e.g., Bitcoin) or superior digital instruments (e.g., stablecoins) offer better settlement, security, and durability. - Elastic fiduciary media become undesirable as counterparty risk and inflation rise.

The inversion marks a return to monetary natural selection—not a breakdown of Gresham’s Law, but the collapse of its preconditions.

IV. Elasticity and Control

Elastic fiduciary media (like fiat currency) are not intrinsically evil. They are tools of state finance and debt management, enabling rapid expansion of credit and liquidity. However, when their issuance is unconstrained, and legal tender laws force their use, they become weapons of economic coercion.

Banks issue credit unconstrained by real savings, and governments enforce the use of inflated media through taxation and courts. This distorts capital allocation, devalues productive labor, and ultimately hollows out monetary confidence.

V. Monetary Reversion: The Return of Hard Money

When the coercion ends—whether gradually or suddenly—the monetary system reverts. The preferences of the productive and wealthy reassert themselves:

• Superior money is not just saved—it begins to circulate.
• Weaker currencies are rejected not just for savings, but for daily exchange.
• The hoarded form becomes the traded form, and Gresham’s Law inverts completely.

Bitcoin, gold, and even highly credible stable instruments begin to function as true money, not just stores of value. The natural monetary order returns, and the State becomes a late participant, not the originator of monetary reality.

VI. Conclusion

Gresham’s Law operates only under distortion. Its inversion is not an anomaly—it is a signal of the collapse of coercion. The monetary system then reorganizes around productive preference, technological efficiency, and economic sovereignty.

The most efficient market will always dictate the form of hard money. The State can delay this reckoning through legal force, but it cannot prevent it indefinitely. Once free choice returns, bad money dies, and good money lives again.

@ 21335073:a244b1ad

The other day, I had the privilege of sitting down with one of my favorite living artists. Our conversation was so captivating that I felt compelled to share it. I’m leaving his name out for privacy.

Since our last meeting, I’d watched a documentary about his life, one he’d helped create. I told him how much I admired his openness in it. There’s something strange about knowing intimate details of someone’s life when they know so little about yours—it’s almost like I knew him too well for the kind of relationship we have.

He paused, then said quietly, with a shy grin, that watching the documentary made him realize how “odd and eccentric” he is. I laughed and told him he’s probably the sanest person I know. Because he’s lived fully, chasing love, passion, and purpose with hardly any regrets. He’s truly lived.

Today, I turn 44, and I’ll admit I’m a bit eccentric myself. I think I came into the world this way. I’ve made mistakes along the way, but I carry few regrets. Every misstep taught me something. And as I age, I’m not interested in blending in with the world—I’ll probably just lean further into my own brand of “weird.” I want to live life to the brim. The older I get, the more I see that the “normal” folks often seem less grounded than the eccentric artists who dare to live boldly. Life’s too short to just exist, actually live.

I’m not saying to be strange just for the sake of it. But I’ve seen what the crowd celebrates, and I’m not impressed. Forge your own path, even if it feels lonely or unpopular at times.

It’s easy to scroll through the news and feel discouraged. But actually, this is one of the most incredible times to be alive! I wake up every day grateful to be here, now. The future is bursting with possibility—I can feel it.

So, to my fellow weirdos on nostr: stay bold. Keep dreaming, keep pushing, no matter what’s trending. Stay wild enough to believe in a free internet for all. Freedom is radical—hold it tight. Live with the soul of an artist and the grit of a fighter. Thanks for inspiring me and so many others to keep hoping. Thank you all for making the last year of my life so special.

@ b7274d28:c99628cb

A few months ago, a nostrich was switching from iOS to Android and asked for suggestions for #Nostr apps to try out. nostr:npub18ams6ewn5aj2n3wt2qawzglx9mr4nzksxhvrdc4gzrecw7n5tvjqctp424 offered the following as his response:

nostr:nevent1qvzqqqqqqypzq0mhp4ja8fmy48zuk5p6uy37vtk8tx9dqdwcxm32sy8nsaa8gkeyqydhwumn8ghj7un9d3shjtnwdaehgunsd3jkyuewvdhk6tcpz4mhxue69uhhyetvv9ujuerpd46hxtnfduhszythwden5te0dehhxarj9emkjmn99uqzpwwts6n28eyvjpcwvu5akkwu85eg92dpvgw7cgmpe4czdadqvnv984rl0z

Yes. #Android users are fortunate to have some powerful Nostr apps and tools at our disposal that simply have no comparison over on the iOS side. However, a tool is only as good as the knowledge of the user, who must have an understanding of how best to wield it for maximum effect. This fact was immediately evidenced by replies to Derek asking, "What is the use case for Citrine?" and "This is the first time I'm hearing about Citrine and Pokey. Can you give me links for those?"

Well, consider this tutorial your Nostr starter-kit for Android. We'll go over installing and setting up Amber, Amethyst, Citrine, and Pokey, and as a bonus we'll be throwing in the Zapstore and Coinos to boot. We will assume no previous experience with any of the above, so if you already know all about one or more of these apps, you can feel free to skip that tutorial.

So many apps...

You may be wondering, "Why do I need so many apps to use Nostr?" That's perfectly valid, and the honest answer is, you don't. You can absolutely just install a Nostr client from the Play Store, have it generate your Nostr identity for you, and stick with the default relays already set up in that app. You don't even need to connect a wallet, if you don't want to. However, you won't experience all that Nostr has to offer if that is as far as you go, any more than you would experience all that Italian cuisine has to offer if you only ever try spaghetti.

Nostr is not just one app that does one thing, like Facebook, Twitter, or TikTok. It is an entire ecosystem of applications that are all built on top of a protocol that allows them to be interoperable. This set of tools will help you make the most out of that interoperability, which you will never get from any of the big-tech social platforms. It will provide a solid foundation for you to build upon as you explore more and more of what Nostr has to offer.

So what do these apps do?

Fundamental to everything you do on Nostr is the need to cryptographically sign with your private key. If you aren't sure what that means, just imagine that you had to enter your password every time you hit the "like" button on Facebook, or every time you commented on the latest dank meme. That would get old really fast, right? That's effectively what Nostr requires, but on steroids.

To keep this from being something you manually have to do every 5 seconds when you post a note, react to someone else's note, or add a comment, Nostr apps can store your private key and use it to sign behind the scenes for you. This is very convenient, but it means you are trusting that app to not do anything with your private key that you don't want it to. You are also trusting it to not leak your private key, because anyone who gets their hands on it will be able to post as you, see your private messages, and effectively be you on Nostr. The more apps you give your private key to, the greater your risk that it will eventually be compromised.

Enter #Amber, an application that will store your private key in only one app, and all other compatible Nostr apps can communicate with it to request a signature, without giving any of those other apps access to your private key.

Most Nostr apps for Android now support logging in and signing with Amber, and you can even use it to log into apps on other devices, such as some of the web apps you use on your PC. It's an incredible tool given to us by nostr:npub1w4uswmv6lu9yel005l3qgheysmr7tk9uvwluddznju3nuxalevvs2d0jr5, and only available for Android users. Those on iPhone are incredibly jealous that they don't have anything comparable, yet.

Speaking of nostr:npub1w4uswmv6lu9yel005l3qgheysmr7tk9uvwluddznju3nuxalevvs2d0jr5, the next app is also one of his making.

All Nostr data is stored on relays, which are very simple servers that Nostr apps read notes from and write notes to. In most forms of social media, it can be a pain to get your own data out to keep a backup. That's not the case on Nostr. Anyone can run their own relay, either for the sake of backing up their personal notes, or for others to post their notes to, as well.

Since Nostr notes take up very little space, you can actually run a relay on your phone. I have been on Nostr for almost 2 and a half years, and I have 25,000+ notes of various kinds on my relay, and a backup of that full database is just 24MB on my phone's storage.

Having that backup can save your bacon if you try out a new Nostr client and it doesn't find your existing follow list for some reason, so it writes a new one and you suddenly lose all of the people you were following. Just pop into your #Citrine relay, confirm it still has your correct follow list or import it from a recent backup, then have Citrine restore it. Done.

Additionally, there are things you may want to only save to a relay you control, such as draft messages that you aren't ready to post publicly, or eCash tokens, which can actually be saved to Nostr relays now. Citrine can also be used with Amber for signing into certain Nostr applications that use a relay to communicate with Amber.

If you are really adventurous, you can also expose Citrine over Tor to be used as an outbox relay, or used for peer-to-peer private messaging, but that is far more involved than the scope of this tutorial series.

You can't get far in Nostr without a solid and reliable client to interact with. #Amethyst is the client we will be using for this tutorial because there simply isn't another Android client that comes close, so far. Moreover, it can be a great client for new users to get started on, and yet it has a ton of features for power-users to take advantage of as well.

There are plenty of other good clients to check out over time, such as Coracle, YakiHonne, Voyage, Olas, Flotilla and others, but I keep coming back to Amethyst, and by the time you finish this tutorial, I think you'll see why. nostr:npub1gcxzte5zlkncx26j68ez60fzkvtkm9e0vrwdcvsjakxf9mu9qewqlfnj5z and others who have contributed to Amethyst have really built something special in this client, and it just keeps improving with every update that's shipped.

Most social media apps have some form of push notifications, and some Nostr apps do, too. Where the issue comes in is that Nostr apps are all interoperable. If you have more than one application, you're going to have both of them notifying you. Nostr users are known for having five or more Nostr apps that they use regularly. If all of them had notifications turned on, it would be a nightmare. So maybe you limit it to only one of your Nostr apps having notifications turned on, but then you are pretty well locked-in to opening that particular app when you tap on the notification.

Pokey, by nostr:npub1v3tgrwwsv7c6xckyhm5dmluc05jxd4yeqhpxew87chn0kua0tjzqc6yvjh, solves this issue, allowing you to turn notifications off for all of your Nostr apps, and have Pokey handle them all for you. Then, when you tap on a Pokey notification, you can choose which Nostr app to open it in.

Pokey also gives you control over the types of things you want to be notified about. Maybe you don't care about reactions, and you just want to know about zaps, comments, and direct messages. Pokey has you covered. It even supports multiple accounts, so you can get notifications for all the npubs you control.

One of the most unique and incredibly fun aspects of Nostr is the ability to send and receive #zaps. Instead of merely giving someone a 👍️ when you like something they said, you can actually send them real value in the form of sats, small portions of a Bitcoin. There is nothing quite like the experience of receiving your first zap and realizing that someone valued what you said enough to send you a small amount (and sometimes not so small) of #Bitcoin, the best money mankind has ever known.

To be able to have that experience, though, you are going to need a wallet that can send and receive zaps, and preferably one that is easy to connect to Nostr applications. My current preference for that is Alby Hub, but not everyone wants to deal with all that comes along with running a #Lightning node. That being the case, I have opted to use nostr:npub1h2qfjpnxau9k7ja9qkf50043xfpfy8j5v60xsqryef64y44puwnq28w8ch for this tutorial, because they offer one of the easiest wallets to set up, and it connects to most Nostr apps by just copy/pasting a connection string from the settings in the wallet into the settings in your Nostr app of choice.

Additionally, even though #Coinos is a custodial wallet, you can have it automatically transfer any #sats over a specified threshold to a separate wallet, allowing you to mitigate the custodial risk without needing to keep an eye on your balance and make the transfer manually.

Most of us on Android are used to getting all of our mobile apps from one souce: the Google Play Store. That's not possible for this tutorial series. Only one of the apps mentioned above is available in Google's permissioned playground. However, on Android we have the advantage of being able to install whatever we want on our device, just by popping into our settings and flipping a toggle. Indeed, thumbing our noses at big-tech is at the heart of the Nostr ethos, so why would we make ourselves beholden to Google for installing Nostr apps?

The nostr:npub10r8xl2njyepcw2zwv3a6dyufj4e4ajx86hz6v4ehu4gnpupxxp7stjt2p8 is an alternative app store made by nostr:npub1wf4pufsucer5va8g9p0rj5dnhvfeh6d8w0g6eayaep5dhps6rsgs43dgh9 as a resource for all sorts of open-source apps, but especially Nostr apps. What is more, you can log in with Amber, connect a wallet like Coinos, and support the developers of your favorite Nostr apps directly within the #Zapstore by zapping their app releases.

One of the biggest features of the Zapstore is the fact that developers can cryptographically sign their app releases using their Nostr keys, so you know that the app you are downloading is the one they actually released and hasn't been altered in any way. The Zapstore will warn you and won't let you install the app if the signature is invalid.

Getting Started

Since the Zapstore will be the source we use for installing most of the other apps mentioned, we will start with installing the Zapstore.

We will then use the Zapstore to install Amber and set it up with our Nostr account, either by creating a new private key, or by importing one we already have. We'll also use it to log into the Zapstore.

Next, we will install Amethyst from the Zapstore and log into it via Amber.

After this, we will install Citrine from the Zapstore and add it as a local relay on Amethyst.

Because we want to be able to send and receive zaps, we will set up a wallet with CoinOS and connect it to Amethyst and the Zapstore using Nostr Wallet Connect.

Finally, we will install Pokey using the Zapstore, log into it using Amber, and set up the notifications we want to receive.

By the time you are done with this series, you will have a great head-start on your Nostr journey compared to muddling through it all on your own. Moreover, you will have developed a familiarity with how things generally work on Nostr that can be applied to other apps you try out in the future.

Continue to Part 2: The Zapstore. Nostr Link: nostr:naddr1qvzqqqr4gupzpde8f55w86vrhaeqmd955y4rraw8aunzxgxstsj7eyzgntyev2xtqydhwumn8ghj7un9d3shjtnzwf5kw6r5vfhkcapwdejhgtcqp5cnwdphxv6rwwp3xvmnzvqgty5au

@ 21335073:a244b1ad

Someone asked for my thoughts, so I’ll share them thoughtfully. I’m not here to dictate how to promote Nostr—I’m still learning about it myself. While I’m not new to Nostr, freedom tech is a newer space for me. I’m skilled at advocating for topics I deeply understand, but freedom tech isn’t my expertise, so take my words with a grain of salt. Nothing I say is set in stone.

Those who need Nostr the most are the ones most vulnerable to censorship on other platforms right now. Reaching them requires real-time awareness of global issues and the dynamic relationships between governments and tech providers, which can shift suddenly. Effective Nostr promoters must grasp this and adapt quickly.

The best messengers are people from or closely tied to these at-risk regions—those who truly understand the local political and cultural dynamics. They can connect with those in need when tensions rise. Ideal promoters are rational, trustworthy, passionate about Nostr, but above all, dedicated to amplifying people’s voices when it matters most.

Forget influencers, corporate-backed figures, or traditional online PR—it comes off as inauthentic, corny, desperate and forced. Nostr’s promotion should be grassroots and organic, driven by a few passionate individuals who believe in Nostr and the communities they serve.

The idea that “people won’t join Nostr due to lack of reach” is nonsense. Everyone knows X’s “reach” is mostly with bots. If humans want real conversations, Nostr is the place. X is great for propaganda, but Nostr is for the authentic voices of the people.

Those spreading Nostr must be so passionate they’re willing to onboard others, which is time-consuming but rewarding for the right person. They’ll need to make Nostr and onboarding a core part of who they are. I see no issue with that level of dedication. I’ve been known to get that way myself at times. It’s fun for some folks.

With love, I suggest not adding Bitcoin promotion with Nostr outreach. Zaps already integrate that element naturally. (Still promote within the Bitcoin ecosystem, but this is about reaching vulnerable voices who needed Nostr yesterday.)

To promote Nostr, forget conventional strategies. “Influencers” aren’t the answer. “Influencers” are not the future. A trusted local community member has real influence—reach them. Connect with people seeking Nostr’s benefits but lacking the technical language to express it. This means some in the Nostr community might need to step outside of the Bitcoin bubble, which is uncomfortable but necessary. Thank you in advance to those who are willing to do that.

I don’t know who is paid to promote Nostr, if anyone. This piece isn’t shade. But it’s exhausting to see innocent voices globally silenced on corporate platforms like X while Nostr exists. Last night, I wondered: how many more voices must be censored before the Nostr community gets uncomfortable and thinks creatively to reach the vulnerable?

A warning: the global need for censorship-resistant social media is undeniable. If Nostr doesn’t make itself known, something else will fill that void. Let’s start this conversation.

@ 51bbb15e:b77a2290

Yeah, I’m sure everything in the file is legit. 👍 Let’s review the guard witness testimony…Oh wait, they weren’t at their posts despite 24/7 survellience instructions after another Epstein “suicide” attempt two weeks earlier. Well, at least the video of the suicide is in the file? Oh wait, a techical glitch. Damn those coincidences!

At this point, the Trump administration has zero credibility with me on anything related to the Epstein case and his clients. I still suspect the administration is using the Epstein files as leverage to keep a lot of RINOs in line, whereas they’d be sabotaging his agenda at every turn otherwise. However, I just don’t believe in ends-justify-the-means thinking. It’s led almost all of DC to toss out every bit of the values they might once have had.

@ a0e937b7:50db609a

Because we are not merely addicted to #Narrativium: It is our drive, imbued into our very essence. And it is so much easier to absorb our daily dose from the billions of trickles provided by everyone else as a substitute drug #Gossipium, or temporarily saturate our unquenchable thirst by just giving in to the temptation by the incessable stream of Movies and Series providing #Fictionium than it is to find a properly satisfying Source Of Narrativium (acronymize that 😉), let alone create our own Narrativium that might even be worthy of sharing. And yet, there is so much more fulfilment possible by letting one's creativity work instead of merely using a "share" button - which briefly seems to trick the human brain into believing that one has actually participated in providing one's peers with proper Narrativium, possibly as part of an implicit social contract: "I give you all some Narrativium I found, now give me more in return". It is such a trivial action to take, even more effortless than gossiping. But let's be honest, it often just feels hollow. And even when we write something, it is again tempting to just create #Rantium instead of something actually useful.

Gossypium herbaceum, the cotton plant (Photo by H. Zell from Wikipedia)

Originally I merely wanted to post a witty quote from https://wiki.lspace.org/mediawiki/Narrativium about Narrativium on Facebook:

"Humans add narrativium to their world. They insist on interpreting the universe as if it's telling a story. This leads them to focus on facts that fit the story, while ignoring those that don't." - T. Pratchett, I. Steward, J. Cohen, The Science of Discworld I

Maybe even subtly allude to how that might explain quite a lot about the everyday insanity that seems to surround us, especially these days.

"We are not Homo sapiens, Wise Man. We are the third chimpanzee. [...] We are Pan narrans, the storytelling ape. [...] if you understand the power of story, and learn to detect abuses of it, you might actually deserve the appellation Homo sapiens." - T. Pratchett, I. Steward, J. Cohen, The Science of Discworld II

Really. I was just going to quote a bit and go on about my day with some meaningless procrastination. Why already bother with housework when I can delay that until tomorrow or the day after and just watch some series in the Arrowverse now? But after ten minutes of a Legends of Tomorrow episode called "Lucha de Apuestas", curiosity got the better of me. What is it with Luchadores and their masks, I mockingly wondered. So I read Wikipedia on it. Lots of culture, history and, most importantly to me, Narrativium. I probably couldn't care less for to guys bumping fists on a stage, I don't really care about watching any sports either. But there's a certain fascination to stories, isn't there? So I felt like sharing about Narrativium, and here we are.

—

That's it for now, I might keep writing on this. One day. Just as I keep continuing writing everything else I start. Not. Well, motivate me.

@ a39d19ec:3d88f61e

Die Debatte um Migration, Grenzsicherung und Abschiebungen wird in Deutschland meist emotional geführt. Wer fordert, dass illegale Einwanderer abgeschoben werden, sieht sich nicht selten dem Vorwurf des Rassismus ausgesetzt. Doch dieser Vorwurf ist nicht nur sachlich unbegründet, sondern verkehrt die Realität ins Gegenteil: Tatsächlich sind es gerade diejenigen, die hinter jeder Forderung nach Rechtssicherheit eine rassistische Motivation vermuten, die selbst in erster Linie nach Hautfarbe, Herkunft oder Nationalität urteilen.

Das Recht steht über Emotionen

Deutschland ist ein Rechtsstaat. Das bedeutet, dass Regeln nicht nach Bauchgefühl oder politischer Stimmungslage ausgelegt werden können, sondern auf klaren gesetzlichen Grundlagen beruhen müssen. Einer dieser Grundsätze ist in Artikel 16a des Grundgesetzes verankert. Dort heißt es:

„Auf Absatz 1 [Asylrecht] kann sich nicht berufen, wer aus einem Mitgliedstaat der Europäischen Gemeinschaften oder aus einem anderen Drittstaat einreist, in dem die Anwendung des Abkommens über die Rechtsstellung der Flüchtlinge und der Europäischen Menschenrechtskonvention sichergestellt ist.“

Das bedeutet, dass jeder, der über sichere Drittstaaten nach Deutschland einreist, keinen Anspruch auf Asyl hat. Wer dennoch bleibt, hält sich illegal im Land auf und unterliegt den geltenden Regelungen zur Rückführung. Die Forderung nach Abschiebungen ist daher nichts anderes als die Forderung nach der Einhaltung von Recht und Gesetz.

Die Umkehrung des Rassismusbegriffs

Wer einerseits behauptet, dass das deutsche Asyl- und Aufenthaltsrecht strikt durchgesetzt werden soll, und andererseits nicht nach Herkunft oder Hautfarbe unterscheidet, handelt wertneutral. Diejenigen jedoch, die in einer solchen Forderung nach Rechtsstaatlichkeit einen rassistischen Unterton sehen, projizieren ihre eigenen Denkmuster auf andere: Sie unterstellen, dass die Debatte ausschließlich entlang ethnischer, rassistischer oder nationaler Kriterien geführt wird – und genau das ist eine rassistische Denkweise.

Jemand, der illegale Einwanderung kritisiert, tut dies nicht, weil ihn die Herkunft der Menschen interessiert, sondern weil er den Rechtsstaat respektiert. Hingegen erkennt jemand, der hinter dieser Kritik Rassismus wittert, offenbar in erster Linie die „Rasse“ oder Herkunft der betreffenden Personen und reduziert sie darauf.

Finanzielle Belastung statt ideologischer Debatte

Neben der rechtlichen gibt es auch eine ökonomische Komponente. Der deutsche Wohlfahrtsstaat basiert auf einem Solidarprinzip: Die Bürger zahlen in das System ein, um sich gegenseitig in schwierigen Zeiten zu unterstützen. Dieser Wohlstand wurde über Generationen hinweg von denjenigen erarbeitet, die hier seit langem leben. Die Priorität liegt daher darauf, die vorhandenen Mittel zuerst unter denjenigen zu verteilen, die durch Steuern, Sozialabgaben und Arbeit zum Erhalt dieses Systems beitragen – nicht unter denen, die sich durch illegale Einreise und fehlende wirtschaftliche Eigenleistung in das System begeben.

Das ist keine ideologische Frage, sondern eine rein wirtschaftliche Abwägung. Ein Sozialsystem kann nur dann nachhaltig funktionieren, wenn es nicht unbegrenzt belastet wird. Würde Deutschland keine klaren Regeln zur Einwanderung und Abschiebung haben, würde dies unweigerlich zur Überlastung des Sozialstaates führen – mit negativen Konsequenzen für alle.

Sozialpatriotismus

Ein weiterer wichtiger Aspekt ist der Schutz der Arbeitsleistung jener Generationen, die Deutschland nach dem Zweiten Weltkrieg mühsam wieder aufgebaut haben. Während oft betont wird, dass die Deutschen moralisch kein Erbe aus der Zeit vor 1945 beanspruchen dürfen – außer der Verantwortung für den Holocaust –, ist es umso bedeutsamer, das neue Erbe nach 1945 zu respektieren, das auf Fleiß, Disziplin und harter Arbeit beruht. Der Wiederaufbau war eine kollektive Leistung deutscher Menschen, deren Früchte nicht bedenkenlos verteilt werden dürfen, sondern vorrangig denjenigen zugutekommen sollten, die dieses Fundament mitgeschaffen oder es über Generationen mitgetragen haben.

Rechtstaatlichkeit ist nicht verhandelbar

Wer sich für eine konsequente Abschiebepraxis ausspricht, tut dies nicht aus rassistischen Motiven, sondern aus Respekt vor der Rechtsstaatlichkeit und den wirtschaftlichen Grundlagen des Landes. Der Vorwurf des Rassismus in diesem Kontext ist daher nicht nur falsch, sondern entlarvt eine selektive Wahrnehmung nach rassistischen Merkmalen bei denjenigen, die ihn erheben.

@ c9badfea:610f861a

1. Install Sky Map (it's free and open source)
2. Launch the app and tap Accept, then tap OK
3. When asked to access the device's location, tap While Using The App
4. Tap somewhere on the screen to activate the menu, then tap ⁝ and select Settings
5. Disable Send Usage Statistics
6. Return to the main screen and enjoy stargazing!

ℹ️ Use the 🔍 icon in the upper toolbar to search for a specific celestial body, or tap the 👁️ icon to activate night mode

@ 9cb3545c:2ff47bca

Introduction

Public companies that hold Bitcoin on behalf of investors (often issuing securities backed by those Bitcoin holdings) have faced growing pressure to demonstrate proof of reserves – evidence that they genuinely hold the cryptocurrency they claim. One approach is to publish the company’s Bitcoin wallet addresses so that anyone can verify the balances on the blockchain. This practice gained momentum after high-profile crypto collapses (e.g. FTX in 2022) eroded trust, leading major exchanges and fund issuers like Binance, Kraken, OKX, and Bitwise to publicize wallet addresses as proof of assets . The goal is transparency and reassurance for investors. However, making wallet addresses public comes with significant security and privacy risks. This report examines those risks – from cybersecurity threats and blockchain tracing to regulatory and reputational implications – and weighs them against the transparency benefits of on-chain proof of reserves.

Proof of Reserves via Public Wallet Addresses

In the cryptocurrency ethos of “don’t trust – verify,” on-chain proof of reserves is seen as a powerful tool. By disclosing wallet addresses (or cryptographic attestations of balances), a company lets investors and analysts independently verify that the Bitcoin reserves exist on-chain. For example, some firms have dashboards showing their addresses and balances in real time . In theory, this transparency builds trust by proving assets are not being misreported or misused. Shareholders gain confidence that the company’s Bitcoin holdings are intact, potentially preventing fraud or mismanagement.

Yet this approach essentially sacrifices the pseudonymity of blockchain transactions. Publishing a wallet address ties a large, known institution to specific on-chain funds. While Bitcoin addresses are public by design, most companies treat their specific addresses as sensitive information. Public proof-of-reserve disclosures break that anonymity, raising several concerns as detailed below.

Cybersecurity Threats from Visible Wallet Balances

Revealing a wallet address with a large balance can make a company a prime target for hackers and cybercriminals. Knowing exactly where significant reserves are held gives attackers a clear blueprint. As Bitcoin advocate (and MicroStrategy Executive Chairman) Michael Saylor warned in 2025, “publicly known wallet addresses become prime targets for malicious actors. Knowing where significant reserves are held provides hackers with a clear target, potentially increasing the risk of sophisticated attacks” . In other words, publishing the address increases the attack surface – attackers might intensify phishing campaigns, malware deployment, or insider bribery aimed at obtaining the keys or access to those wallets.

Even if the wallets are secured in cold storage, a public address advertisement may encourage attempts to penetrate the organization’s security. Custodians and partners could also be targeted. Saylor noted that this exposure isn’t just risky for the company holding the Bitcoin; it can indirectly put their custodial providers and related exchanges at risk as well . For instance, if a third-party custodian manages the wallets, hackers might attempt to breach that custodian knowing the reward (the company’s Bitcoin) is great.

Companies themselves have acknowledged these dangers. Grayscale Investments, which runs the large Grayscale Bitcoin Trust (GBTC), pointedly refused to publish its wallet addresses in late 2022, citing “security concerns” and complex custody arrangements that have “kept our investors’ assets safe for years” . Grayscale implied that revealing on-chain addresses could undermine those security measures, and it chose not to “circumvent complex security arrangements” just to appease public demand . This highlights a key point: corporate treasury security protocols often assume wallet details remain confidential. Publicizing them could invalidate certain assumptions (for example, if an address was meant to be operationally secret, it can no longer serve that role once exposed).

Additionally, a publicly known trove of cryptocurrency might invite physical security threats. While not a purely “cyber” issue, if criminals know a particular company or facility controls a wallet with, say, thousands of Bitcoin, it could lead to threats against personnel (extortion or coercion to obtain keys). This is a less common scenario for large institutions (which typically have robust physical security), but smaller companies or key individuals could face elevated personal risk by being associated with huge visible crypto reserves.

In summary, cybersecurity experts consider public proof-of-reserve addresses a double-edged sword: transparency comes at the cost of advertising exactly where a fortune is held. As Saylor bluntly put it, “the conventional way of issuing proof of reserves today is actually insecure… This method undermines the security of the issuer, the custodian, the exchanges and the investors. This is not a good idea”  . From a pure security standpoint, broadcasting your wallets is akin to drawing a bullseye on them.

Privacy Risks: Address Clustering and Blockchain Tracing

Blockchain data is public, so publishing addresses opens the door to unwanted analytics and loss of privacy for the business. Even without knowing the private keys, analysts can scrutinize every transaction in and out of those addresses. This enables address clustering – linking together addresses that interact – and other forms of blockchain forensics that can reveal sensitive information about the company’s activities.

One immediate risk is that observers can track the company’s transaction patterns. For example, if the company moves Bitcoin from its reserve address to an exchange or to another address, that move is visible in real time. Competitors, investors, or even attackers could deduce strategic information: perhaps the company is planning to sell (if coins go to an exchange wallet) or is reallocating funds. A known institution’s on-chain movements can thus “reveal strategic movements or holdings”, eroding the company’s operational privacy . In a volatile market, advance knowledge of a large buy or sell by a major player could even be exploited by others (front-running the market, etc.).

Publishing one or a few static addresses also violates a basic privacy principle of Bitcoin: address reuse. Best practice in Bitcoin is to use a fresh address for each transaction to avoid linking them  . If a company continuously uses the same “proof of reserve” address, all counterparties sending funds to or receiving funds from that address become visible. Observers could map out the company’s business relationships or vendors by analyzing counterparties. A Reddit user commenting on an ETF that published a single address noted that “reusing a single address for this makes me question their risk management… There are much better and more privacy-preserving ways to prove reserves… without throwing everything in a single public address” . In other words, a naive implementation of proof-of-reserve (one big address) maximizes privacy leakage.

Even if multiple addresses are used, if they are all disclosed, one can perform clustering analysis to find connections. This happened in the Grayscale case: although Grayscale would not confirm any addresses, community analysts traced and identified 432 addresses likely belonging to GBTC’s custodial holdings by following on-chain traces from known intermediary accounts . They managed to attribute roughly 317,705 BTC (about half of GBTC’s holdings) to those addresses . This demonstrates that even partial information can enable clustering – and if the company directly published addresses, the task becomes even easier to map the entirety of its on-chain asset base.

Another threat vector is “dusting” attacks, which become more feasible when an address is publicly known. In a dusting attack, an adversary sends a tiny amount of cryptocurrency (dust) to a target address. The dust itself is harmless, but if the target address ever spends that dust together with other funds, it can cryptographically link the target address to other addresses in the same wallet. Blockchain security researchers note that “with UTXO-based assets, an attacker could distribute dust to an address to reveal the owner’s other addresses by tracking the dust’s movement… If the owner unknowingly combines this dust with their funds in a transaction, the attacker can… link multiple addresses to a single owner”, compromising privacy . A company that publishes a list of reserve addresses could be systematically dusted by malicious actors attempting to map out all addresses under the company’s control. This could unmask cold wallet addresses that the company never intended to publicize, further eroding its privacy and security.

Investor confidentiality is another subtle concern. If the business model involves individual investor accounts or contributions (for instance, a trust where investors can deposit or withdraw Bitcoin), public addresses might expose those movements. An outside observer might not know which investor corresponds to a transaction, but unusual inflows/outflows could signal actions by big clients. In extreme cases, if an investor’s own wallet is known (say a large investor announces their involvement), one might link that to transactions in the company’s reserve addresses. This could inadvertently reveal an investor’s activities or holdings, breaching expectations of confidentiality. Even absent direct identification, some investors might simply be uncomfortable with their transactions being part of a publicly traceable ledger tied to the company.

In summary, publishing reserve addresses facilitates blockchain tracing that can pierce the veil of business privacy. It hands analysts the keys to observe how funds move, potentially exposing operational strategies, counterparties, and internal processes. As one industry publication noted, linking a large known institution to specific addresses can compromise privacy and reveal more than intended . Companies must consider whether they are ready for that level of transparency into their every on-chain move.

Regulatory and Compliance Implications

From a regulatory perspective, wallet address disclosure lies in uncharted territory, but it raises several flags. First and foremost is the issue of incomplete information: A wallet address only shows assets, not the company’s liabilities or other obligations. Regulators worry that touting on-chain holdings could give a false sense of security. The U.S. Securities and Exchange Commission (SEC) has cautioned investors to “not place too much confidence in the mere fact a company says it’s got a proof-of-reserves”, noting that such reports “lack sufficient information” for stakeholders to ascertain if liabilities can be met . In other words, a public company might show a big Bitcoin address balance, but if it has debts or customer liabilities of equal or greater value, the proof-of-reserve alone is “not necessarily an indicator that the company is in a good financial position” .

This regulatory stance implies that address disclosure, if done, must be paired with proper context. A public company would likely need to clarify in its financial statements or investor communications that on-chain reserves are unencumbered (not pledged as loan collateral, not already sold forward, etc.) and that total liabilities are accounted for. Otherwise, there’s a risk of misleading investors, which could have legal consequences. For example, if investors interpret the on-chain balance as proof of solvency but the company actually had leveraged those bitcoins for loans, lawsuits or regulatory enforcement could follow for misrepresentation.

There’s also a compliance burden associated with revealing addresses. Once an address is known to be the company’s, that company effectively must monitor all transactions related to it. If someone sends funds to that address (even without permission), the company might receive tainted coins (from hacked sources or sanctioned entities). This could trigger anti-money laundering (AML) red flags. Normally, compliance teams can ignore random deposits to unknown wallets, but they cannot ignore something sent into their publicly identified corporate wallet. Even a tiny dust amount sent from a blacklisted address could complicate compliance – for instance, the company would need to prove it has no relation to the sender and perhaps even avoid moving those tainted outputs. Being in the open increases such exposure. Threat actors might even exploit this by “poisoning” a company’s address with unwanted transactions, just to create regulatory headaches or reputational smears.

Another consideration is that custodial agreements and internal risk controls might forbid public disclosure of addresses. Many public companies use third-party custodians for their Bitcoin (for example, Coinbase Custody, BitGo, etc.). These custodians often treat wallet details as confidential for security. Grayscale noted that its Bitcoin are custodied on Coinbase and implied that revealing on-chain info would interfere with security arrangements  . It’s possible that some custodians would object to their clients broadcasting addresses, or might require additional assurances. A company going against such advice might be seen as negligent if something went wrong.

Regulators have so far not mandated on-chain proofs for public companies – in fact, recent laws have exempted public companies from proof-of-reserve mandates on the assumption they are already subject to rigorous SEC reporting. For example, a Texas bill in 2023 required crypto exchanges and custodians to provide quarterly proof-of-reserves to the state, but it “specifically carved out public reporting companies” since they already file audited financials with the SEC . The rationale was that between SEC filings and audits, public companies have oversight that private crypto firms lack . However, this also highlights a gap: even audited financials might not verify 100% of crypto assets (auditors often sample balances). Some observers noted that standard audits “may not ever include the 100% custodial asset testing contemplated by proof of reserves”, especially since quarterly SEC filings (10-Q) are often not audited . This puts public companies in a nuanced position – they are trusted to use traditional audits and internal controls, but the onus is on them if they choose to add extra transparency like on-chain proofs.

Finally, securities regulators focus on fair disclosure and accuracy. If a company publicly posts addresses, those essentially become investor disclosures subject to anti-fraud rules. The firm must keep them up to date and accurate. Any mistake (such as publishing a wrong address or failing to mention that some coins are locked up or lent out) could attract regulatory scrutiny for being misleading. In contrast, a formal audit or certification from a third-party comes with standards and disclaimers that are better understood by regulators. A self-published wallet list is an unprecedented form of disclosure that regulators haven’t fully vetted – meaning the company bears the risk if something is misinterpreted.

In summary, wallet address disclosure as proof-of-reserve must be handled very carefully to avoid regulatory pitfalls. The SEC and others have warned that on-chain assets alone don’t tell the whole story . Public companies would need to integrate such proofs with their official reporting in a responsible way – otherwise they risk confusion or even regulatory backlash for giving a false sense of security.

Reputational and Operational Risks

While transparency is meant to enhance reputation, in practice public wallet disclosures can create new reputational vulnerabilities. Once an address is public, a company’s every on-chain action is under the microscope of the crypto community and media. Any anomaly or perceived misstep can snowball into public relations problems.

One vivid example occurred with Crypto.com in late 2022. After the exchange published its cold wallet addresses to prove reserves (a move prompted by the FTX collapse), on-chain analysts quickly noticed a “suspicious transfer of 320,000 ETH” – about 82% of Crypto.com’s Ether reserves – moving from their cold wallet to another exchange (Gate.io)  . This large, unexpected transfer sparked immediate panic and FUD (fear, uncertainty, and doubt) on social media. Observers speculated that Crypto.com might be insolvent or was manipulating snapshots of reserves by borrowing funds. The CEO had to publicly respond, admitting it was an operational error – the ETH was supposed to go to a new cold storage address but ended up at a whitelisted external address by mistake . The funds were eventually returned, but not before reputational damage was done: the incident made headlines about mishandled funds and rattled user confidence  . This case illustrates how full public visibility can turn an internal slip-up into a highly public crisis. If the addresses had not been public, the mistake might have been quietly corrected; with on-chain transparency, there was nowhere to hide and no way to control the narrative before the public drew worst-case conclusions.

Even routine operations can be misinterpreted. Blockchain data lacks context – analysts may jump to conclusions that hurt a company’s reputation even if nothing is actually wrong. For instance, Binance (the world’s largest crypto exchange) encountered scrutiny when on-chain observers noted that one of its reserve wallets (labeled “Binance 8”) contained far more assets than it should have. This wallet was meant to hold collateral for Binance’s issued tokens, but held an excess balance, suggesting possible commingling of customer funds with collateral  . Bloomberg and others reported a ~$12.7 billion discrepancy visible on-chain . Binance had to acknowledge the issue as a “clerical error” and quickly separate the funds, all under the glare of public attention  . While Binance maintained that user assets were fully backed and the mistake was purely operational, the episode raised public concern over Binance’s practices, feeding a narrative that even the largest exchange had internal control lapses. The key point is that public proof-of-reserves made the lapse obvious to everyone, forcing a reactive explanation. The reputational hit (even if temporary) was an operational risk of being so transparent.

Additionally, strategic confidentiality is lost. If a company holding Bitcoin as a reserve asset decides to make a major move (say, reallocating to a different wallet, or using some Bitcoin for a strategic investment or loan), doing so with known addresses broadcasts that strategy. Competitors or market analysts can infer things like “Company X is moving 10% of its BTC — why? Are they selling? Hedging? Using it as collateral?” This can erode any competitive advantage of keeping financial strategies discreet. It might even affect the company’s stock price if investors interpret moves negatively. For example, if a blockchain analysis shows the company’s reserves dropping, shareholders might fear the company sold Bitcoin (perhaps due to financial distress), even if the reality is benign (like moving funds to a new custodian). The company would be forced into continuous public explanation of on-chain actions to prevent misunderstanding.

There’s also a risk of exposing business partnerships. Suppose the company uses certain exchanges or OTC desks to rebalance its holdings – transactions with those service providers will be visible and could link the company to them. If one of those partners has issues (say a hacked exchange or a sanctioned entity inadvertently), the company could be reputationally contaminated by association through the blockchain trail.

Finally, not all publicity is good publicity in the crypto world. A public proof-of-reserve might invite armchair auditors to scrutinize and criticize every aspect of the company’s crypto management. Minor issues could be blown out of proportion. On the flip side, if a company chooses not to publish addresses, it could face reputational risk from a different angle: skeptics might question why it isn’t being transparent. (Indeed, Grayscale’s refusal to disclose wallet addresses led to social media chatter about whether they truly held all the Bitcoin they claimed, contributing to investor nervousness and a steep discount on GBTC shares .) Thus, companies are in a delicate spot: share too much and every move invites scrutiny; share too little and you breed distrust.

Balancing Transparency Benefits vs. Risks

The central question is whether the benefit of proving reserve holdings to investors outweighs these security and privacy risks. It’s a classic risk-reward calculation, and opinions in the industry are divided.

On the side of transparency, many argue that the credibility and trust gained by proof-of-reserves is invaluable. Advocates note that Bitcoin was designed for open verification – “on-chain auditability and permissionless transparency” are core features . By embracing this, companies demonstrate they are good stewards of a “trustless” asset. In fact, some believe public companies have a duty to be extra transparent. A recent Nasdaq report contended that “when a publicly traded company holds Bitcoin but offers no visibility into how that Bitcoin is held or verified, it exposes itself to multiple levels of risk: legal, reputational, operational, and strategic”, undermining trust . In that view, opacity is riskier in the long run – a lack of proof could weaken investor confidence or invite regulatory suspicion. Shareholders and analysts may actually penalize a company that refuses to provide verifiable proof of its crypto assets .

Transparency done right can also differentiate a firm as a leader in governance. Publishing reserve data (whether via addresses or through third-party attestations) can be seen as a commitment to high standards. For example, Metaplanet, an investment firm, publicly discloses its BTC reserve addresses and even provides a live dashboard for anyone to verify balances . This proactive openness signals confidence and has been touted as an industry best practice in some quarters. By proving its reserves, a company can potentially avoid the fate of those that lost public trust (as happened with opaque crypto firms in 2022). It’s also a means to preempt false rumors – if data is out in the open, misinformation has less room to grow.

However, the pro-transparency camp increasingly acknowledges that there are smarter ways to achieve trust without courting all the risks. One compromise is using cryptographic proofs or audits instead of plain address dumps. For instance, exchanges like Kraken have implemented Merkle tree proof-of-reserves: an independent auditor verifies all customer balances on-chain and provides a cryptographic report, and customers can individually verify their account is included without the exchange revealing every address publicly. This method proves solvency to those who need to know without handing over a complete roadmap to attackers. Another emerging solution is zero-knowledge proofs, where a company can prove knowledge or ownership of certain assets without revealing the addresses or amounts to the public. These technologies are still maturing, but they aim to deliver the best of both worlds: transparency and privacy.

On the side of caution, many experts believe the risks of full public disclosure outweigh the incremental gain in transparency, especially for regulated public companies. Michael Saylor encapsulates this viewpoint: he calls on-chain proof-of-reserve “a bad idea” for institutions, arguing that it “offers one-way transparency” (assets only) and “leaves organizations open to cyberattacks” . He stresses that no serious security expert would advise a Fortune 500 company to list all its wallet addresses, as it essentially compromises corporate security over time . Saylor and others also point out the pointlessness of an assets-only proof: unless you also prove liabilities, showing off reserves might even be dangerous because it could lull investors into a false sense of security .

Regulators and traditional auditors echo this: proof-of-reserves, while a useful tool, “is not enough by itself” to guarantee financial health . They advocate for holistic transparency – audits that consider internal controls, liabilities, and legal obligations, not just a snapshot of a blockchain address  . From this perspective, a public company can satisfy transparency demands through rigorous third-party audits and disclosures rather than raw on-chain data. Indeed, public companies are legally bound to extensive reporting; adding public crypto addresses on top may be seen as redundant and risky.

There is also an implicit cost-benefit analysis: A successful attack resulting from over-sharing could be catastrophic (loss of funds, legal liability, reputational ruin), whereas the benefit of public proof is somewhat intangible (improved investor sentiment, which might be achieved via other assurance methods anyway). Given that trade-off, many firms err on the side of caution. As evidence, few if any U.S.-listed companies that hold Bitcoin have published their wallet addresses. Instead, they reference independent custodians and audits for assurance. Even crypto-native companies have pulled back on full transparency after realizing the downsides – for example, some auditing firms halted issuing proof-of-reserves reports due to concerns about how they were interpreted and the liability involved  .

Industry best practices are still evolving. A prudent approach gaining favor is to prove reserves without leaking sensitive details. This can involve disclosing total balances and having an auditor or blockchain oracle confirm the assets exist, but without listing every address publicly. Companies are also encouraged to disclose encumbrances (whether any of the reserves are collateralized or lent out) in tandem, to address the liabilities issue . By doing so, they aim to achieve transparency and maintain security.

In evaluating whether to publish wallet addresses, a company must ask: Will this level of openness meaningfully increase stakeholder trust, or would a more controlled disclosure achieve the same goal with less risk? For many public companies, the answer has been to avoid public addresses. The risks – from attracting hackers to revealing strategic moves – tend to outweigh the marginal transparency benefit in their judgment. The collapse of unregulated exchanges has certainly proven the value of reserve verification, but public companies operate in a different context with audits and legal accountability. Thus, the optimal solution may be a middle ground: proving reserves through vetted processes (auditor attestations, cryptographic proofs) that satisfy investor needs without blatantly exposing the company’s financial backend to the world.

Conclusion

Publishing Bitcoin wallet addresses as proof of reserves is a bold transparency measure – one that speaks to crypto’s ideals of open verification – but it comes with a laundry list of security considerations. Public companies weighing this approach must contend with the heightened cybersecurity threat of advertising their treasure troves to hackers, the loss of privacy and confidentiality as on-chain sleuths dissect their every transaction, and potential regulatory complications if such disclosures are misunderstood or incomplete. Real-world incidents illustrate the downsides: firms that revealed addresses have seen how quickly online communities flag (and sometimes misinterpret) their blockchain moves, causing reputational turbulence and forcing rapid damage control  .

On the other hand, proving reserves to investors is important – it can prevent fraud and bolster trust. The question is how to achieve it without incurring unacceptable risk. Many experts and industry leaders lean towards the view that simply publishing wallet addresses is too risky a method, especially for public companies with much to lose  . The risks often do outweigh the direct benefits in such cases. Transparency remains crucial, but it can be provided in safer ways – through regular audits, cryptographic proofs that don’t expose all wallet details, and comprehensive disclosures that include liabilities and controls.

In conclusion, while on-chain proof of reserves via public addresses offers a tantalizing level of openness, it must be approached with extreme caution. For most public companies, the smart strategy is to balance transparency with security: verify and show investors that assets exist and are sufficient, but do so in a controlled manner that doesn’t compromise the very assets you’re trying to protect. As the industry matures, we can expect more refined proof-of-reserve practices that satisfy the demand for honesty and solvency verification without unduly endangering the enterprise. Until then, companies will continue to tread carefully, mindful that transparency is only truly valuable when it doesn’t come at the price of security and trust.

Sources:

•   Grayscale statement on refusal to share on-chain proof-of-reserves 
•   Community analysis identifying Grayscale’s wallet addresses 
•   Cointelegraph – Crypto.com’s mistaken 320k ETH transfer spotted via on-chain proof-of-reserves  
•   Axios – Binance wallet “commingling” error observed on-chain  
•   Michael Saylor’s remarks on security risks of publishing wallet addresses   
•   SEC Acting Chief Accountant on limitations of proof-of-reserves reports 
•   Nasdaq (Bitcoin for Corporations) – argument for corporate transparency & proof-of-reserves   
•   1inch Security Blog – explanation of dusting attacks and privacy loss via address linking 

@ e844b39d:adafb6a2

I've been going so deep into black & white for a longer period now that I've totally forgotten about colours!

Actually that is how I felt when I started editing these, it was kinda too much haha

Grasshopper on our banana flower

This was to test my old Minolta 70-210/4 Beercan, even though the AF is slow it still locked in time to get this grasshopper!

I'm contemplating bringing this gear on the long trip instead of the old Nikon stuff, so gotta know it will do almost all sorts of jobs...

Random flower

I know that the pastel colours that I found using auto levels is in there, in the combination of the Sony A900 and the Beercan, which is one of the main reasons that I got it all around a decade ago.

Twig

Maybe too much? But still, these colours are in there, just gotta whack the files hard in post hehe

Sharpness is no problem

All of these are at f4, its sharp enough to tackle anything really.

Spider web

Of course this could be better technically, but it will do for almost anything I'll get across. Also this was manual focus, I didn't think the matte screen and viewfinder would make it possible to focus like this, never really tried before!

Amulet and my Nikon gear

I found a tiny amulet on the floor, of course its the cats that are responsible for that...

Zelda is happy

The A900 has built in stabilization, so any old lenses will get that by default! Which makes it far easier to get things like this right a around 1/4th of a second, even with that mirror clacking...

This one is with the Minolta 20/2.8, which is a lens I should really explore more. I got that and a 24/2.8 for a very low price, never had the time to use them much, and now I realize that they both can focus all the way down to 25 centimeters!

Now that is something I can use creatively, and on the road with ease...

I think this might end with me selling (dumping, really) my Nikon gear instead of this!

We'll find out soon 😁

@ 04c915da:3dfbecc9

This piece is the first in a series that will focus on things I think are a priority if your focus is similar to mine: building a strong family and safeguarding their future.

---

Choosing the ideal place to raise a family is one of the most significant decisions you will ever make. For simplicity sake I will break down my thought process into key factors: strong property rights, the ability to grow your own food, access to fresh water, the freedom to own and train with guns, and a dependable community.

A Jurisdiction with Strong Property Rights

Strong property rights are essential and allow you to build on a solid foundation that is less likely to break underneath you. Regions with a history of limited government and clear legal protections for landowners are ideal. Personally I think the US is the single best option globally, but within the US there is a wide difference between which state you choose. Choose carefully and thoughtfully, think long term. Obviously if you are not American this is not a realistic option for you, there are other solid options available especially if your family has mobility. I understand many do not have this capability to easily move, consider that your first priority, making movement and jurisdiction choice possible in the first place.

Abundant Access to Fresh Water

Water is life. I cannot overstate the importance of living somewhere with reliable, clean, and abundant freshwater. Some regions face water scarcity or heavy regulations on usage, so prioritizing a place where water is plentiful and your rights to it are protected is critical. Ideally you should have well access so you are not tied to municipal water supplies. In times of crisis or chaos well water cannot be easily shutoff or disrupted. If you live in an area that is drought prone, you are one drought away from societal chaos. Not enough people appreciate this simple fact.

Grow Your Own Food

A location with fertile soil, a favorable climate, and enough space for a small homestead or at the very least a garden is key. In stable times, a small homestead provides good food and important education for your family. In times of chaos your family being able to grow and raise healthy food provides a level of self sufficiency that many others will lack. Look for areas with minimal restrictions, good weather, and a culture that supports local farming.

Guns

The ability to defend your family is fundamental. A location where you can legally and easily own guns is a must. Look for places with a strong gun culture and a political history of protecting those rights. Owning one or two guns is not enough and without proper training they will be a liability rather than a benefit. Get comfortable and proficient. Never stop improving your skills. If the time comes that you must use a gun to defend your family, the skills must be instinct. Practice. Practice. Practice.

A Strong Community You Can Depend On

No one thrives alone. A ride or die community that rallies together in tough times is invaluable. Seek out a place where people know their neighbors, share similar values, and are quick to lend a hand. Lead by example and become a good neighbor, people will naturally respond in kind. Small towns are ideal, if possible, but living outside of a major city can be a solid balance in terms of work opportunities and family security.

---

Let me know if you found this helpful. My plan is to break down how I think about these five key subjects in future posts.

@ a39d19ec:3d88f61e

Nun da das deutsche Bundesregime den Ruin Deutschlands beschlossen hat, der sehr wahrscheinlich mit dem Werkzeug des Geld druckens "finanziert" wird, kamen mir so viele Gedanken zur Geldmengenausweitung, dass ich diese für einmal niedergeschrieben habe.

Die Ausweitung der Geldmenge führt aus klassischer wirtschaftlicher Sicht immer zu Preissteigerungen, weil mehr Geld im Umlauf auf eine begrenzte Menge an Gütern trifft. Dies lässt sich in mehreren Schritten analysieren:

1. Quantitätstheorie des Geldes

Die klassische Gleichung der Quantitätstheorie des Geldes lautet:

M • V = P • Y

wobei:
- M die Geldmenge ist,
- V die Umlaufgeschwindigkeit des Geldes,
- P das Preisniveau,
- Y die reale Wirtschaftsleistung (BIP).

Wenn M steigt und V sowie Y konstant bleiben, muss P steigen – also Inflation entstehen.

2. Gütermenge bleibt begrenzt

Die Menge an real produzierten Gütern und Dienstleistungen wächst meist nur langsam im Vergleich zur Ausweitung der Geldmenge. Wenn die Geldmenge schneller steigt als die Produktionsgütermenge, führt dies dazu, dass mehr Geld für die gleiche Menge an Waren zur Verfügung steht – die Preise steigen.

3. Erwartungseffekte und Spekulation

Wenn Unternehmen und Haushalte erwarten, dass mehr Geld im Umlauf ist, da eine zentrale Planung es so wollte, können sie steigende Preise antizipieren. Unternehmen erhöhen ihre Preise vorab, und Arbeitnehmer fordern höhere Löhne. Dies kann eine sich selbst verstärkende Spirale auslösen.

4. Internationale Perspektive

Eine erhöhte Geldmenge kann die Währung abwerten, wenn andere Länder ihre Geldpolitik stabil halten. Eine schwächere Währung macht Importe teurer, was wiederum Preissteigerungen antreibt.

5. Kritik an der reinen Geldmengen-Theorie

Der Vollständigkeit halber muss erwähnt werden, dass die meisten modernen Ökonomen im Staatsauftrag argumentieren, dass Inflation nicht nur von der Geldmenge abhängt, sondern auch von der Nachfrage nach Geld (z. B. in einer Wirtschaftskrise). Dennoch zeigt die historische Erfahrung, dass eine unkontrollierte Geldmengenausweitung langfristig immer zu Preissteigerungen führt, wie etwa in der Hyperinflation der Weimarer Republik oder in Simbabwe.

@ 90c656ff:9383fd4e

Since its creation, Bitcoin has been a revolutionary asset, challenging the traditional financial system and proposing a new form of decentralized money. However, its future remains uncertain and the subject of intense debate. Among the possible outcomes, two extreme scenarios stand out: hyperbitcoinization-where Bitcoin becomes the dominant currency in the global economy—and obsolescence, where the network loses relevance and is replaced by other solutions.

• Hyperbitcoinization: The World Adopts Bitcoin as a Monetary Standard

01 - Loss of trust in fiat currencies: Due to excessive money printing by central banks, many economies face rampant inflation. Bitcoin, with its fixed supply of 21 million units, emerges as a more trustworthy alternative.

02 - Growing adoption by companies and governments: Some countries have already begun integrating Bitcoin into their economies, accepting it for payments and as a store of value. If this trend continues, Bitcoin’s legitimacy as a global currency will grow.

03 - Ease of global transactions: Bitcoin enables fast and low-cost international transfers, removing the need for financial intermediaries and reducing operational costs.

04 - Technological advancements: Scalability improvements, such as the Lightning Network, can make Bitcoin more efficient for daily use, encouraging mass adoption.

If hyperbitcoinization becomes reality, the world may witness a radical shift in the financial system—with greater decentralization, censorship resistance, and an economy based on sound, predictable money.

• Obsolescence: Bitcoin Loses Relevance and Is Replaced

01 - Restrictive government regulations: If major economic powers enforce strict regulations on Bitcoin, adoption could slow, reducing its utility.

02 - Technological shortcomings or lack of innovation: Despite its security and decentralization, Bitcoin may struggle to scale effectively. If superior solutions emerge and gain acceptance, Bitcoin could lose its leading position.

03 - Competition from faster, more user-friendly alternatives: Other forms of digital money may surpass Bitcoin in scalability and usability, potentially leading to a decline in Bitcoin adoption.

04 - Decreasing miner incentives: As new Bitcoin issuance halves every four years, miners will rely increasingly on transaction fees. If those fees are insufficient to sustain network security, long-term viability could be at risk.

In summary, Bitcoin’s future could unfold along multiple paths, depending on factors like innovation, global adoption, and resilience to external challenges. Hyperbitcoinization would represent an economic revolution—ushering in a decentralized, inflation-resistant monetary system. Yet, obsolescence remains a risk if the network fails to adapt to future demands. Regardless of the outcome, Bitcoin has already made its mark on financial history, paving the way for a new era of digital money and economic freedom.

Thank you very much for reading this far. I hope everything is well with you, and sending a big hug from your favorite Bitcoiner maximalist from Madeira. Long live freedom!

@ 04c915da:3dfbecc9

Here’s a revised timeline of macro-level events from The Mandibles: A Family, 2029–2047 by Lionel Shriver, reimagined in a world where Bitcoin is adopted as a widely accepted form of money, altering the original narrative’s assumptions about currency collapse and economic control. In Shriver’s original story, the failure of Bitcoin is assumed amid the dominance of the bancor and the dollar’s collapse. Here, Bitcoin’s success reshapes the economic and societal trajectory, decentralizing power and challenging state-driven outcomes.

Part One: 2029–2032

• 2029 (Early Year)\ The United States faces economic strain as the dollar weakens against global shifts. However, Bitcoin, having gained traction emerges as a viable alternative. Unlike the original timeline, the bancor—a supranational currency backed by a coalition of nations—struggles to gain footing as Bitcoin’s decentralized adoption grows among individuals and businesses worldwide, undermining both the dollar and the bancor.

• 2029 (Mid-Year: The Great Renunciation)\ Treasury bonds lose value, and the government bans Bitcoin, labeling it a threat to sovereignty (mirroring the original bancor ban). However, a Bitcoin ban proves unenforceable—its decentralized nature thwarts confiscation efforts, unlike gold in the original story. Hyperinflation hits the dollar as the U.S. prints money, but Bitcoin’s fixed supply shields adopters from currency devaluation, creating a dual-economy split: dollar users suffer, while Bitcoin users thrive.

• 2029 (Late Year)\ Dollar-based inflation soars, emptying stores of goods priced in fiat currency. Meanwhile, Bitcoin transactions flourish in underground and online markets, stabilizing trade for those plugged into the bitcoin ecosystem. Traditional supply chains falter, but peer-to-peer Bitcoin networks enable local and international exchange, reducing scarcity for early adopters. The government’s gold confiscation fails to bolster the dollar, as Bitcoin’s rise renders gold less relevant.

• 2030–2031\ Crime spikes in dollar-dependent urban areas, but Bitcoin-friendly regions see less chaos, as digital wallets and smart contracts facilitate secure trade. The U.S. government doubles down on surveillance to crack down on bitcoin use. A cultural divide deepens: centralized authority weakens in Bitcoin-adopting communities, while dollar zones descend into lawlessness.

• 2032\ By this point, Bitcoin is de facto legal tender in parts of the U.S. and globally, especially in tech-savvy or libertarian-leaning regions. The federal government’s grip slips as tax collection in dollars plummets—Bitcoin’s traceability is low, and citizens evade fiat-based levies. Rural and urban Bitcoin hubs emerge, while the dollar economy remains fractured.

Time Jump: 2032–2047

• Over 15 years, Bitcoin solidifies as a global reserve currency, eroding centralized control. The U.S. government adapts, grudgingly integrating bitcoin into policy, though regional autonomy grows as Bitcoin empowers local economies.

Part Two: 2047

• 2047 (Early Year)\ The U.S. is a hybrid state: Bitcoin is legal tender alongside a diminished dollar. Taxes are lower, collected in BTC, reducing federal overreach. Bitcoin’s adoption has decentralized power nationwide. The bancor has faded, unable to compete with Bitcoin’s grassroots momentum.

• 2047 (Mid-Year)\ Travel and trade flow freely in Bitcoin zones, with no restrictive checkpoints. The dollar economy lingers in poorer areas, marked by decay, but Bitcoin’s dominance lifts overall prosperity, as its deflationary nature incentivizes saving and investment over consumption. Global supply chains rebound, powered by bitcoin enabled efficiency.

• 2047 (Late Year)\ The U.S. is a patchwork of semi-autonomous zones, united by Bitcoin’s universal acceptance rather than federal control. Resource scarcity persists due to past disruptions, but economic stability is higher than in Shriver’s original dystopia—Bitcoin’s success prevents the authoritarian slide, fostering a freer, if imperfect, society.

Key Differences

• Currency Dynamics: Bitcoin’s triumph prevents the bancor’s dominance and mitigates hyperinflation’s worst effects, offering a lifeline outside state control.
• Government Power: Centralized authority weakens as Bitcoin evades bans and taxation, shifting power to individuals and communities.
• Societal Outcome: Instead of a surveillance state, 2047 sees a decentralized, bitcoin driven world—less oppressive, though still stratified between Bitcoin haves and have-nots.

This reimagining assumes Bitcoin overcomes Shriver’s implied skepticism to become a robust, adopted currency by 2029, fundamentally altering the novel’s bleak trajectory.

@ 0d97beae:c5274a14

This article hopes to complement the article by Lyn Alden on YouTube: https://www.youtube.com/watch?v=jk_HWmmwiAs

The reason why we have broken money

Before the invention of key technologies such as the printing press and electronic communications, even such as those as early as morse code transmitters, gold had won the competition for best medium of money around the world.

In fact, it was not just gold by itself that became money, rulers and world leaders developed coins in order to help the economy grow. Gold nuggets were not as easy to transact with as coins with specific imprints and denominated sizes.

However, these modern technologies created massive efficiencies that allowed us to communicate and perform services more efficiently and much faster, yet the medium of money could not benefit from these advancements. Gold was heavy, slow and expensive to move globally, even though requesting and performing services globally did not have this limitation anymore.

Banks took initiative and created derivatives of gold: paper and electronic money; these new currencies allowed the economy to continue to grow and evolve, but it was not without its dark side. Today, no currency is denominated in gold at all, money is backed by nothing and its inherent value, the paper it is printed on, is worthless too.

Banks and governments eventually transitioned from a money derivative to a system of debt that could be co-opted and controlled for political and personal reasons. Our money today is broken and is the cause of more expensive, poorer quality goods in the economy, a larger and ever growing wealth gap, and many of the follow-on problems that have come with it.

Bitcoin overcomes the "transfer of hard money" problem

Just like gold coins were created by man, Bitcoin too is a technology created by man. Bitcoin, however is a much more profound invention, possibly more of a discovery than an invention in fact. Bitcoin has proven to be unbreakable, incorruptible and has upheld its ability to keep its units scarce, inalienable and counterfeit proof through the nature of its own design.

Since Bitcoin is a digital technology, it can be transferred across international borders almost as quickly as information itself. It therefore severely reduces the need for a derivative to be used to represent money to facilitate digital trade. This means that as the currency we use today continues to fare poorly for many people, bitcoin will continue to stand out as hard money, that just so happens to work as well, functionally, along side it.

Bitcoin will also always be available to anyone who wishes to earn it directly; even China is unable to restrict its citizens from accessing it. The dollar has traditionally become the currency for people who discover that their local currency is unsustainable. Even when the dollar has become illegal to use, it is simply used privately and unofficially. However, because bitcoin does not require you to trade it at a bank in order to use it across borders and across the web, Bitcoin will continue to be a viable escape hatch until we one day hit some critical mass where the world has simply adopted Bitcoin globally and everyone else must adopt it to survive.

Bitcoin has not yet proven that it can support the world at scale. However it can only be tested through real adoption, and just as gold coins were developed to help gold scale, tools will be developed to help overcome problems as they arise; ideally without the need for another derivative, but if necessary, hopefully with one that is more neutral and less corruptible than the derivatives used to represent gold.

Bitcoin blurs the line between commodity and technology

Bitcoin is a technology, it is a tool that requires human involvement to function, however it surprisingly does not allow for any concentration of power. Anyone can help to facilitate Bitcoin's operations, but no one can take control of its behaviour, its reach, or its prioritisation, as it operates autonomously based on a pre-determined, neutral set of rules.

At the same time, its built-in incentive mechanism ensures that people do not have to operate bitcoin out of the good of their heart. Even though the system cannot be co-opted holistically, It will not stop operating while there are people motivated to trade their time and resources to keep it running and earn from others' transaction fees. Although it requires humans to operate it, it remains both neutral and sustainable.

Never before have we developed or discovered a technology that could not be co-opted and used by one person or faction against another. Due to this nature, Bitcoin's units are often described as a commodity; they cannot be usurped or virtually cloned, and they cannot be affected by political biases.

The dangers of derivatives

A derivative is something created, designed or developed to represent another thing in order to solve a particular complication or problem. For example, paper and electronic money was once a derivative of gold.

In the case of Bitcoin, if you cannot link your units of bitcoin to an "address" that you personally hold a cryptographically secure key to, then you very likely have a derivative of bitcoin, not bitcoin itself. If you buy bitcoin on an online exchange and do not withdraw the bitcoin to a wallet that you control, then you legally own an electronic derivative of bitcoin.

Bitcoin is a new technology. It will have a learning curve and it will take time for humanity to learn how to comprehend, authenticate and take control of bitcoin collectively. Having said that, many people all over the world are already using and relying on Bitcoin natively. For many, it will require for people to find the need or a desire for a neutral money like bitcoin, and to have been burned by derivatives of it, before they start to understand the difference between the two. Eventually, it will become an essential part of what we regard as common sense.

Learn for yourself

If you wish to learn more about how to handle bitcoin and avoid derivatives, you can start by searching online for tutorials about "Bitcoin self custody".

There are many options available, some more practical for you, and some more practical for others. Don't spend too much time trying to find the perfect solution; practice and learn. You may make mistakes along the way, so be careful not to experiment with large amounts of your bitcoin as you explore new ideas and technologies along the way. This is similar to learning anything, like riding a bicycle; you are sure to fall a few times, scuff the frame, so don't buy a high performance racing bike while you're still learning to balance.

@ 90c656ff:9383fd4e

Since its creation, Bitcoin has been much more than just an alternative to traditional money. With the ongoing digitalization of the global economy, Bitcoin has emerged as a foundational pillar for new forms of transactions, commerce, and value storage. Its decentralization, transparency, and censorship resistance make it a solid base for digital economies, where financial interactions occur without the need for traditional intermediaries.

• Bitcoin’s role in the digital economy

01 - Global, borderless transactions: Anyone with internet access can send and receive Bitcoin without needing a bank or government authorization.

02 - Limited and predictable supply: Unlike fiat currencies that can be inflated by central banks, Bitcoin has a fixed cap of 21 million units, making it a scarce and reliable asset.

03 - Security and transparency: The Bitcoin blockchain or timechain publicly records all transactions, ensuring a secure and auditable system.

04 - Censorship resistance: No government or institution can block Bitcoin transactions, enabling a freer and more accessible digital economy.

With these characteristics, Bitcoin is already transforming various economic sectors and driving new forms of commerce and investment.

• Bitcoin in digital commerce and the global economy

01 - E-commerce: Businesses and consumers can use Bitcoin for fast international transactions without exorbitant fees.

02 - International remittances: Workers sending money to their home countries can avoid high fees and long delays by using Bitcoin.

03 - Emerging economies: In countries with unstable currencies and unreliable banking systems, Bitcoin serves as a secure and decentralized alternative for storing wealth and conducting daily transactions.

Additionally, Bitcoin is being adopted by companies and even governments as a store of value, reinforcing its role as a foundation for the digital economy of the future.

• Challenges and adapting to the new economy

01 - Price volatility: Bitcoin’s fluctuating value can make it difficult to use as a daily medium of exchange.

02 - Regulations and governmental resistance: Some countries attempt to restrict or regulate Bitcoin to maintain control over the traditional financial system.

03 - Education and adoption: Many people still lack the knowledge to use Bitcoin safely and effectively.

In summary, Bitcoin is transforming the way the world interacts with money, offering a decentralized and transparent alternative for digital economies. As more individuals and businesses adopt Bitcoin for payments, savings, and global commerce, its impact becomes increasingly clear. Despite the challenges, Bitcoin continues to solidify its place as the foundation of a new economic paradigm—where financial freedom and technological innovation go hand in hand.

Thank you very much for reading this far. I hope everything is well with you, and sending a big hug from your favorite Bitcoiner maximalist from Madeira. Long live freedom!

@ 37fe9853:bcd1b039

yoyoaa

@ 6ad3e2a3:c90b7740

I’ve written about MSTR twice already, https://www.chrisliss.com/p/mstr and https://www.chrisliss.com/p/mstr-part-2, but I want to focus on legendary short seller James Chanos’ current trade wherein he buys bitcoin (via ETF) and shorts MSTR, in essence to “be like Mike” Saylor who sells MSTR shares at the market and uses them to add bitcoin to the company’s balance sheet. After all, if it’s good enough for Saylor, why shouldn’t everyone be doing it — shorting a company whose stock price is more than 2x its bitcoin holdings and using the proceeds to buy the bitcoin itself?

Saylor himself has said selling shares at 2x NAV (net asset value) to buy bitcoin is like selling dollars for two dollars each, and Chanos has apparently decided to get in while the getting (market cap more than 2x net asset value) is good. If the price of bitcoin moons, sending MSTR’s shares up, you are more than hedged in that event, too. At least that’s the theory.

The problem with this bet against MSTR’s mNAV, i.e., you are betting MSTR’s market cap will converge 1:1 toward its NAV in the short and medium term is this trade does not exist in a vacuum. Saylor has described how his ATM’s (at the market) sales of shares are accretive in BTC per share because of this very premium they carry. Yes, we’ll dilute your shares of the company, but because we’re getting you 2x the bitcoin per share, you are getting an ever smaller slice of an ever bigger overall pie, and the pie is growing 2x faster than your slice is reducing. (I https://www.chrisliss.com/p/mstr how this works in my first post.)

But for this accretion to continue, there must be a constant supply of “greater fools” to pony up for the infinitely printable shares which contain only half their value in underlying bitcoin. Yes, those shares will continue to accrete more BTC per share, but only if there are more fools willing to make this trade in the future. So will there be a constant supply of such “fools” to keep fueling MSTR’s mNAV multiple indefinitely?

Yes, there will be in my opinion because you have to look at the trade from the prospective fools’ perspective. Those “fools” are not trading bitcoin for MSTR, they are trading their dollars, selling other equities to raise them maybe, but in the end it’s a dollars for shares trade. They are not selling bitcoin for them.

You might object that those same dollars could buy bitcoin instead, so they are surely trading the opportunity cost of buying bitcoin for them, but if only 5-10 percent of the market (or less) is buying bitcoin itself, the bucket in which which those “fools” reside is the entire non-bitcoin-buying equity market. (And this is not considering the even larger debt market which Saylor has yet to tap in earnest.)

So for those 90-95 percent who do not and are not presently planning to own bitcoin itself, is buying MSTR a fool’s errand, so to speak? Not remotely. If MSTR shares are infinitely printable ATM, they are still less so than the dollar and other fiat currencies. And MSTR shares are backed 2:1 by bitcoin itself, while the fiat currencies are backed by absolutely nothing. So if you hold dollars or euros, trading them for MSTR shares is an errand more sage than foolish.

That’s why this trade (buying BTC and shorting MSTR) is so dangerous. Not only are there many people who won’t buy BTC buying MSTR, there are many funds and other investment entities who are only able to buy MSTR.

Do you want to get BTC at 1:1 with the 5-10 percent or MSTR backed 2:1 with the 90-95 percent. This is a bit like medical tests that have a 95 percent accuracy rate for an asymptomatic disease that only one percent of the population has. If someone tests positive, it’s more likely to be a false one than an indication he has the disease*. The accuracy rate, even at 19:1, is subservient to the size of the respective populations.

At some point this will no longer be the case, but so long as the understanding of bitcoin is not widespread, so long as the dollar is still the unit of account, the “greater fools” buying MSTR are still miles ahead of the greatest fools buying neither, and the stock price and mNAV should only increase.

. . .

One other thought: it’s more work to play defense than offense because the person on offense knows where he’s going, and the defender can only react to him once he moves. Similarly, Saylor by virtue of being the issuer of the shares knows when more will come online while Chanos and other short sellers are borrowing them to sell in reaction to Saylor’s strategy. At any given moment, Saylor can pause anytime, choosing to issue convertible debt or preferred shares with which to buy more bitcoin, and the shorts will not be given advance notice.

If the price runs, and there is no ATM that week because Saylor has stopped on a dime, so to speak, the shorts will be left having to scramble to change directions and buy the shares back to cover. Their momentum might be in the wrong direction, though, and like Allen Iverson breaking ankles with a crossover, Saylor might trigger a massive short squeeze, rocketing the share price ever higher. That’s why he actually welcomes Chanos et al trying this copycat strategy — it becomes the fuel for outsized gains.

For that reason, news that Chanos is shorting MSTR has not shaken my conviction, though there are other more pertinent https://www.chrisliss.com/p/mstr-part-2 with MSTR, of which one should be aware. And as always, do your own due diligence before investing in anything.

* To understand this, consider a population of 100,000, with one percent having a disease. That means 1,000 have it, 99,000 do not. If the test is 95 percent accurate, and everyone is tested, 950 of the 1,000 will test positive (true positives), 50 who have it will test negative (false negatives.) Of the positives, 95 percent of 99,000 (94,050) will test negative (true negatives) and five percent (4,950) will test positive (false positives). That means 4,950 out of 5,900 positives (84%) will be false.

@ cefb08d1:f419beff

Gabriela Bryan vs Caitlin Simmers | Western Australia Margaret River Pro 2025 - Final

https://www.youtube.com/watch?v=2GK8l3RPqmE

Jordy Smith vs Griffin Colapinto | Western Australia Margaret River Pro 2025 - Final

https://www.youtube.com/watch?v=zGWMVDwU_is

Highlights: Western Australia Margaret River Pro 2025 - All the Highlights

https://www.youtube.com/watch?v=32055IXrtnU

Ranking WSL Women:

Ranking WSL Men:

Source: https://www.worldsurfleague.com/athletes/tour/wct?year=2025

https://stacker.news/items/990198

@ 34f1ddab:2ca0cf7c

Losing access to your cryptocurrency can feel like losing a part of your future. Whether it’s due to a forgotten password, a damaged seed backup, or a simple mistake in a transfer, the stress can be overwhelming. Fortunately, cryptrecver.com is here to assist! With our expert-led recovery services, you can safely and swiftly reclaim your lost Bitcoin and other cryptocurrencies.

Why Trust Crypt Recver? 🤝 🛠️ Expert Recovery Solutions At Crypt Recver, we specialize in addressing complex wallet-related issues. Our skilled engineers have the tools and expertise to handle:

Partially lost or forgotten seed phrases Extracting funds from outdated or invalid wallet addresses Recovering data from damaged hardware wallets Restoring coins from old or unsupported wallet formats You’re not just getting a service; you’re gaining a partner in your cryptocurrency journey.

🚀 Fast and Efficient Recovery We understand that time is crucial in crypto recovery. Our optimized systems enable you to regain access to your funds quickly, focusing on speed without compromising security. With a success rate of over 90%, you can rely on us to act swiftly on your behalf.

🔒 Privacy is Our Priority Your confidentiality is essential. Every recovery session is conducted with the utmost care, ensuring all processes are encrypted and confidential. You can rest assured that your sensitive information remains private.

💻 Advanced Technology Our proprietary tools and brute-force optimization techniques maximize recovery efficiency. Regardless of how challenging your case may be, our technology is designed to give you the best chance at retrieving your crypto.

Our Recovery Services Include: 📈 Bitcoin Recovery: Lost access to your Bitcoin wallet? We help recover lost wallets, private keys, and passphrases. Transaction Recovery: Mistakes happen — whether it’s an incorrect wallet address or a lost password, let us manage the recovery. Cold Wallet Restoration: If your cold wallet is failing, we can safely extract your assets and migrate them into a secure new wallet. Private Key Generation: Lost your private key? Our experts can help you regain control using advanced methods while ensuring your privacy. ⚠️ What We Don’t Do While we can handle many scenarios, some limitations exist. For instance, we cannot recover funds stored in custodial wallets or cases where there is a complete loss of four or more seed words without partial information available. We are transparent about what’s possible, so you know what to expect

Don’t Let Lost Crypto Hold You Back! Did you know that between 3 to 3.4 million BTC — nearly 20% of the total supply — are estimated to be permanently lost? Don’t become part of that statistic! Whether it’s due to a forgotten password, sending funds to the wrong address, or damaged drives, we can help you navigate these challenges

🛡️ Real-Time Dust Attack Protection Our services extend beyond recovery. We offer dust attack protection, keeping your activity anonymous and your funds secure, shielding your identity from unwanted tracking, ransomware, and phishing attempts.

🎉 Start Your Recovery Journey Today! Ready to reclaim your lost crypto? Don’t wait until it’s too late! 👉 cryptrecver.com

📞 Need Immediate Assistance? Connect with Us! For real-time support or questions, reach out to our dedicated team on: ✉️ Telegram: t.me/crypptrcver 💬 WhatsApp: +1(941)317–1821

Crypt Recver is your trusted partner in cryptocurrency recovery. Let us turn your challenges into victories. Don’t hesitate — your crypto future starts now! 🚀✨

Act fast and secure your digital assets with cryptrecver.com.Losing access to your cryptocurrency can feel like losing a part of your future. Whether it’s due to a forgotten password, a damaged seed backup, or a simple mistake in a transfer, the stress can be overwhelming. Fortunately, cryptrecver.com is here to assist! With our expert-led recovery services, you can safely and swiftly reclaim your lost Bitcoin and other cryptocurrencies.

# Why Trust Crypt Recver? 🤝

🛠️ Expert Recovery Solutions\ At Crypt Recver, we specialize in addressing complex wallet-related issues. Our skilled engineers have the tools and expertise to handle:

• Partially lost or forgotten seed phrases
• Extracting funds from outdated or invalid wallet addresses
• Recovering data from damaged hardware wallets
• Restoring coins from old or unsupported wallet formats

You’re not just getting a service; you’re gaining a partner in your cryptocurrency journey.

🚀 Fast and Efficient Recovery\ We understand that time is crucial in crypto recovery. Our optimized systems enable you to regain access to your funds quickly, focusing on speed without compromising security. With a success rate of over 90%, you can rely on us to act swiftly on your behalf.

🔒 Privacy is Our Priority\ Your confidentiality is essential. Every recovery session is conducted with the utmost care, ensuring all processes are encrypted and confidential. You can rest assured that your sensitive information remains private.

💻 Advanced Technology\ Our proprietary tools and brute-force optimization techniques maximize recovery efficiency. Regardless of how challenging your case may be, our technology is designed to give you the best chance at retrieving your crypto.

Our Recovery Services Include: 📈

• Bitcoin Recovery: Lost access to your Bitcoin wallet? We help recover lost wallets, private keys, and passphrases.
• Transaction Recovery: Mistakes happen — whether it’s an incorrect wallet address or a lost password, let us manage the recovery.
• Cold Wallet Restoration: If your cold wallet is failing, we can safely extract your assets and migrate them into a secure new wallet.
• Private Key Generation: Lost your private key? Our experts can help you regain control using advanced methods while ensuring your privacy.

⚠️ What We Don’t Do\ While we can handle many scenarios, some limitations exist. For instance, we cannot recover funds stored in custodial wallets or cases where there is a complete loss of four or more seed words without partial information available. We are transparent about what’s possible, so you know what to expect

# Don’t Let Lost Crypto Hold You Back!

Did you know that between 3 to 3.4 million BTC — nearly 20% of the total supply — are estimated to be permanently lost? Don’t become part of that statistic! Whether it’s due to a forgotten password, sending funds to the wrong address, or damaged drives, we can help you navigate these challenges

🛡️ Real-Time Dust Attack Protection\ Our services extend beyond recovery. We offer dust attack protection, keeping your activity anonymous and your funds secure, shielding your identity from unwanted tracking, ransomware, and phishing attempts.

🎉 Start Your Recovery Journey Today!\ Ready to reclaim your lost crypto? Don’t wait until it’s too late!\ 👉 cryptrecver.com

📞 Need Immediate Assistance? Connect with Us!\ For real-time support or questions, reach out to our dedicated team on:\ ✉️ Telegram: t.me/crypptrcver\ 💬 WhatsApp: +1(941)317–1821

Crypt Recver is your trusted partner in cryptocurrency recovery. Let us turn your challenges into victories. Don’t hesitate — your crypto future starts now! 🚀✨

Act fast and secure your digital assets with cryptrecver.com.

@ 62033ff8:e4471203

收录的内容中 kind=1的部分，实话说 质量不高。 所以我增加了kind=30023 长文的article，但是更新的太少，多个relays 的服务器也没有多少长文。

所有搜索nostr如果需要产生价值，需要有高质量的文章和新闻。 而且现在有很多机器人的文章充满着浪费空间的作用，其他作用都用不上。

https://www.duozhutuan.com 目前放的是给搜索引擎提供搜索的原材料。没有做UI给人类浏览。所以看上去是粗糙的。 我并没有打算去做一个发microblog的 web客户端，那类的客户端太多了。

我觉得nostr社区需要解决的还是应用。如果仅仅是microblog 感觉有点够呛

幸运的是npub.pro 建站这样的，我觉得有点意思。

yakihonne 智能widget 也有意思

我做的TaskQ5 我自己在用了。分布式的任务系统，也挺好的。

@ 23b0e2f8:d8af76fc

Necessário

• Um Android que você não use mais (a câmera deve estar funcionando).
• Um cartão microSD (opcional, usado apenas uma vez).
• Um dispositivo para acompanhar seus fundos (provavelmente você já tem um).

Algumas coisas que você precisa saber

• O dispositivo servirá como um assinador. Qualquer movimentação só será efetuada após ser assinada por ele.
• O cartão microSD será usado para transferir o APK do Electrum e garantir que o aparelho não terá contato com outras fontes de dados externas após sua formatação. Contudo, é possível usar um cabo USB para o mesmo propósito.
• A ideia é deixar sua chave privada em um dispositivo offline, que ficará desligado em 99% do tempo. Você poderá acompanhar seus fundos em outro dispositivo conectado à internet, como seu celular ou computador pessoal.

---

O tutorial será dividido em dois módulos:

• Módulo 1 - Criando uma carteira fria/assinador.
• Módulo 2 - Configurando um dispositivo para visualizar seus fundos e assinando transações com o assinador.

---

No final, teremos:

• Uma carteira fria que também servirá como assinador.
• Um dispositivo para acompanhar os fundos da carteira.

---

Módulo 1 - Criando uma carteira fria/assinador

1. Baixe o APK do Electrum na aba de downloads em https://electrum.org/. Fique à vontade para verificar as assinaturas do software, garantindo sua autenticidade.

2. Formate o cartão microSD e coloque o APK do Electrum nele. Caso não tenha um cartão microSD, pule este passo.

1. Retire os chips e acessórios do aparelho que será usado como assinador, formate-o e aguarde a inicialização.

1. Durante a inicialização, pule a etapa de conexão ao Wi-Fi e rejeite todas as solicitações de conexão. Após isso, você pode desinstalar aplicativos desnecessários, pois precisará apenas do Electrum. Certifique-se de que Wi-Fi, Bluetooth e dados móveis estejam desligados. Você também pode ativar o modo avião.\ (Curiosidade: algumas pessoas optam por abrir o aparelho e danificar a antena do Wi-Fi/Bluetooth, impossibilitando essas funcionalidades.)

1. Insira o cartão microSD com o APK do Electrum no dispositivo e instale-o. Será necessário permitir instalações de fontes não oficiais.

1. No Electrum, crie uma carteira padrão e gere suas palavras-chave (seed). Anote-as em um local seguro. Caso algo aconteça com seu assinador, essas palavras permitirão o acesso aos seus fundos novamente. (Aqui entra seu método pessoal de backup.)

---

Módulo 2 - Configurando um dispositivo para visualizar seus fundos e assinando transações com o assinador.

1. Criar uma carteira somente leitura em outro dispositivo, como seu celular ou computador pessoal, é uma etapa bastante simples. Para este tutorial, usaremos outro smartphone Android com Electrum. Instale o Electrum a partir da aba de downloads em https://electrum.org/ ou da própria Play Store. (ATENÇÃO: O Electrum não existe oficialmente para iPhone. Desconfie se encontrar algum.)

2. Após instalar o Electrum, crie uma carteira padrão, mas desta vez escolha a opção Usar uma chave mestra.

1. Agora, no assinador que criamos no primeiro módulo, exporte sua chave pública: vá em Carteira > Detalhes da carteira > Compartilhar chave mestra pública.

1. Escaneie o QR gerado da chave pública com o dispositivo de consulta. Assim, ele poderá acompanhar seus fundos, mas sem permissão para movimentá-los.

2. Para receber fundos, envie Bitcoin para um dos endereços gerados pela sua carteira: Carteira > Addresses/Coins.

3. Para movimentar fundos, crie uma transação no dispositivo de consulta. Como ele não possui a chave privada, será necessário assiná-la com o dispositivo assinador.

1. No assinador, escaneie a transação não assinada, confirme os detalhes, assine e compartilhe. Será gerado outro QR, desta vez com a transação já assinada.

1. No dispositivo de consulta, escaneie o QR da transação assinada e transmita-a para a rede.

---

Conclusão

Pontos positivos do setup:

• Simplicidade: Basta um dispositivo Android antigo.
• Flexibilidade: Funciona como uma ótima carteira fria, ideal para holders.

Pontos negativos do setup:

• Padronização: Não utiliza seeds no padrão BIP-39, você sempre precisará usar o electrum.
• Interface: A aparência do Electrum pode parecer antiquada para alguns usuários.

Nesse ponto, temos uma carteira fria que também serve para assinar transações. O fluxo de assinar uma transação se torna: Gerar uma transação não assinada > Escanear o QR da transação não assinada > Conferir e assinar essa transação com o assinador > Gerar QR da transação assinada > Escanear a transação assinada com qualquer outro dispositivo que possa transmiti-la para a rede.

Como alguns devem saber, uma transação assinada de Bitcoin é praticamente impossível de ser fraudada. Em um cenário catastrófico, você pode mesmo que sem internet, repassar essa transação assinada para alguém que tenha acesso à rede por qualquer meio de comunicação. Mesmo que não queiramos que isso aconteça um dia, esse setup acaba por tornar essa prática possível.

---

@ b83a28b7:35919450

This article was originally part of the sermon of Plebchain Radio Episode 111 (May 2, 2025) that nostr:nprofile1qyxhwumn8ghj7mn0wvhxcmmvqyg8wumn8ghj7mn0wd68ytnvv9hxgqpqtvqc82mv8cezhax5r34n4muc2c4pgjz8kaye2smj032nngg52clq7fgefr and I did with nostr:nprofile1qythwumn8ghj7ct5d3shxtnwdaehgu3wd3skuep0qyt8wumn8ghj7ct4w35zumn0wd68yvfwvdhk6tcqyzx4h2fv3n9r6hrnjtcrjw43t0g0cmmrgvjmg525rc8hexkxc0kd2rhtk62 and nostr:nprofile1qyxhwumn8ghj7mn0wvhxcmmvqyg8wumn8ghj7mn0wd68ytnvv9hxgqpq4wxtsrj7g2jugh70pfkzjln43vgn4p7655pgky9j9w9d75u465pqahkzd0 of the nostr:nprofile1qythwumn8ghj7ct5d3shxtnwdaehgu3wd3skuep0qyt8wumn8ghj7etyv4hzumn0wd68ytnvv9hxgtcqyqwfvwrccp4j2xsuuvkwg0y6a20637t6f4cc5zzjkx030dkztt7t5hydajn

Listen to the full episode here:

<<https://fountain.fm/episode/Ln9Ej0zCZ5dEwfo8w2Ho>>

---

Bitcoin has always been a narrative revolution disguised as code. White paper, cypherpunk lore, pizza‑day legends - every block is a paragraph in the world’s most relentless epic. But code alone rarely converts the skeptic; it’s the camp‑fire myth that slips past the prefrontal cortex and shakes hands with the limbic system. People don’t adopt protocols first - they fall in love with protagonists.

Early adopters heard the white‑paper hymn, but most folks need characters first: a pizza‑day dreamer; a mother in a small country, crushed by the cost of remittance; a Warsaw street vendor swapping złoty for sats. When their arcs land, the brain releases a neurochemical OP_RETURN which says, “I belong in this plot.” That’s the sly roundabout orange pill: conviction smuggled inside catharsis.

That’s why, from 22–25 May in Warsaw’s Kinoteka, the Bitcoin Film Fest is loading its reels with rebellion. Each documentary, drama, and animated rabbit‑hole is a stealth wallet, zipping conviction straight into the feels of anyone still clasped within the cold claw of fiat. You come for the plot, you leave checking block heights.

---

Here's the clip of the sermon from the episode:

nostr:nevent1qvzqqqqqqypzpwp69zm7fewjp0vkp306adnzt7249ytxhz7mq3w5yc629u6er9zsqqsy43fwz8es2wnn65rh0udc05tumdnx5xagvzd88ptncspmesdqhygcrvpf2

@ b83a28b7:35919450

This article was originally part of the sermon of Plebchain Radio Episode 110 (May 2, 2025) that nostr:nprofile1qyxhwumn8ghj7mn0wvhxcmmvqyg8wumn8ghj7mn0wd68ytnvv9hxgqpqtvqc82mv8cezhax5r34n4muc2c4pgjz8kaye2smj032nngg52clq7fgefr and I did with nostr:nprofile1qythwumn8ghj7ct5d3shxtnwdaehgu3wd3skuep0qyt8wumn8ghj7ct4w35zumn0wd68yvfwvdhk6tcqyzx4h2fv3n9r6hrnjtcrjw43t0g0cmmrgvjmg525rc8hexkxc0kd2rhtk62 and nostr:nprofile1qyxhwumn8ghj7mn0wvhxcmmvqyg8wumn8ghj7mn0wd68ytnvv9hxgqpq4wxtsrj7g2jugh70pfkzjln43vgn4p7655pgky9j9w9d75u465pqahkzd0 of the nostr:nprofile1qythwumn8ghj7ct5d3shxtnwdaehgu3wd3skuep0qyt8wumn8ghj7etyv4hzumn0wd68ytnvv9hxgtcqyqwfvwrccp4j2xsuuvkwg0y6a20637t6f4cc5zzjkx030dkztt7t5hydajn

Listen to the full episode here:

<https://fountain.fm/episode/Ln9Ej0zCZ5dEwfo8w2Ho>

---

Bitcoin has always been a narrative revolution disguised as code. White paper, cypherpunk lore, pizza‑day legends - every block is a paragraph in the world’s most relentless epic. But code alone rarely converts the skeptic; it’s the camp‑fire myth that slips past the prefrontal cortex and shakes hands with the limbic system. People don’t adopt protocols first - they fall in love with protagonists.

Early adopters heard the white‑paper hymn, but most folks need characters first: a pizza‑day dreamer; a mother in a small country, crushed by the cost of remittance; a Warsaw street vendor swapping złoty for sats. When their arcs land, the brain releases a neurochemical OP_RETURN which says, “I belong in this plot.” That’s the sly roundabout orange pill: conviction smuggled inside catharsis.

That’s why, from 22–25 May in Warsaw’s Kinoteka, the Bitcoin Film Fest is loading its reels with rebellion. Each documentary, drama, and animated rabbit‑hole is a stealth wallet, zipping conviction straight into the feels of anyone still clasped within the cold claw of fiat. You come for the plot, you leave checking block heights.

---

Here's the clip of the sermon from the episode:

nostr:nevent1qvzqqqqqqypzpwp69zm7fewjp0vkp306adnzt7249ytxhz7mq3w5yc629u6er9zsqqsy43fwz8es2wnn65rh0udc05tumdnx5xagvzd88ptncspmesdqhygcrvpf2

@ 39cc53c9:27168656

Read the original blog post

The new website is finally live! I put in a lot of hard work over the past months on it. I'm proud to say that it's out now and it looks pretty cool, at least to me!

Why rewrite it all?

The old kycnot.me site was built using Python with Flask about two years ago. Since then, I've gained a lot more experience with Golang and coding in general. Trying to update that old codebase, which had a lot of design flaws, would have been a bad idea. It would have been like building on an unstable foundation.

That's why I made the decision to rewrite the entire application. Initially, I chose to use SvelteKit with JavaScript. I did manage to create a stable site that looked similar to the new one, but it required Jav aScript to work. As I kept coding, I started feeling like I was repeating "the Python mistake". I was writing the app in a language I wasn't very familiar with (just like when I was learning Python at that mom ent), and I wasn't happy with the code. It felt like spaghetti code all the time.

So, I made a complete U-turn and started over, this time using Golang. While I'm not as proficient in Golang as I am in Python now, I find it to be a very enjoyable language to code with. Most aof my recent pr ojects have been written in Golang, and I'm getting the hang of it. I tried to make the best decisions I could and structure the code as well as possible. Of course, there's still room for improvement, which I'll address in future updates.

Now I have a more maintainable website that can scale much better. It uses a real database instead of a JSON file like the old site, and I can add many more features. Since I chose to go with Golang, I mad e the "tradeoff" of not using JavaScript at all, so all the rendering load falls on the server. But I believe it's a tradeoff that's worth it.

What's new

• UI/UX - I've designed a new logo and color palette for kycnot.me. I think it looks pretty cool and cypherpunk. I am not a graphic designer, but I think I did a decent work and I put a lot of thinking on it to make it pleasant!
• Point system - The new point system provides more detailed information about the listings, and can be expanded to cover additional features across all services. Anyone can request a new point!
• ToS Scrapper: I've implemented a powerful automated terms-of-service scrapper that collects all the ToS pages from the listings. It saves you from the hassle of reading the ToS by listing the lines that are suspiciously related to KYC/AML practices. This is still in development and it will improve for sure, but it works pretty fine right now!
• Search bar - The new search bar allows you to easily filter services. It performs a full-text search on the Title, Description, Category, and Tags of all the services. Looking for VPN services? Just search for "vpn"!
• Transparency - To be more transparent, all discussions about services now take place publicly on GitLab. I won't be answering any e-mails (an auto-reply will prompt to write to the corresponding Gitlab issue). This ensures that all service-related matters are publicly accessible and recorded. Additionally, there's a real-time audits page that displays database changes.
• Listing Requests - I have upgraded the request system. The new form allows you to directly request services or points without any extra steps. In the future, I plan to enable requests for specific changes to parts of the website.
• Lightweight and fast - The new site is lighter and faster than its predecessor!
• Tor and I2P - At last! kycnot.me is now officially on Tor and I2P!

How?

This rewrite has been a labor of love, in the end, I've been working on this for more than 3 months now. I don't have a team, so I work by myself on my free time, but I find great joy in helping people on their private journey with cryptocurrencies. Making it easier for individuals to use cryptocurrencies without KYC is a goal I am proud of!

If you appreciate my work, you can support me through the methods listed here. Alternatively, feel free to send me an email with a kind message!

Technical details

All the code is written in Golang, the website makes use of the chi router for the routing part. I also make use of BigCache for caching database requests. There is 0 JavaScript, so all the rendering load falls on the server, this means it needed to be efficient enough to not drawn with a few users since the old site was reporting about 2M requests per month on average (note that this are not unique users).

The database is running with mariadb, using gorm as the ORM. This is more than enough for this project. I started working with an sqlite database, but I ended up migrating to mariadb since it works better with JSON.

The scraper is using chromedp combined with a series of keywords, regex and other logic. It runs every 24h and scraps all the services. You can find the scraper code here.

The frontend is written using Golang Templates for the HTML, and TailwindCSS plus DaisyUI for the CSS classes framework. I also use some plain CSS, but it's minimal.

The requests forms is the only part of the project that requires JavaScript to be enabled. It is needed for parsing some from fields that are a bit complex and for the "captcha", which is a simple Proof of Work that runs on your browser, destinated to avoid spam. For this, I use mCaptcha.

@ 39cc53c9:27168656

Read the original blog post

Know Your Customer is a regulation that requires companies of all sizes to verify the identity, suitability, and risks involved with maintaining a business relationship with a customer. Such procedures fit within the broader scope of anti-money laundering (AML) and counterterrorism financing (CTF) regulations.

Banks, exchanges, online business, mail providers, domain registrars... Everyone wants to know who you are before you can even opt for their service. Your personal information is flowing around the internet in the hands of "god-knows-who" and secured by "trust-me-bro military-grade encryption". Once your account is linked to your personal (and verified) identity, tracking you is just as easy as keeping logs on all these platforms.

Rights for Illusions

KYC processes aim to combat terrorist financing, money laundering, and other illicit activities. On the surface, KYC seems like a commendable initiative. I mean, who wouldn't want to halt terrorists and criminals in their tracks?

The logic behind KYC is: "If we mandate every financial service provider to identify their users, it becomes easier to pinpoint and apprehend the malicious actors."

However, terrorists and criminals are not precisely lining up to be identified. They're crafty. They may adopt false identities or find alternative strategies to continue their operations. Far from being outwitted, many times they're several steps ahead of regulations. Realistically, KYC might deter a small fraction – let's say about 1% ^1 – of these malefactors. Yet, the cost? All of us are saddled with the inconvenient process of identification just to use a service.

Under the rhetoric of "ensuring our safety", governments and institutions enact regulations that seem more out of a dystopian novel, gradually taking away our right to privacy.

To illustrate, consider a city where the mayor has rolled out facial recognition cameras in every nook and cranny. A band of criminals, intent on robbing a local store, rolls in with a stolen car, their faces obscured by masks and their bodies cloaked in all-black clothes. Once they've committed the crime and exited the city's boundaries, they switch vehicles and clothes out of the cameras' watchful eyes. The high-tech surveillance? It didn’t manage to identify or trace them. Yet, for every law-abiding citizen who merely wants to drive through the city or do some shopping, their movements and identities are constantly logged. The irony? This invasive tracking impacts all of us, just to catch the 1% ^1 of less-than-careful criminals.

KYC? Not you.

KYC creates barriers to participation in normal economic activity, to supposedly stop criminals. ^2

KYC puts barriers between many users and businesses. One of these comes from the fact that the process often requires multiple forms of identification, proof of address, and sometimes even financial records. For individuals in areas with poor record-keeping, non-recognized legal documents, or those who are unbanked, homeless or transient, obtaining these documents can be challenging, if not impossible.

For people who are not skilled with technology or just don't have access to it, there's also a barrier since KYC procedures are mostly online, leaving them inadvertently excluded.

Another barrier goes for the casual or one-time user, where they might not see the value in undergoing a rigorous KYC process, and these requirements can deter them from using the service altogether.

It also wipes some businesses out of the equation, since for smaller businesses, the costs associated with complying with KYC norms—from the actual process of gathering and submitting documents to potential delays in operations—can be prohibitive in economical and/or technical terms.

You're not welcome

Imagine a swanky new club in town with a strict "members only" sign. You hear the music, you see the lights, and you want in. You step up, ready to join, but suddenly there's a long list of criteria you must meet. After some time, you are finally checking all the boxes. But then the club rejects your membership with no clear reason why. You just weren't accepted. Frustrating, right?

This club scenario isn't too different from the fact that KYC is being used by many businesses as a convenient gatekeeping tool. A perfect excuse based on a "legal" procedure they are obliged to.

Even some exchanges may randomly use this to freeze and block funds from users, claiming these were "flagged" by a cryptic system that inspects the transactions. You are left hostage to their arbitrary decision to let you successfully pass the KYC procedure. If you choose to sidestep their invasive process, they might just hold onto your funds indefinitely.

Your identity has been stolen

KYC data has been found to be for sale on many dark net markets^3. Exchanges may have leaks or hacks, and such leaks contain very sensitive data. We're talking about the full monty: passport or ID scans, proof of address, and even those awkward selfies where you're holding up your ID next to your face. All this data is being left to the mercy of the (mostly) "trust-me-bro" security systems of such companies. Quite scary, isn't it?

As cheap as $10 for 100 documents, with discounts applying for those who buy in bulk, the personal identities of innocent users who passed KYC procedures are for sale. ^3

In short, if you have ever passed the KYC/AML process of a crypto exchange, your privacy is at risk of being compromised, or it might even have already been compromised.

(they) Know Your Coins

You may already know that Bitcoin and most cryptocurrencies have a transparent public blockchain, meaning that all data is shown unencrypted for everyone to see and recorded forever. If you link an address you own to your identity through KYC, for example, by sending an amount from a KYC exchange to it, your Bitcoin is no longer pseudonymous and can then be traced.

If, for instance, you send Bitcoin from such an identified address to another KYC'ed address (say, from a friend), everyone having access to that address-identity link information (exchanges, governments, hackers, etc.) will be able to associate that transaction and know who you are transacting with.

Conclusions

To sum up, KYC does not protect individuals; rather, it's a threat to our privacy, freedom, security and integrity. Sensible information flowing through the internet is thrown into chaos by dubious security measures. It puts borders between many potential customers and businesses, and it helps governments and companies track innocent users. That's the chaos KYC has stirred.

The criminals are using stolen identities from companies that gathered them thanks to these very same regulations that were supposed to combat them. Criminals always know how to circumvent such regulations. In the end, normal people are the most affected by these policies.

The threat that KYC poses to individuals in terms of privacy, security and freedom is not to be neglected. And if we don’t start challenging these systems and questioning their efficacy, we are just one step closer to the dystopian future that is now foreseeable.

Edited 20/03/2024 * Add reference to the 1% statement on Rights for Illusions section to an article where Chainalysis found that only 0.34% of the transaction volume with cryptocurrencies in 2023 was attributable to criminal activity ^1

@ 04c915da:3dfbecc9

Bitcoin has always been rooted in freedom and resistance to authority. I get that many of you are conflicted about the US Government stacking but by design we cannot stop anyone from using bitcoin. Many have asked me for my thoughts on the matter, so let’s rip it.

Concern

One of the most glaring issues with the strategic bitcoin reserve is its foundation, built on stolen bitcoin. For those of us who value private property this is an obvious betrayal of our core principles. Rather than proof of work, the bitcoin that seeds this reserve has been taken by force. The US Government should return the bitcoin stolen from Bitfinex and the Silk Road.

Using stolen bitcoin for the reserve creates a perverse incentive. If governments see bitcoin as a valuable asset, they will ramp up efforts to confiscate more bitcoin. The precedent is a major concern, and I stand strongly against it, but it should be also noted that governments were already seizing coin before the reserve so this is not really a change in policy.

Ideally all seized bitcoin should be burned, by law. This would align incentives properly and make it less likely for the government to actively increase coin seizures. Due to the truly scarce properties of bitcoin, all burned bitcoin helps existing holders through increased purchasing power regardless. This change would be unlikely but those of us in policy circles should push for it regardless. It would be best case scenario for American bitcoiners and would create a strong foundation for the next century of American leadership.

Optimism

The entire point of bitcoin is that we can spend or save it without permission. That said, it is a massive benefit to not have one of the strongest governments in human history actively trying to ruin our lives.

Since the beginning, bitcoiners have faced horrible regulatory trends. KYC, surveillance, and legal cases have made using bitcoin and building bitcoin businesses incredibly difficult. It is incredibly important to note that over the past year that trend has reversed for the first time in a decade. A strategic bitcoin reserve is a key driver of this shift. By holding bitcoin, the strongest government in the world has signaled that it is not just a fringe technology but rather truly valuable, legitimate, and worth stacking.

This alignment of incentives changes everything. The US Government stacking proves bitcoin’s worth. The resulting purchasing power appreciation helps all of us who are holding coin and as bitcoin succeeds our government receives direct benefit. A beautiful positive feedback loop.

Realism

We are trending in the right direction. A strategic bitcoin reserve is a sign that the state sees bitcoin as an asset worth embracing rather than destroying. That said, there is a lot of work left to be done. We cannot be lulled into complacency, the time to push forward is now, and we cannot take our foot off the gas. We have a seat at the table for the first time ever. Let's make it worth it.

We must protect the right to free usage of bitcoin and other digital technologies. Freedom in the digital age must be taken and defended, through both technical and political avenues. Multiple privacy focused developers are facing long jail sentences for building tools that protect our freedom. These cases are not just legal battles. They are attacks on the soul of bitcoin. We need to rally behind them, fight for their freedom, and ensure the ethos of bitcoin survives this new era of government interest. The strategic reserve is a step in the right direction, but it is up to us to hold the line and shape the future.

@ 207ad2a0:e7cca7b0

Quick context: I wanted to check out Nostr's longform posts and this blog post seemed like a good one to try and mirror. It's originally from my free to read/share attempt to write a novel, but this post here is completely standalone - just describing how I used AI image generation to make a small piece of the work.

Hold on, put your pitchforks down - outside of using Grammerly & Emacs for grammatical corrections - not a single character was generated or modified by computers; a non-insignificant portion of my first draft originating on pen & paper. No AI is ~~weird and crazy~~ imaginative enough to write like I do. The only successful AI contribution you'll find is a single image, the map, which I heavily edited. This post will go over how I generated and modified an image using AI, which I believe brought some value to the work, and cover a few quick thoughts about AI towards the end.

Let's be clear, I can't draw, but I wanted a map which I believed would improve the story I was working on. After getting abysmal results by prompting AI with text only I decided to use "Diffuse the Rest," a Stable Diffusion tool that allows you to provide a reference image + description to fine tune what you're looking for. I gave it this Microsoft Paint looking drawing:

and after a number of outputs, selected this one to work on:

The image is way better than the one I provided, but had I used it as is, I still feel it would have decreased the quality of my work instead of increasing it. After firing up Gimp I cropped out the top and bottom, expanded the ocean and separated the landmasses, then copied the top right corner of the large landmass to replace the bottom left that got cut off. Now we've got something that looks like concept art: not horrible, and gets the basic idea across, but it's still due for a lot more detail.

The next thing I did was add some texture to make it look more map like. I duplicated the layer in Gimp and applied the "Cartoon" filter to both for some texture. The top layer had a much lower effect strength to give it a more textured look, while the lower layer had a higher effect strength that looked a lot like mountains or other terrain features. Creating a layer mask allowed me to brush over spots to display the lower layer in certain areas, giving it some much needed features.

At this point I'd made it to where I felt it may improve the work instead of detracting from it - at least after labels and borders were added, but the colors seemed artificial and out of place. Luckily, however, this is when PhotoFunia could step in and apply a sketch effect to the image.

At this point I was pretty happy with how it was looking, it was close to what I envisioned and looked very visually appealing while still being a good way to portray information. All that was left was to make the white background transparent, add some minor details, and add the labels and borders. Below is the exact image I wound up using:

Overall, I'm very satisfied with how it turned out, and if you're working on a creative project, I'd recommend attempting something like this. It's not a central part of the work, but it improved the chapter a fair bit, and was doable despite lacking the talent and not intending to allocate a budget to my making of a free to read and share story.

The AI Generated Elephant in the Room

If you've read my non-fiction writing before, you'll know that I think AI will find its place around the skill floor as opposed to the skill ceiling. As you saw with my input, I have absolutely zero drawing talent, but with some elbow grease and an existing creative direction before and after generating an image I was able to get something well above what I could have otherwise accomplished. Outside of the lowest common denominators like stock photos for the sole purpose of a link preview being eye catching, however, I doubt AI will be wholesale replacing most creative works anytime soon. I can assure you that I tried numerous times to describe the map without providing a reference image, and if I used one of those outputs (or even just the unedited output after providing the reference image) it would have decreased the quality of my work instead of improving it.

I'm going to go out on a limb and expect that AI image, text, and video is all going to find its place in slop & generic content (such as AI generated slop replacing article spinners and stock photos respectively) and otherwise be used in a supporting role for various creative endeavors. For people working on projects like I'm working on (e.g. intended budget $0) it's helpful to have an AI capable of doing legwork - enabling projects to exist or be improved in ways they otherwise wouldn't have. I'm also guessing it'll find its way into more professional settings for grunt work - think a picture frame or fake TV show that would exist in the background of an animated project - likely a detail most people probably wouldn't notice, but that would save the creators time and money and/or allow them to focus more on the essential aspects of said work. Beyond that, as I've predicted before: I expect plenty of emails will be generated from a short list of bullet points, only to be summarized by the recipient's AI back into bullet points.

I will also make a prediction counter to what seems mainstream: AI is about to peak for a while. The start of AI image generation was with Google's DeepDream in 2015 - image recognition software that could be run in reverse to "recognize" patterns where there were none, effectively generating an image from digital noise or an unrelated image. While I'm not an expert by any means, I don't think we're too far off from that a decade later, just using very fine tuned tools that develop more coherent images. I guess that we're close to maxing out how efficiently we're able to generate images and video in that manner, and the hard caps on how much creative direction we can have when using AI - as well as the limits to how long we can keep it coherent (e.g. long videos or a chronologically consistent set of images) - will prevent AI from progressing too far beyond what it is currently unless/until another breakthrough occurs.

@ 39cc53c9:27168656

Read the original blog post

Over the past few months, I've dedicated my time to a complete rewrite of the kycnot.me website. The technology stack remains unchanged; Golang paired with TailwindCSS. However, I've made some design choices in this iteration that I believe significantly enhance the site. Particularly to backend code.

UI Improvements

You'll notice a refreshed UI that retains the original concept but has some notable enhancements. The service list view is now more visually engaging, it displays additional information in a more aesthetically pleasing manner. Both filtering and searching functionalities have been optimized for speed and user experience.

Service pages have been also redesigned to highlight key information at the top, with the KYC Level box always accessible. The display of service attributes is now more visually intuitive.

The request form, especially the Captcha, has undergone substantial improvements. The new self-made Captcha is robust, addressing the reliability issues encountered with the previous version.

Terms of Service Summarizer

A significant upgrade is the Terms of Service summarizer/reviewer, now powered by AI (GPT-4-turbo). It efficiently condenses each service's ToS, extracting and presenting critical points, including any warnings. Summaries are updated monthly, processing over 40 ToS pages via the OpenAI API using a self-crafted and thoroughly tested prompt.

Nostr Comments

I've integrated a comment section for each service using Nostr. For guidance on using this feature, visit the dedicated how-to page.

Database

The backend database has transitioned to pocketbase, an open-source Golang backend that has been a pleasure to work with. I maintain an updated fork of the Golang SDK for pocketbase at pluja/pocketbase.

Scoring

The scoring algorithm has also been refined to be more fair. Despite I had considered its removal due to the complexity it adds (it is very difficult to design a fair scoring system), some users highlighted its value, so I kept it. The updated algorithm is available open source.

Listings

Each listing has been re-evaluated, and the ones that were no longer operational were removed. New additions are included, and the backlog of pending services will be addressed progressively, since I still have access to the old database.

API

The API now offers more comprehensive data. For more details, check here.

About Page

The About page has been restructured for brevity and clarity.

Other Changes

Extensive changes have been implemented in the server-side logic, since the whole code base was re-written from the ground up. I may discuss these in a future post, but for now, I consider the current version to be just a bit beyond beta, and additional updates are planned in the coming weeks.

@ e6817453:b0ac3c39

The Rise of Graph RAGs and the Quest for Data Quality

As we enter a new year, it’s impossible to ignore the boom of retrieval-augmented generation (RAG) systems, particularly those leveraging graph-based approaches. The previous year saw a surge in advancements and discussions about Graph RAGs, driven by their potential to enhance large language models (LLMs), reduce hallucinations, and deliver more reliable outputs. Let’s dive into the trends, challenges, and strategies for making the most of Graph RAGs in artificial intelligence.

Booming Interest in Graph RAGs

Graph RAGs have dominated the conversation in AI circles. With new research papers and innovations emerging weekly, it’s clear that this approach is reshaping the landscape. These systems, especially those developed by tech giants like Microsoft, demonstrate how graphs can:

• Enhance LLM Outputs: By grounding responses in structured knowledge, graphs significantly reduce hallucinations.
• Support Complex Queries: Graphs excel at managing linked and connected data, making them ideal for intricate problem-solving.

Conferences on linked and connected data have increasingly focused on Graph RAGs, underscoring their central role in modern AI systems. However, the excitement around this technology has brought critical questions to the forefront: How do we ensure the quality of the graphs we’re building, and are they genuinely aligned with our needs?

Data Quality: The Foundation of Effective Graphs

A high-quality graph is the backbone of any successful RAG system. Constructing these graphs from unstructured data requires attention to detail and rigorous processes. Here’s why:

• Richness of Entities: Effective retrieval depends on graphs populated with rich, detailed entities.
• Freedom from Hallucinations: Poorly constructed graphs amplify inaccuracies rather than mitigating them.

Without robust data quality, even the most sophisticated Graph RAGs become ineffective. As a result, the focus must shift to refining the graph construction process. Improving data strategy and ensuring meticulous data preparation is essential to unlock the full potential of Graph RAGs.

Hybrid Graph RAGs and Variations

While standard Graph RAGs are already transformative, hybrid models offer additional flexibility and power. Hybrid RAGs combine structured graph data with other retrieval mechanisms, creating systems that:

• Handle diverse data sources with ease.
• Offer improved adaptability to complex queries.

Exploring these variations can open new avenues for AI systems, particularly in domains requiring structured and unstructured data processing.

Ontology: The Key to Graph Construction Quality

Ontology — defining how concepts relate within a knowledge domain — is critical for building effective graphs. While this might sound abstract, it’s a well-established field blending philosophy, engineering, and art. Ontology engineering provides the framework for:

• Defining Relationships: Clarifying how concepts connect within a domain.
• Validating Graph Structures: Ensuring constructed graphs are logically sound and align with domain-specific realities.

Traditionally, ontologists — experts in this discipline — have been integral to large enterprises and research teams. However, not every team has access to dedicated ontologists, leading to a significant challenge: How can teams without such expertise ensure the quality of their graphs?

How to Build Ontology Expertise in a Startup Team

For startups and smaller teams, developing ontology expertise may seem daunting, but it is achievable with the right approach:

1. Assign a Knowledge Champion: Identify a team member with a strong analytical mindset and give them time and resources to learn ontology engineering.
2. Provide Training: Invest in courses, workshops, or certifications in knowledge graph and ontology creation.
3. Leverage Partnerships: Collaborate with academic institutions, domain experts, or consultants to build initial frameworks.
4. Utilize Tools: Introduce ontology development tools like Protégé, OWL, or SHACL to simplify the creation and validation process.
5. Iterate with Feedback: Continuously refine ontologies through collaboration with domain experts and iterative testing.

So, it is not always affordable for a startup to have a dedicated oncologist or knowledge engineer in a team, but you could involve consulters or build barefoot experts.

You could read about barefoot experts in my article :

Even startups can achieve robust and domain-specific ontology frameworks by fostering in-house expertise.

How to Find or Create Ontologies

For teams venturing into Graph RAGs, several strategies can help address the ontology gap:

1. Leverage Existing Ontologies: Many industries and domains already have open ontologies. For instance:

2. Public Knowledge Graphs: Resources like Wikipedia’s graph offer a wealth of structured knowledge.

3. Industry Standards: Enterprises such as Siemens have invested in creating and sharing ontologies specific to their fields.

4. Business Framework Ontology (BFO): A valuable resource for enterprises looking to define business processes and structures.

5. Build In-House Expertise: If budgets allow, consider hiring knowledge engineers or providing team members with the resources and time to develop expertise in ontology creation.

6. Utilize LLMs for Ontology Construction: Interestingly, LLMs themselves can act as a starting point for ontology development:

7. Prompt-Based Extraction: LLMs can generate draft ontologies by leveraging their extensive training on graph data.

8. Domain Expert Refinement: Combine LLM-generated structures with insights from domain experts to create tailored ontologies.

Parallel Ontology and Graph Extraction

An emerging approach involves extracting ontologies and graphs in parallel. While this can streamline the process, it presents challenges such as:

• Detecting Hallucinations: Differentiating between genuine insights and AI-generated inaccuracies.
• Ensuring Completeness: Ensuring no critical concepts are overlooked during extraction.

Teams must carefully validate outputs to ensure reliability and accuracy when employing this parallel method.

LLMs as Ontologists

While traditionally dependent on human expertise, ontology creation is increasingly supported by LLMs. These models, trained on vast amounts of data, possess inherent knowledge of many open ontologies and taxonomies. Teams can use LLMs to:

• Generate Skeleton Ontologies: Prompt LLMs with domain-specific information to draft initial ontology structures.
• Validate and Refine Ontologies: Collaborate with domain experts to refine these drafts, ensuring accuracy and relevance.

However, for validation and graph construction, formal tools such as OWL, SHACL, and RDF should be prioritized over LLMs to minimize hallucinations and ensure robust outcomes.

Final Thoughts: Unlocking the Power of Graph RAGs

The rise of Graph RAGs underscores a simple but crucial correlation: improving graph construction and data quality directly enhances retrieval systems. To truly harness this power, teams must invest in understanding ontologies, building quality graphs, and leveraging both human expertise and advanced AI tools.

As we move forward, the interplay between Graph RAGs and ontology engineering will continue to shape the future of AI. Whether through adopting existing frameworks or exploring innovative uses of LLMs, the path to success lies in a deep commitment to data quality and domain understanding.

Have you explored these technologies in your work? Share your experiences and insights — and stay tuned for more discussions on ontology extraction and its role in AI advancements. Cheers to a year of innovation!

@ 04c915da:3dfbecc9

Recently we have seen a wave of high profile X accounts hacked. These attacks have exposed the fragility of the status quo security model used by modern social media platforms like X. Many users have asked if nostr fixes this, so lets dive in. How do these types of attacks translate into the world of nostr apps? For clarity, I will use X’s security model as representative of most big tech social platforms and compare it to nostr.

The Status Quo

On X, you never have full control of your account. Ultimately to use it requires permission from the company. They can suspend your account or limit your distribution. Theoretically they can even post from your account at will. An X account is tied to an email and password. Users can also opt into two factor authentication, which adds an extra layer of protection, a login code generated by an app. In theory, this setup works well, but it places a heavy burden on users. You need to create a strong, unique password and safeguard it. You also need to ensure your email account and phone number remain secure, as attackers can exploit these to reset your credentials and take over your account. Even if you do everything responsibly, there is another weak link in X infrastructure itself. The platform’s infrastructure allows accounts to be reset through its backend. This could happen maliciously by an employee or through an external attacker who compromises X’s backend. When an account is compromised, the legitimate user often gets locked out, unable to post or regain control without contacting X’s support team. That process can be slow, frustrating, and sometimes fruitless if support denies the request or cannot verify your identity. Often times support will require users to provide identification info in order to regain access, which represents a privacy risk. The centralized nature of X means you are ultimately at the mercy of the company’s systems and staff.

Nostr Requires Responsibility

Nostr flips this model radically. Users do not need permission from a company to access their account, they can generate as many accounts as they want, and cannot be easily censored. The key tradeoff here is that users have to take complete responsibility for their security. Instead of relying on a username, password, and corporate servers, nostr uses a private key as the sole credential for your account. Users generate this key and it is their responsibility to keep it safe. As long as you have your key, you can post. If someone else gets it, they can post too. It is that simple. This design has strong implications. Unlike X, there is no backend reset option. If your key is compromised or lost, there is no customer support to call. In a compromise scenario, both you and the attacker can post from the account simultaneously. Neither can lock the other out, since nostr relays simply accept whatever is signed with a valid key.

The benefit? No reliance on proprietary corporate infrastructure.. The negative? Security rests entirely on how well you protect your key.

Future Nostr Security Improvements

For many users, nostr’s standard security model, storing a private key on a phone with an encrypted cloud backup, will likely be sufficient. It is simple and reasonably secure. That said, nostr’s strength lies in its flexibility as an open protocol. Users will be able to choose between a range of security models, balancing convenience and protection based on need.

One promising option is a web of trust model for key rotation. Imagine pre-selecting a group of trusted friends. If your account is compromised, these people could collectively sign an event announcing the compromise to the network and designate a new key as your legitimate one. Apps could handle this process seamlessly in the background, notifying followers of the switch without much user interaction. This could become a popular choice for average users, but it is not without tradeoffs. It requires trust in your chosen web of trust, which might not suit power users or large organizations. It also has the issue that some apps may not recognize the key rotation properly and followers might get confused about which account is “real.”

For those needing higher security, there is the option of multisig using FROST (Flexible Round-Optimized Schnorr Threshold). In this setup, multiple keys must sign off on every action, including posting and updating a profile. A hacker with just one key could not do anything. This is likely overkill for most users due to complexity and inconvenience, but it could be a game changer for large organizations, companies, and governments. Imagine the White House nostr account requiring signatures from multiple people before a post goes live, that would be much more secure than the status quo big tech model.

Another option are hardware signers, similar to bitcoin hardware wallets. Private keys are kept on secure, offline devices, separate from the internet connected phone or computer you use to broadcast events. This drastically reduces the risk of remote hacks, as private keys never touches the internet. It can be used in combination with multisig setups for extra protection. This setup is much less convenient and probably overkill for most but could be ideal for governments, companies, or other high profile accounts.

---

Nostr’s security model is not perfect but is robust and versatile. Ultimately users are in control and security is their responsibility. Apps will give users multiple options to choose from and users will choose what best fits their need.

@ 04c915da:3dfbecc9

In much of the world, it is incredibly difficult to access U.S. dollars. Local currencies are often poorly managed and riddled with corruption. Billions of people demand a more reliable alternative. While the dollar has its own issues of corruption and mismanagement, it is widely regarded as superior to the fiat currencies it competes with globally. As a result, Tether has found massive success providing low cost, low friction access to dollars. Tether claims 400 million total users, is on track to add 200 million more this year, processes 8.1 million transactions daily, and facilitates $29 billion in daily transfers. Furthermore, their estimates suggest nearly 40% of users rely on it as a savings tool rather than just a transactional currency.

Tether’s rise has made the company a financial juggernaut. Last year alone, Tether raked in over $13 billion in profit, with a lean team of less than 100 employees. Their business model is elegantly simple: hold U.S. Treasuries and collect the interest. With over $113 billion in Treasuries, Tether has turned a straightforward concept into a profit machine.

Tether’s success has resulted in many competitors eager to claim a piece of the pie. This has triggered a massive venture capital grift cycle in USD tokens, with countless projects vying to dethrone Tether. Due to Tether’s entrenched network effect, these challengers face an uphill battle with little realistic chance of success. Most educated participants in the space likely recognize this reality but seem content to perpetuate the grift, hoping to cash out by dumping their equity positions on unsuspecting buyers before they realize the reality of the situation.

Historically, Tether’s greatest vulnerability has been U.S. government intervention. For over a decade, the company operated offshore with few allies in the U.S. establishment, making it a major target for regulatory action. That dynamic has shifted recently and Tether has seized the opportunity. By actively courting U.S. government support, Tether has fortified their position. This strategic move will likely cement their status as the dominant USD token for years to come.

While undeniably a great tool for the millions of users that rely on it, Tether is not without flaws. As a centralized, trusted third party, it holds the power to freeze or seize funds at its discretion. Corporate mismanagement or deliberate malpractice could also lead to massive losses at scale. In their goal of mitigating regulatory risk, Tether has deepened ties with law enforcement, mirroring some of the concerns of potential central bank digital currencies. In practice, Tether operates as a corporate CBDC alternative, collaborating with authorities to surveil and seize funds. The company proudly touts partnerships with leading surveillance firms and its own data reveals cooperation in over 1,000 law enforcement cases, with more than $2.5 billion in funds frozen.

---

The global demand for Tether is undeniable and the company’s profitability reflects its unrivaled success. Tether is owned and operated by bitcoiners and will likely continue to push forward strategic goals that help the movement as a whole. Recent efforts to mitigate the threat of U.S. government enforcement will likely solidify their network effect and stifle meaningful adoption of rival USD tokens or CBDCs. Yet, for all their achievements, Tether is simply a worse form of money than bitcoin. Tether requires trust in a centralized entity, while bitcoin can be saved or spent without permission. Furthermore, Tether is tied to the value of the US Dollar which is designed to lose purchasing power over time, while bitcoin, as a truly scarce asset, is designed to increase in purchasing power with adoption. As people awaken to the risks of Tether’s control, and the benefits bitcoin provides, bitcoin adoption will likely surpass it.

@ a4a6b584:1e05b95b

The Four-Layer Framework

Layer 1: Zoom Out

Start by looking at the big picture. What’s the subject about, and why does it matter? Focus on the overarching ideas and how they fit together. Think of this as the 30,000-foot view—it’s about understanding the "why" and "how" before diving into the "what."

Example: If you’re learning programming, start by understanding that it’s about giving logical instructions to computers to solve problems.

• Tip: Keep it simple. Summarize the subject in one or two sentences and avoid getting bogged down in specifics at this stage.

Once you have the big picture in mind, it’s time to start breaking it down.

---

Layer 2: Categorize and Connect

Now it’s time to break the subject into categories—like creating branches on a tree. This helps your brain organize information logically and see connections between ideas.

Example: Studying biology? Group concepts into categories like cells, genetics, and ecosystems.

• Tip: Use headings or labels to group similar ideas. Jot these down in a list or simple diagram to keep track.

With your categories in place, you’re ready to dive into the details that bring them to life.

---

Layer 3: Master the Details

Once you’ve mapped out the main categories, you’re ready to dive deeper. This is where you learn the nuts and bolts—like formulas, specific techniques, or key terminology. These details make the subject practical and actionable.

Example: In programming, this might mean learning the syntax for loops, conditionals, or functions in your chosen language.

• Tip: Focus on details that clarify the categories from Layer 2. Skip anything that doesn’t add to your understanding.

Now that you’ve mastered the essentials, you can expand your knowledge to include extra material.

---

Layer 4: Expand Your Horizons

Finally, move on to the extra material—less critical facts, trivia, or edge cases. While these aren’t essential to mastering the subject, they can be useful in specialized discussions or exams.

Example: Learn about rare programming quirks or historical trivia about a language’s development.

• Tip: Spend minimal time here unless it’s necessary for your goals. It’s okay to skim if you’re short on time.

---

Pro Tips for Better Learning

1. Use Active Recall and Spaced Repetition

Test yourself without looking at notes. Review what you’ve learned at increasing intervals—like after a day, a week, and a month. This strengthens memory by forcing your brain to actively retrieve information.

2. Map It Out

Create visual aids like diagrams or concept maps to clarify relationships between ideas. These are particularly helpful for organizing categories in Layer 2.

3. Teach What You Learn

Explain the subject to someone else as if they’re hearing it for the first time. Teaching exposes any gaps in your understanding and helps reinforce the material.

4. Engage with LLMs and Discuss Concepts

Take advantage of tools like ChatGPT or similar large language models to explore your topic in greater depth. Use these tools to:
- Ask specific questions to clarify confusing points.
- Engage in discussions to simulate real-world applications of the subject.
- Generate examples or analogies that deepen your understanding.

Tip: Use LLMs as a study partner, but don’t rely solely on them. Combine these insights with your own critical thinking to develop a well-rounded perspective.

---

Get Started

Ready to try the Four-Layer Method? Take 15 minutes today to map out the big picture of a topic you’re curious about—what’s it all about, and why does it matter? By building your understanding step by step, you’ll master the subject with less stress and more confidence.

@ 39cc53c9:27168656

Read the original blog post

I'm launching a new service review section on this blog in collaboration with OrangeFren. These reviews are sponsored, yet the sponsorship does not influence the outcome of the evaluations. Reviews are done in advance, then, the service provider has the discretion to approve publication without modifications.

Sponsored reviews are independent from the kycnot.me list, being only part of the blog. The reviews have no impact on the scores of the listings or their continued presence on the list. Should any issues arise, I will not hesitate to remove any listing.

---

The review

WizardSwap is an instant exchange centred around privacy coins. It was launched in 2020 making it old enough to have weathered the 2021 bull run and the subsequent bearish year.

| Pros | Cons | |------|------| | Tor-friendly | Limited liquidity | | Guarantee of no KYC | Overly simplistic design | | Earn by providing liquidity | |

Rating: ★★★★★ Service Website: wizardswap.io

Liquidity

Right off the bat, we'll start off by pointing out that WizardSwap relies on its own liquidity reserves, meaning they aren't just a reseller of Binance or another exchange. They're also committed to a no-KYC policy, when asking them, they even promised they would rather refund a user their original coins, than force them to undergo any sort of verification.

On the one hand, full control over all their infrastructure gives users the most privacy and conviction about the KYC policies remaining in place.

On the other hand, this means the liquidity available for swapping isn't huge. At the time of testing we could only purchase at most about 0.73 BTC with XMR.

It's clear the team behind WizardSwap is aware of this shortfall and so they've come up with a solution unique among instant exchanges. They let you, the user, deposit any of the currencies they support into your account and earn a profit on the trades made using your liquidity.

Trading

Fees on WizardSwap are middle-of-the-pack. The normal fee is 2.2%. That's more than some exchanges that reserve the right to suddenly demand you undergo verification, yet less than half the fees on some other privacy-first exchanges. However as we mentioned in the section above you can earn almost all of that fee (2%) if you provide liquidity to WizardSwap.

It's good that with the current Bitcoin fee market their fees are constant regardless of how much, or how little, you send. This is in stark contrast with some of the alternative swap providers that will charge you a massive premium when attempting to swap small amounts of BTC away.

Test trades

Test trades are always performed without previous notice to the service provider.

During our testing we performed a few test trades and found that every single time WizardSwap immediately detected the incoming transaction and the amount we received was exactly what was quoted before depositing. The fees were inline with what WizardSwap advertises.

• Monero payment proof
• Bitcoin received
• Wizardswap TX link - it's possible that this link may cease to be valid at some point in the future.

ToS and KYC

WizardSwap does not have a Terms of Service or a Privacy Policy page, at least none that can be found by users. Instead, they offer a FAQ section where they addresses some basic questions.

The site does not mention any KYC or AML practices. It also does not specify how refunds are handled in case of failure. However, based on the FAQ section "What if I send funds after the offer expires?" it can be inferred that contacting support is necessary and network fees will be deducted from any refund.

UI & Tor

WizardSwap can be visited both via your usual browser and Tor Browser. Should you decide on the latter you'll find that the website works even with the most strict settings available in the Tor Browser (meaning no JavaScript).

However, when disabling Javascript you'll miss the live support chat, as well as automatic refreshing of the trade page. The lack of the first means that you will have no way to contact support from the trade page if anything goes wrong during your swap, although you can do so by mail.

One important thing to have in mind is that if you were to accidentally close the browser during the swap, and you did not save the swap ID or your browser history is disabled, you'll have no easy way to return to the trade. For this reason we suggest when you begin a trade to copy the url or ID to someplace safe, before sending any coins to WizardSwap.

The UI you'll be greeted by is simple, minimalist, and easy to navigate. It works well not just across browsers, but also across devices. You won't have any issues using this exchange on your phone.

Getting in touch

The team behind WizardSwap appears to be most active on X (formerly Twitter): https://twitter.com/WizardSwap_io

If you have any comments or suggestions about the exchange make sure to reach out to them. In the past they've been very receptive to user feedback, for instance a few months back WizardSwap was planning on removing DeepOnion, but the community behind that project got together ^1 and after reaching out WizardSwap reversed their decision ^2.

You can also contact them via email at: support @ wizardswap . io

Disclaimer

None of the above should be understood as investment or financial advice. The views are our own only and constitute a faithful representation of our experience in using and investigating this exchange. This review is not a guarantee of any kind on the services rendered by the exchange. Do your own research before using any service.

@ fe32298e:20516265

Today I learned how to install NVapi to monitor my GPUs in Home Assistant.

NVApi is a lightweight API designed for monitoring NVIDIA GPU utilization and enabling automated power management. It provides real-time GPU metrics, supports integration with tools like Home Assistant, and offers flexible power management and PCIe link speed management based on workload and thermal conditions.

• GPU Utilization Monitoring: Utilization, memory usage, temperature, fan speed, and power consumption.
• Automated Power Limiting: Adjusts power limits dynamically based on temperature thresholds and total power caps, configurable per GPU or globally.
• Cross-GPU Coordination: Total power budget applies across multiple GPUs in the same system.
• PCIe Link Speed Management: Controls minimum and maximum PCIe link speeds with idle thresholds for power optimization.
• Home Assistant Integration: Uses the built-in RESTful platform and template sensors.

Getting the Data

sudo apt install golang-go git clone https://github.com/sammcj/NVApi.git cd NVapi go run main.go -port 9999 -rate 1 curl http://localhost:9999/gpu

Response for a single GPU: [ { "index": 0, "name": "NVIDIA GeForce RTX 4090", "gpu_utilisation": 0, "memory_utilisation": 0, "power_watts": 16, "power_limit_watts": 450, "memory_total_gb": 23.99, "memory_used_gb": 0.46, "memory_free_gb": 23.52, "memory_usage_percent": 2, "temperature": 38, "processes": [], "pcie_link_state": "not managed" } ]

Response for multiple GPUs: [ { "index": 0, "name": "NVIDIA GeForce RTX 3090", "gpu_utilisation": 0, "memory_utilisation": 0, "power_watts": 14, "power_limit_watts": 350, "memory_total_gb": 24, "memory_used_gb": 0.43, "memory_free_gb": 23.57, "memory_usage_percent": 2, "temperature": 36, "processes": [], "pcie_link_state": "not managed" }, { "index": 1, "name": "NVIDIA RTX A4000", "gpu_utilisation": 0, "memory_utilisation": 0, "power_watts": 10, "power_limit_watts": 140, "memory_total_gb": 15.99, "memory_used_gb": 0.56, "memory_free_gb": 15.43, "memory_usage_percent": 3, "temperature": 41, "processes": [], "pcie_link_state": "not managed" } ]

Start at Boot

Create /etc/systemd/system/nvapi.service:

``` [Unit] Description=Run NVapi After=network.target

[Service] Type=simple Environment="GOPATH=/home/ansible/go" WorkingDirectory=/home/ansible/NVapi ExecStart=/usr/bin/go run main.go -port 9999 -rate 1 Restart=always User=ansible

Environment="GPU_TEMP_CHECK_INTERVAL=5"

Environment="GPU_TOTAL_POWER_CAP=400"

Environment="GPU_0_LOW_TEMP=40"

Environment="GPU_0_MEDIUM_TEMP=70"

Environment="GPU_0_LOW_TEMP_LIMIT=135"

Environment="GPU_0_MEDIUM_TEMP_LIMIT=120"

Environment="GPU_0_HIGH_TEMP_LIMIT=100"

Environment="GPU_1_LOW_TEMP=45"

Environment="GPU_1_MEDIUM_TEMP=75"

Environment="GPU_1_LOW_TEMP_LIMIT=140"

Environment="GPU_1_MEDIUM_TEMP_LIMIT=125"

Environment="GPU_1_HIGH_TEMP_LIMIT=110"

[Install] WantedBy=multi-user.target ```

Home Assistant

Add to Home Assistant configuration.yaml and restart HA (completely).

For a single GPU, this works: ``` sensor: - platform: rest name: MYPC GPU Information resource: http://mypc:9999 method: GET headers: Content-Type: application/json value_template: "{{ value_json[0].index }}" json_attributes: - name - gpu_utilisation - memory_utilisation - power_watts - power_limit_watts - memory_total_gb - memory_used_gb - memory_free_gb - memory_usage_percent - temperature scan_interval: 1 # seconds

• platform: template sensors: mypc_gpu_0_gpu: friendly_name: "MYPC {{ state_attr('sensor.mypc_gpu_information', 'name') }} GPU" value_template: "{{ state_attr('sensor.mypc_gpu_information', 'gpu_utilisation') }}" unit_of_measurement: "%" mypc_gpu_0_memory: friendly_name: "MYPC {{ state_attr('sensor.mypc_gpu_information', 'name') }} Memory" value_template: "{{ state_attr('sensor.mypc_gpu_information', 'memory_utilisation') }}" unit_of_measurement: "%" mypc_gpu_0_power: friendly_name: "MYPC {{ state_attr('sensor.mypc_gpu_information', 'name') }} Power" value_template: "{{ state_attr('sensor.mypc_gpu_information', 'power_watts') }}" unit_of_measurement: "W" mypc_gpu_0_power_limit: friendly_name: "MYPC {{ state_attr('sensor.mypc_gpu_information', 'name') }} Power Limit" value_template: "{{ state_attr('sensor.mypc_gpu_information', 'power_limit_watts') }}" unit_of_measurement: "W" mypc_gpu_0_temperature: friendly_name: "MYPC {{ state_attr('sensor.mypc_gpu_information', 'name') }} Temperature" value_template: "{{ state_attr('sensor.mypc_gpu_information', 'temperature') }}" unit_of_measurement: "°C" ```

For multiple GPUs: ``` rest: scan_interval: 1 resource: http://mypc:9999 sensor: - name: "MYPC GPU0 Information" value_template: "{{ value_json[0].index }}" json_attributes_path: "$.0" json_attributes: - name - gpu_utilisation - memory_utilisation - power_watts - power_limit_watts - memory_total_gb - memory_used_gb - memory_free_gb - memory_usage_percent - temperature - name: "MYPC GPU1 Information" value_template: "{{ value_json[1].index }}" json_attributes_path: "$.1" json_attributes: - name - gpu_utilisation - memory_utilisation - power_watts - power_limit_watts - memory_total_gb - memory_used_gb - memory_free_gb - memory_usage_percent - temperature

• platform: template sensors: mypc_gpu_0_gpu: friendly_name: "MYPC GPU0 GPU" value_template: "{{ state_attr('sensor.mypc_gpu0_information', 'gpu_utilisation') }}" unit_of_measurement: "%" mypc_gpu_0_memory: friendly_name: "MYPC GPU0 Memory" value_template: "{{ state_attr('sensor.mypc_gpu0_information', 'memory_utilisation') }}" unit_of_measurement: "%" mypc_gpu_0_power: friendly_name: "MYPC GPU0 Power" value_template: "{{ state_attr('sensor.mypc_gpu0_information', 'power_watts') }}" unit_of_measurement: "W" mypc_gpu_0_power_limit: friendly_name: "MYPC GPU0 Power Limit" value_template: "{{ state_attr('sensor.mypc_gpu0_information', 'power_limit_watts') }}" unit_of_measurement: "W" mypc_gpu_0_temperature: friendly_name: "MYPC GPU0 Temperature" value_template: "{{ state_attr('sensor.mypc_gpu0_information', 'temperature') }}" unit_of_measurement: "C"

• platform: template sensors: mypc_gpu_1_gpu: friendly_name: "MYPC GPU1 GPU" value_template: "{{ state_attr('sensor.mypc_gpu1_information', 'gpu_utilisation') }}" unit_of_measurement: "%" mypc_gpu_1_memory: friendly_name: "MYPC GPU1 Memory" value_template: "{{ state_attr('sensor.mypc_gpu1_information', 'memory_utilisation') }}" unit_of_measurement: "%" mypc_gpu_1_power: friendly_name: "MYPC GPU1 Power" value_template: "{{ state_attr('sensor.mypc_gpu1_information', 'power_watts') }}" unit_of_measurement: "W" mypc_gpu_1_power_limit: friendly_name: "MYPC GPU1 Power Limit" value_template: "{{ state_attr('sensor.mypc_gpu1_information', 'power_limit_watts') }}" unit_of_measurement: "W" mypc_gpu_1_temperature: friendly_name: "MYPC GPU1 Temperature" value_template: "{{ state_attr('sensor.mypc_gpu1_information', 'temperature') }}" unit_of_measurement: "C"

```

Basic entity card: type: entities entities: - entity: sensor.mypc_gpu_0_gpu secondary_info: last-updated - entity: sensor.mypc_gpu_0_memory secondary_info: last-updated - entity: sensor.mypc_gpu_0_power secondary_info: last-updated - entity: sensor.mypc_gpu_0_power_limit secondary_info: last-updated - entity: sensor.mypc_gpu_0_temperature secondary_info: last-updated

Ansible Role

```

• name: install go become: true package: name: golang-go state: present

• name: git clone git: repo: "https://github.com/sammcj/NVApi.git" dest: "/home/ansible/NVapi" update: yes force: true

go run main.go -port 9999 -rate 1

• name: install systemd service become: true copy: src: nvapi.service dest: /etc/systemd/system/nvapi.service

• name: Reload systemd daemons, enable, and restart nvapi become: true systemd: name: nvapi daemon_reload: yes enabled: yes state: restarted ```

@ 04c915da:3dfbecc9

One of the most common criticisms leveled against nostr is the perceived lack of assurance when it comes to data storage. Critics argue that without a centralized authority guaranteeing that all data is preserved, important information will be lost. They also claim that running a relay will become prohibitively expensive. While there is truth to these concerns, they miss the mark. The genius of nostr lies in its flexibility, resilience, and the way it harnesses human incentives to ensure data availability in practice.

A nostr relay is simply a server that holds cryptographically verifiable signed data and makes it available to others. Relays are simple, flexible, open, and require no permission to run. Critics are right that operating a relay attempting to store all nostr data will be costly. What they miss is that most will not run all encompassing archive relays. Nostr does not rely on massive archive relays. Instead, anyone can run a relay and choose to store whatever subset of data they want. This keeps costs low and operations flexible, making relay operation accessible to all sorts of individuals and entities with varying use cases.

Critics are correct that there is no ironclad guarantee that every piece of data will always be available. Unlike bitcoin where data permanence is baked into the system at a steep cost, nostr does not promise that every random note or meme will be preserved forever. That said, in practice, any data perceived as valuable by someone will likely be stored and distributed by multiple entities. If something matters to someone, they will keep a signed copy.

Nostr is the Streisand Effect in protocol form. The Streisand effect is when an attempt to suppress information backfires, causing it to spread even further. With nostr, anyone can broadcast signed data, anyone can store it, and anyone can distribute it. Try to censor something important? Good luck. The moment it catches attention, it will be stored on relays across the globe, copied, and shared by those who find it worth keeping. Data deemed important will be replicated across servers by individuals acting in their own interest.

Nostr’s distributed nature ensures that the system does not rely on a single point of failure or a corporate overlord. Instead, it leans on the collective will of its users. The result is a network where costs stay manageable, participation is open to all, and valuable verifiable data is stored and distributed forever.

@ 6f6b50bb:a848e5a1

Che cosa significherebbe trattare l'IA come uno strumento invece che come una persona?

Dall’avvio di ChatGPT, le esplorazioni in due direzioni hanno preso velocità.

La prima direzione riguarda le capacità tecniche. Quanto grande possiamo addestrare un modello? Quanto bene può rispondere alle domande del SAT? Con quanta efficienza possiamo distribuirlo?

La seconda direzione riguarda il design dell’interazione. Come comunichiamo con un modello? Come possiamo usarlo per un lavoro utile? Quale metafora usiamo per ragionare su di esso?

La prima direzione è ampiamente seguita e enormemente finanziata, e per una buona ragione: i progressi nelle capacità tecniche sono alla base di ogni possibile applicazione. Ma la seconda è altrettanto cruciale per il campo e ha enormi incognite. Siamo solo a pochi anni dall’inizio dell’era dei grandi modelli. Quali sono le probabilità che abbiamo già capito i modi migliori per usarli?

Propongo una nuova modalità di interazione, in cui i modelli svolgano il ruolo di applicazioni informatiche (ad esempio app per telefoni): fornendo un’interfaccia grafica, interpretando gli input degli utenti e aggiornando il loro stato. In questa modalità, invece di essere un “agente” che utilizza un computer per conto dell’essere umano, l’IA può fornire un ambiente informatico più ricco e potente che possiamo utilizzare.

Metafore per l’interazione

Al centro di un’interazione c’è una metafora che guida le aspettative di un utente su un sistema. I primi giorni dell’informatica hanno preso metafore come “scrivanie”, “macchine da scrivere”, “fogli di calcolo” e “lettere” e le hanno trasformate in equivalenti digitali, permettendo all’utente di ragionare sul loro comportamento. Puoi lasciare qualcosa sulla tua scrivania e tornare a prenderlo; hai bisogno di un indirizzo per inviare una lettera. Man mano che abbiamo sviluppato una conoscenza culturale di questi dispositivi, la necessità di queste particolari metafore è scomparsa, e con esse i design di interfaccia skeumorfici che le rafforzavano. Come un cestino o una matita, un computer è ora una metafora di se stesso.

La metafora dominante per i grandi modelli oggi è modello-come-persona. Questa è una metafora efficace perché le persone hanno capacità estese che conosciamo intuitivamente. Implica che possiamo avere una conversazione con un modello e porgli domande; che il modello possa collaborare con noi su un documento o un pezzo di codice; che possiamo assegnargli un compito da svolgere da solo e che tornerà quando sarà finito.

Tuttavia, trattare un modello come una persona limita profondamente il nostro modo di pensare all’interazione con esso. Le interazioni umane sono intrinsecamente lente e lineari, limitate dalla larghezza di banda e dalla natura a turni della comunicazione verbale. Come abbiamo tutti sperimentato, comunicare idee complesse in una conversazione è difficile e dispersivo. Quando vogliamo precisione, ci rivolgiamo invece a strumenti, utilizzando manipolazioni dirette e interfacce visive ad alta larghezza di banda per creare diagrammi, scrivere codice e progettare modelli CAD. Poiché concepiamo i modelli come persone, li utilizziamo attraverso conversazioni lente, anche se sono perfettamente in grado di accettare input diretti e rapidi e di produrre risultati visivi. Le metafore che utilizziamo limitano le esperienze che costruiamo, e la metafora modello-come-persona ci impedisce di esplorare il pieno potenziale dei grandi modelli.

Per molti casi d’uso, e specialmente per il lavoro produttivo, credo che il futuro risieda in un’altra metafora: modello-come-computer.

Usare un’IA come un computer

Sotto la metafora modello-come-computer, interagiremo con i grandi modelli seguendo le intuizioni che abbiamo sulle applicazioni informatiche (sia su desktop, tablet o telefono). Nota che ciò non significa che il modello sarà un’app tradizionale più di quanto il desktop di Windows fosse una scrivania letterale. “Applicazione informatica” sarà un modo per un modello di rappresentarsi a noi. Invece di agire come una persona, il modello agirà come un computer.

Agire come un computer significa produrre un’interfaccia grafica. Al posto del flusso lineare di testo in stile telescrivente fornito da ChatGPT, un sistema modello-come-computer genererà qualcosa che somiglia all’interfaccia di un’applicazione moderna: pulsanti, cursori, schede, immagini, grafici e tutto il resto. Questo affronta limitazioni chiave dell’interfaccia di chat standard modello-come-persona:

• Scoperta. Un buon strumento suggerisce i suoi usi. Quando l’unica interfaccia è una casella di testo vuota, spetta all’utente capire cosa fare e comprendere i limiti del sistema. La barra laterale Modifica in Lightroom è un ottimo modo per imparare l’editing fotografico perché non si limita a dirti cosa può fare questa applicazione con una foto, ma cosa potresti voler fare. Allo stesso modo, un’interfaccia modello-come-computer per DALL-E potrebbe mostrare nuove possibilità per le tue generazioni di immagini.

• Efficienza. La manipolazione diretta è più rapida che scrivere una richiesta a parole. Per continuare l’esempio di Lightroom, sarebbe impensabile modificare una foto dicendo a una persona quali cursori spostare e di quanto. Ci vorrebbe un giorno intero per chiedere un’esposizione leggermente più bassa e una vibranza leggermente più alta, solo per vedere come apparirebbe. Nella metafora modello-come-computer, il modello può creare strumenti che ti permettono di comunicare ciò che vuoi più efficientemente e quindi di fare le cose più rapidamente.

A differenza di un’app tradizionale, questa interfaccia grafica è generata dal modello su richiesta. Questo significa che ogni parte dell’interfaccia che vedi è rilevante per ciò che stai facendo in quel momento, inclusi i contenuti specifici del tuo lavoro. Significa anche che, se desideri un’interfaccia più ampia o diversa, puoi semplicemente richiederla. Potresti chiedere a DALL-E di produrre alcuni preset modificabili per le sue impostazioni ispirati da famosi artisti di schizzi. Quando clicchi sul preset Leonardo da Vinci, imposta i cursori per disegni prospettici altamente dettagliati in inchiostro nero. Se clicchi su Charles Schulz, seleziona fumetti tecnicolor 2D a basso dettaglio.

Una bicicletta della mente proteiforme

La metafora modello-come-persona ha una curiosa tendenza a creare distanza tra l’utente e il modello, rispecchiando il divario di comunicazione tra due persone che può essere ridotto ma mai completamente colmato. A causa della difficoltà e del costo di comunicare a parole, le persone tendono a suddividere i compiti tra loro in blocchi grandi e il più indipendenti possibile. Le interfacce modello-come-persona seguono questo schema: non vale la pena dire a un modello di aggiungere un return statement alla tua funzione quando è più veloce scriverlo da solo. Con il sovraccarico della comunicazione, i sistemi modello-come-persona sono più utili quando possono fare un intero blocco di lavoro da soli. Fanno le cose per te.

Questo contrasta con il modo in cui interagiamo con i computer o altri strumenti. Gli strumenti producono feedback visivi in tempo reale e sono controllati attraverso manipolazioni dirette. Hanno un overhead comunicativo così basso che non è necessario specificare un blocco di lavoro indipendente. Ha più senso mantenere l’umano nel loop e dirigere lo strumento momento per momento. Come stivali delle sette leghe, gli strumenti ti permettono di andare più lontano a ogni passo, ma sei ancora tu a fare il lavoro. Ti permettono di fare le cose più velocemente.

Considera il compito di costruire un sito web usando un grande modello. Con le interfacce di oggi, potresti trattare il modello come un appaltatore o un collaboratore. Cercheresti di scrivere a parole il più possibile su come vuoi che il sito appaia, cosa vuoi che dica e quali funzionalità vuoi che abbia. Il modello genererebbe una prima bozza, tu la eseguirai e poi fornirai un feedback. “Fai il logo un po’ più grande”, diresti, e “centra quella prima immagine principale”, e “deve esserci un pulsante di login nell’intestazione”. Per ottenere esattamente ciò che vuoi, invierai una lista molto lunga di richieste sempre più minuziose.

Un’interazione alternativa modello-come-computer sarebbe diversa: invece di costruire il sito web, il modello genererebbe un’interfaccia per te per costruirlo, dove ogni input dell’utente a quell’interfaccia interroga il grande modello sotto il cofano. Forse quando descrivi le tue necessità creerebbe un’interfaccia con una barra laterale e una finestra di anteprima. All’inizio la barra laterale contiene solo alcuni schizzi di layout che puoi scegliere come punto di partenza. Puoi cliccare su ciascuno di essi, e il modello scrive l’HTML per una pagina web usando quel layout e lo visualizza nella finestra di anteprima. Ora che hai una pagina su cui lavorare, la barra laterale guadagna opzioni aggiuntive che influenzano la pagina globalmente, come accoppiamenti di font e schemi di colore. L’anteprima funge da editor WYSIWYG, permettendoti di afferrare elementi e spostarli, modificarne i contenuti, ecc. A supportare tutto ciò è il modello, che vede queste azioni dell’utente e riscrive la pagina per corrispondere ai cambiamenti effettuati. Poiché il modello può generare un’interfaccia per aiutare te e lui a comunicare più efficientemente, puoi esercitare più controllo sul prodotto finale in meno tempo.

La metafora modello-come-computer ci incoraggia a pensare al modello come a uno strumento con cui interagire in tempo reale piuttosto che a un collaboratore a cui assegnare compiti. Invece di sostituire un tirocinante o un tutor, può essere una sorta di bicicletta proteiforme per la mente, una che è sempre costruita su misura esattamente per te e il terreno che intendi attraversare.

Un nuovo paradigma per l’informatica?

I modelli che possono generare interfacce su richiesta sono una frontiera completamente nuova nell’informatica. Potrebbero essere un paradigma del tutto nuovo, con il modo in cui cortocircuitano il modello di applicazione esistente. Dare agli utenti finali il potere di creare e modificare app al volo cambia fondamentalmente il modo in cui interagiamo con i computer. Al posto di una singola applicazione statica costruita da uno sviluppatore, un modello genererà un’applicazione su misura per l’utente e le sue esigenze immediate. Al posto della logica aziendale implementata nel codice, il modello interpreterà gli input dell’utente e aggiornerà l’interfaccia utente. È persino possibile che questo tipo di interfaccia generativa sostituisca completamente il sistema operativo, generando e gestendo interfacce e finestre al volo secondo necessità.

All’inizio, l’interfaccia generativa sarà un giocattolo, utile solo per l’esplorazione creativa e poche altre applicazioni di nicchia. Dopotutto, nessuno vorrebbe un’app di posta elettronica che occasionalmente invia email al tuo ex e mente sulla tua casella di posta. Ma gradualmente i modelli miglioreranno. Anche mentre si spingeranno ulteriormente nello spazio di esperienze completamente nuove, diventeranno lentamente abbastanza affidabili da essere utilizzati per un lavoro reale.

Piccoli pezzi di questo futuro esistono già. Anni fa Jonas Degrave ha dimostrato che ChatGPT poteva fare una buona simulazione di una riga di comando Linux. Allo stesso modo, websim.ai utilizza un LLM per generare siti web su richiesta mentre li navighi. Oasis, GameNGen e DIAMOND addestrano modelli video condizionati sull’azione su singoli videogiochi, permettendoti di giocare ad esempio a Doom dentro un grande modello. E Genie 2 genera videogiochi giocabili da prompt testuali. L’interfaccia generativa potrebbe ancora sembrare un’idea folle, ma non è così folle.

Ci sono enormi domande aperte su come apparirà tutto questo. Dove sarà inizialmente utile l’interfaccia generativa? Come condivideremo e distribuiremo le esperienze che creiamo collaborando con il modello, se esistono solo come contesto di un grande modello? Vorremmo davvero farlo? Quali nuovi tipi di esperienze saranno possibili? Come funzionerà tutto questo in pratica? I modelli genereranno interfacce come codice o produrranno direttamente pixel grezzi?

Non conosco ancora queste risposte. Dovremo sperimentare e scoprirlo!Che cosa significherebbe trattare l'IA come uno strumento invece che come una persona?

Dall’avvio di ChatGPT, le esplorazioni in due direzioni hanno preso velocità.

La prima direzione riguarda le capacità tecniche. Quanto grande possiamo addestrare un modello? Quanto bene può rispondere alle domande del SAT? Con quanta efficienza possiamo distribuirlo?

La seconda direzione riguarda il design dell’interazione. Come comunichiamo con un modello? Come possiamo usarlo per un lavoro utile? Quale metafora usiamo per ragionare su di esso?

La prima direzione è ampiamente seguita e enormemente finanziata, e per una buona ragione: i progressi nelle capacità tecniche sono alla base di ogni possibile applicazione. Ma la seconda è altrettanto cruciale per il campo e ha enormi incognite. Siamo solo a pochi anni dall’inizio dell’era dei grandi modelli. Quali sono le probabilità che abbiamo già capito i modi migliori per usarli?

Propongo una nuova modalità di interazione, in cui i modelli svolgano il ruolo di applicazioni informatiche (ad esempio app per telefoni): fornendo un’interfaccia grafica, interpretando gli input degli utenti e aggiornando il loro stato. In questa modalità, invece di essere un “agente” che utilizza un computer per conto dell’essere umano, l’IA può fornire un ambiente informatico più ricco e potente che possiamo utilizzare.

Metafore per l’interazione

Al centro di un’interazione c’è una metafora che guida le aspettative di un utente su un sistema. I primi giorni dell’informatica hanno preso metafore come “scrivanie”, “macchine da scrivere”, “fogli di calcolo” e “lettere” e le hanno trasformate in equivalenti digitali, permettendo all’utente di ragionare sul loro comportamento. Puoi lasciare qualcosa sulla tua scrivania e tornare a prenderlo; hai bisogno di un indirizzo per inviare una lettera. Man mano che abbiamo sviluppato una conoscenza culturale di questi dispositivi, la necessità di queste particolari metafore è scomparsa, e con esse i design di interfaccia skeumorfici che le rafforzavano. Come un cestino o una matita, un computer è ora una metafora di se stesso.

La metafora dominante per i grandi modelli oggi è modello-come-persona. Questa è una metafora efficace perché le persone hanno capacità estese che conosciamo intuitivamente. Implica che possiamo avere una conversazione con un modello e porgli domande; che il modello possa collaborare con noi su un documento o un pezzo di codice; che possiamo assegnargli un compito da svolgere da solo e che tornerà quando sarà finito.

Tuttavia, trattare un modello come una persona limita profondamente il nostro modo di pensare all’interazione con esso. Le interazioni umane sono intrinsecamente lente e lineari, limitate dalla larghezza di banda e dalla natura a turni della comunicazione verbale. Come abbiamo tutti sperimentato, comunicare idee complesse in una conversazione è difficile e dispersivo. Quando vogliamo precisione, ci rivolgiamo invece a strumenti, utilizzando manipolazioni dirette e interfacce visive ad alta larghezza di banda per creare diagrammi, scrivere codice e progettare modelli CAD. Poiché concepiamo i modelli come persone, li utilizziamo attraverso conversazioni lente, anche se sono perfettamente in grado di accettare input diretti e rapidi e di produrre risultati visivi. Le metafore che utilizziamo limitano le esperienze che costruiamo, e la metafora modello-come-persona ci impedisce di esplorare il pieno potenziale dei grandi modelli.

Per molti casi d’uso, e specialmente per il lavoro produttivo, credo che il futuro risieda in un’altra metafora: modello-come-computer.

Usare un’IA come un computer

Sotto la metafora modello-come-computer, interagiremo con i grandi modelli seguendo le intuizioni che abbiamo sulle applicazioni informatiche (sia su desktop, tablet o telefono). Nota che ciò non significa che il modello sarà un’app tradizionale più di quanto il desktop di Windows fosse una scrivania letterale. “Applicazione informatica” sarà un modo per un modello di rappresentarsi a noi. Invece di agire come una persona, il modello agirà come un computer.

Agire come un computer significa produrre un’interfaccia grafica. Al posto del flusso lineare di testo in stile telescrivente fornito da ChatGPT, un sistema modello-come-computer genererà qualcosa che somiglia all’interfaccia di un’applicazione moderna: pulsanti, cursori, schede, immagini, grafici e tutto il resto. Questo affronta limitazioni chiave dell’interfaccia di chat standard modello-come-persona:

Scoperta. Un buon strumento suggerisce i suoi usi. Quando l’unica interfaccia è una casella di testo vuota, spetta all’utente capire cosa fare e comprendere i limiti del sistema. La barra laterale Modifica in Lightroom è un ottimo modo per imparare l’editing fotografico perché non si limita a dirti cosa può fare questa applicazione con una foto, ma cosa potresti voler fare. Allo stesso modo, un’interfaccia modello-come-computer per DALL-E potrebbe mostrare nuove possibilità per le tue generazioni di immagini.

Efficienza. La manipolazione diretta è più rapida che scrivere una richiesta a parole. Per continuare l’esempio di Lightroom, sarebbe impensabile modificare una foto dicendo a una persona quali cursori spostare e di quanto. Ci vorrebbe un giorno intero per chiedere un’esposizione leggermente più bassa e una vibranza leggermente più alta, solo per vedere come apparirebbe. Nella metafora modello-come-computer, il modello può creare strumenti che ti permettono di comunicare ciò che vuoi più efficientemente e quindi di fare le cose più rapidamente.

A differenza di un’app tradizionale, questa interfaccia grafica è generata dal modello su richiesta. Questo significa che ogni parte dell’interfaccia che vedi è rilevante per ciò che stai facendo in quel momento, inclusi i contenuti specifici del tuo lavoro. Significa anche che, se desideri un’interfaccia più ampia o diversa, puoi semplicemente richiederla. Potresti chiedere a DALL-E di produrre alcuni preset modificabili per le sue impostazioni ispirati da famosi artisti di schizzi. Quando clicchi sul preset Leonardo da Vinci, imposta i cursori per disegni prospettici altamente dettagliati in inchiostro nero. Se clicchi su Charles Schulz, seleziona fumetti tecnicolor 2D a basso dettaglio.

Una bicicletta della mente proteiforme

La metafora modello-come-persona ha una curiosa tendenza a creare distanza tra l’utente e il modello, rispecchiando il divario di comunicazione tra due persone che può essere ridotto ma mai completamente colmato. A causa della difficoltà e del costo di comunicare a parole, le persone tendono a suddividere i compiti tra loro in blocchi grandi e il più indipendenti possibile. Le interfacce modello-come-persona seguono questo schema: non vale la pena dire a un modello di aggiungere un return statement alla tua funzione quando è più veloce scriverlo da solo. Con il sovraccarico della comunicazione, i sistemi modello-come-persona sono più utili quando possono fare un intero blocco di lavoro da soli. Fanno le cose per te.

Questo contrasta con il modo in cui interagiamo con i computer o altri strumenti. Gli strumenti producono feedback visivi in tempo reale e sono controllati attraverso manipolazioni dirette. Hanno un overhead comunicativo così basso che non è necessario specificare un blocco di lavoro indipendente. Ha più senso mantenere l’umano nel loop e dirigere lo strumento momento per momento. Come stivali delle sette leghe, gli strumenti ti permettono di andare più lontano a ogni passo, ma sei ancora tu a fare il lavoro. Ti permettono di fare le cose più velocemente.

Considera il compito di costruire un sito web usando un grande modello. Con le interfacce di oggi, potresti trattare il modello come un appaltatore o un collaboratore. Cercheresti di scrivere a parole il più possibile su come vuoi che il sito appaia, cosa vuoi che dica e quali funzionalità vuoi che abbia. Il modello genererebbe una prima bozza, tu la eseguirai e poi fornirai un feedback. “Fai il logo un po’ più grande”, diresti, e “centra quella prima immagine principale”, e “deve esserci un pulsante di login nell’intestazione”. Per ottenere esattamente ciò che vuoi, invierai una lista molto lunga di richieste sempre più minuziose.

Un’interazione alternativa modello-come-computer sarebbe diversa: invece di costruire il sito web, il modello genererebbe un’interfaccia per te per costruirlo, dove ogni input dell’utente a quell’interfaccia interroga il grande modello sotto il cofano. Forse quando descrivi le tue necessità creerebbe un’interfaccia con una barra laterale e una finestra di anteprima. All’inizio la barra laterale contiene solo alcuni schizzi di layout che puoi scegliere come punto di partenza. Puoi cliccare su ciascuno di essi, e il modello scrive l’HTML per una pagina web usando quel layout e lo visualizza nella finestra di anteprima. Ora che hai una pagina su cui lavorare, la barra laterale guadagna opzioni aggiuntive che influenzano la pagina globalmente, come accoppiamenti di font e schemi di colore. L’anteprima funge da editor WYSIWYG, permettendoti di afferrare elementi e spostarli, modificarne i contenuti, ecc. A supportare tutto ciò è il modello, che vede queste azioni dell’utente e riscrive la pagina per corrispondere ai cambiamenti effettuati. Poiché il modello può generare un’interfaccia per aiutare te e lui a comunicare più efficientemente, puoi esercitare più controllo sul prodotto finale in meno tempo.

La metafora modello-come-computer ci incoraggia a pensare al modello come a uno strumento con cui interagire in tempo reale piuttosto che a un collaboratore a cui assegnare compiti. Invece di sostituire un tirocinante o un tutor, può essere una sorta di bicicletta proteiforme per la mente, una che è sempre costruita su misura esattamente per te e il terreno che intendi attraversare.

Un nuovo paradigma per l’informatica?

I modelli che possono generare interfacce su richiesta sono una frontiera completamente nuova nell’informatica. Potrebbero essere un paradigma del tutto nuovo, con il modo in cui cortocircuitano il modello di applicazione esistente. Dare agli utenti finali il potere di creare e modificare app al volo cambia fondamentalmente il modo in cui interagiamo con i computer. Al posto di una singola applicazione statica costruita da uno sviluppatore, un modello genererà un’applicazione su misura per l’utente e le sue esigenze immediate. Al posto della logica aziendale implementata nel codice, il modello interpreterà gli input dell’utente e aggiornerà l’interfaccia utente. È persino possibile che questo tipo di interfaccia generativa sostituisca completamente il sistema operativo, generando e gestendo interfacce e finestre al volo secondo necessità.

All’inizio, l’interfaccia generativa sarà un giocattolo, utile solo per l’esplorazione creativa e poche altre applicazioni di nicchia. Dopotutto, nessuno vorrebbe un’app di posta elettronica che occasionalmente invia email al tuo ex e mente sulla tua casella di posta. Ma gradualmente i modelli miglioreranno. Anche mentre si spingeranno ulteriormente nello spazio di esperienze completamente nuove, diventeranno lentamente abbastanza affidabili da essere utilizzati per un lavoro reale.

Piccoli pezzi di questo futuro esistono già. Anni fa Jonas Degrave ha dimostrato che ChatGPT poteva fare una buona simulazione di una riga di comando Linux. Allo stesso modo, websim.ai utilizza un LLM per generare siti web su richiesta mentre li navighi. Oasis, GameNGen e DIAMOND addestrano modelli video condizionati sull’azione su singoli videogiochi, permettendoti di giocare ad esempio a Doom dentro un grande modello. E Genie 2 genera videogiochi giocabili da prompt testuali. L’interfaccia generativa potrebbe ancora sembrare un’idea folle, ma non è così folle.

Ci sono enormi domande aperte su come apparirà tutto questo. Dove sarà inizialmente utile l’interfaccia generativa? Come condivideremo e distribuiremo le esperienze che creiamo collaborando con il modello, se esistono solo come contesto di un grande modello? Vorremmo davvero farlo? Quali nuovi tipi di esperienze saranno possibili? Come funzionerà tutto questo in pratica? I modelli genereranno interfacce come codice o produrranno direttamente pixel grezzi?

Non conosco ancora queste risposte. Dovremo sperimentare e scoprirlo!

Tradotto da:\ https://willwhitney.com/computing-inside-ai.htmlhttps://willwhitney.com/computing-inside-ai.html

@ e6817453:b0ac3c39

I started a long series of articles about how to model different types of knowledge graphs in the relational model, which makes on-device memory models for AI agents possible.

We model-directed graphs

Also, graphs of entities

We even model hypergraphs

Last time, we discussed why classical triple and simple knowledge graphs are insufficient for AI agents and complex memory, especially in the domain of time-aware or multi-model knowledge.

So why do we need metagraphs, and what kind of challenge could they help us to solve?

• complex and nested event and temporal context and temporal relations as edges
• multi-mode and multilingual knowledge
• human-like memory for AI agents that has multiple contexts and relations between knowledge in neuron-like networks

MetaGraphs

A meta graph is a concept that extends the idea of a graph by allowing edges to become graphs. Meta Edges connect a set of nodes, which could also be subgraphs. So, at some level, node and edge are pretty similar in properties but act in different roles in a different context.
Also, in some cases, edges could be referenced as nodes.
This approach enables the representation of more complex relationships and hierarchies than a traditional graph structure allows. Let’s break down each term to understand better metagraphs and how they differ from hypergraphs and graphs.

Graph Basics

• A standard graph has a set of nodes (or vertices) and edges (connections between nodes).
• Edges are generally simple and typically represent a binary relationship between two nodes.
• For instance, an edge in a social network graph might indicate a “friend” relationship between two people (nodes).

Hypergraph

• A hypergraph extends the concept of an edge by allowing it to connect any number of nodes, not just two.
• Each connection, called a hyperedge, can link multiple nodes.
• This feature allows hypergraphs to model more complex relationships involving multiple entities simultaneously. For example, a hyperedge in a hypergraph could represent a project team, connecting all team members in a single relation.
• Despite its flexibility, a hypergraph doesn’t capture hierarchical or nested structures; it only generalizes the number of connections in an edge.

Metagraph

• A metagraph allows the edges to be graphs themselves. This means each edge can contain its own nodes and edges, creating nested, hierarchical structures.
• In a meta graph, an edge could represent a relationship defined by a graph. For instance, a meta graph could represent a network of organizations where each organization’s structure (departments and connections) is represented by its own internal graph and treated as an edge in the larger meta graph.
• This recursive structure allows metagraphs to model complex data with multiple layers of abstraction. They can capture multi-node relationships (as in hypergraphs) and detailed, structured information about each relationship.

Named Graphs and Graph of Graphs

As you can notice, the structure of a metagraph is quite complex and could be complex to model in relational and classical RDF setups. It could create a challenge of luck of tools and software solutions for your problem.
If you need to model nested graphs, you could use a much simpler model of Named graphs, which could take you quite far.

The concept of the named graph came from the RDF community, which needed to group some sets of triples. In this way, you form subgraphs inside an existing graph. You could refer to the subgraph as a regular node. This setup simplifies complex graphs, introduces hierarchies, and even adds features and properties of hypergraphs while keeping a directed nature.

It looks complex, but it is not so hard to model it with a slight modification of a directed graph.
So, the node could host graphs inside. Let's reflect this fact with a location for a node. If a node belongs to a main graph, we could set the location to null or introduce a main node . it is up to you

Nodes could have edges to nodes in different subgraphs. This structure allows any kind of nesting graphs. Edges stay location-free

Meta Graphs in Relational Model

Let’s try to make several attempts to model different meta-graphs with some constraints.

Directed Metagraph where edges are not used as nodes and could not contain subgraphs

In this case, the edge always points to two sets of nodes. This introduces an overhead of creating a node set for a single node. In this model, we can model empty node sets that could require application-level constraints to prevent such cases.

Directed Metagraph where edges are not used as nodes and could contain subgraphs

Adding a node set that could model a subgraph located in an edge is easy but could be separate from in-vertex or out-vert.
I also do not see a direct need to include subgraphs to a node, as we could just use a node set interchangeably, but it still could be a case.

Directed Metagraph where edges are used as nodes and could contain subgraphs

As you can notice, we operate all the time with node sets. We could simply allow the extension node set to elements set that include node and edge IDs, but in this case, we need to use uuid or any other strategy to differentiate node IDs from edge IDs. In this case, we have a collision of ephemeral edges or ephemeral nodes when we want to change the role and purpose of the node as an edge or vice versa.

A full-scale metagraph model is way too complex for a relational database.
So we need a better model.

Now, we have more flexibility but loose structural constraints. We cannot show that the element should have one vertex, one vertex, or both. This type of constraint has been moved to the application level. Also, the crucial question is about query and retrieval needs.
Any meta-graph model should be more focused on domain and needs and should be used in raw form. We did it for a pure theoretical purpose.

@ e6817453:b0ac3c39

Hey folks! Today, let’s dive into the intriguing world of neurosymbolic approaches, retrieval-augmented generation (RAG), and personal knowledge graphs (PKGs). Together, these concepts hold much potential for bringing true reasoning capabilities to large language models (LLMs). So, let’s break down how symbolic logic, knowledge graphs, and modern AI can come together to empower future AI systems to reason like humans.

The Neurosymbolic Approach: What It Means ?

Neurosymbolic AI combines two historically separate streams of artificial intelligence: symbolic reasoning and neural networks. Symbolic AI uses formal logic to process knowledge, similar to how we might solve problems or deduce information. On the other hand, neural networks, like those underlying GPT-4, focus on learning patterns from vast amounts of data — they are probabilistic statistical models that excel in generating human-like language and recognizing patterns but often lack deep, explicit reasoning.

While GPT-4 can produce impressive text, it’s still not very effective at reasoning in a truly logical way. Its foundation, transformers, allows it to excel in pattern recognition, but the models struggle with reasoning because, at their core, they rely on statistical probabilities rather than true symbolic logic. This is where neurosymbolic methods and knowledge graphs come in.

Symbolic Calculations and the Early Vision of AI

If we take a step back to the 1950s, the vision for artificial intelligence was very different. Early AI research was all about symbolic reasoning — where computers could perform logical calculations to derive new knowledge from a given set of rules and facts. Languages like Lisp emerged to support this vision, enabling programs to represent data and code as interchangeable symbols. Lisp was designed to be homoiconic, meaning it treated code as manipulatable data, making it capable of self-modification — a huge leap towards AI systems that could, in theory, understand and modify their own operations.

Lisp: The Earlier AI-Language

Lisp, short for “LISt Processor,” was developed by John McCarthy in 1958, and it became the cornerstone of early AI research. Lisp’s power lay in its flexibility and its use of symbolic expressions, which allowed developers to create programs that could manipulate symbols in ways that were very close to human reasoning. One of the most groundbreaking features of Lisp was its ability to treat code as data, known as homoiconicity, which meant that Lisp programs could introspect and transform themselves dynamically. This ability to adapt and modify its own structure gave Lisp an edge in tasks that required a form of self-awareness, which was key in the early days of AI when researchers were exploring what it meant for machines to “think.”

Lisp was not just a programming language—it represented the vision for artificial intelligence, where machines could evolve their understanding and rewrite their own programming. This idea formed the conceptual basis for many of the self-modifying and adaptive algorithms that are still explored today in AI research. Despite its decline in mainstream programming, Lisp’s influence can still be seen in the concepts used in modern machine learning and symbolic AI approaches.

Prolog: Formal Logic and Deductive Reasoning

In the 1970s, Prolog was developed—a language focused on formal logic and deductive reasoning. Unlike Lisp, based on lambda calculus, Prolog operates on formal logic rules, allowing it to perform deductive reasoning and solve logical puzzles. This made Prolog an ideal candidate for expert systems that needed to follow a sequence of logical steps, such as medical diagnostics or strategic planning.

Prolog, like Lisp, allowed symbols to be represented, understood, and used in calculations, creating another homoiconic language that allows reasoning. Prolog’s strength lies in its rule-based structure, which is well-suited for tasks that require logical inference and backtracking. These features made it a powerful tool for expert systems and AI research in the 1970s and 1980s.

The language is declarative in nature, meaning that you define the problem, and Prolog figures out how to solve it. By using formal logic and setting constraints, Prolog systems can derive conclusions from known facts, making it highly effective in fields requiring explicit logical frameworks, such as legal reasoning, diagnostics, and natural language understanding. These symbolic approaches were later overshadowed during the AI winter — but the ideas never really disappeared. They just evolved.

Solvers and Their Role in Complementing LLMs

One of the most powerful features of Prolog and similar logic-based systems is their use of solvers. Solvers are mechanisms that can take a set of rules and constraints and automatically find solutions that satisfy these conditions. This capability is incredibly useful when combined with LLMs, which excel at generating human-like language but need help with logical consistency and structured reasoning.

For instance, imagine a scenario where an LLM needs to answer a question involving multiple logical steps or a complex query that requires deducing facts from various pieces of information. In this case, a solver can derive valid conclusions based on a given set of logical rules, providing structured answers that the LLM can then articulate in natural language. This allows the LLM to retrieve information and ensure the logical integrity of its responses, leading to much more robust answers.

Solvers are also ideal for handling constraint satisfaction problems — situations where multiple conditions must be met simultaneously. In practical applications, this could include scheduling tasks, generating optimal recommendations, or even diagnosing issues where a set of symptoms must match possible diagnoses. Prolog’s solver capabilities and LLM’s natural language processing power can make these systems highly effective at providing intelligent, rule-compliant responses that traditional LLMs would struggle to produce alone.

By integrating neurosymbolic methods that utilize solvers, we can provide LLMs with a form of deductive reasoning that is missing from pure deep-learning approaches. This combination has the potential to significantly improve the quality of outputs for use-cases that require explicit, structured problem-solving, from legal queries to scientific research and beyond. Solvers give LLMs the backbone they need to not just generate answers but to do so in a way that respects logical rigor and complex constraints.

Graph of Rules for Enhanced Reasoning

Another powerful concept that complements LLMs is using a graph of rules. A graph of rules is essentially a structured collection of logical rules that interconnect in a network-like structure, defining how various entities and their relationships interact. This structured network allows for complex reasoning and information retrieval, as well as the ability to model intricate relationships between different pieces of knowledge.

In a graph of rules, each node represents a rule, and the edges define relationships between those rules — such as dependencies or causal links. This structure can be used to enhance LLM capabilities by providing them with a formal set of rules and relationships to follow, which improves logical consistency and reasoning depth. When an LLM encounters a problem or a question that requires multiple logical steps, it can traverse this graph of rules to generate an answer that is not only linguistically fluent but also logically robust.

For example, in a healthcare application, a graph of rules might include nodes for medical symptoms, possible diagnoses, and recommended treatments. When an LLM receives a query regarding a patient’s symptoms, it can use the graph to traverse from symptoms to potential diagnoses and then to treatment options, ensuring that the response is coherent and medically sound. The graph of rules guides reasoning, enabling LLMs to handle complex, multi-step questions that involve chains of reasoning, rather than merely generating surface-level responses.

Graphs of rules also enable modular reasoning, where different sets of rules can be activated based on the context or the type of question being asked. This modularity is crucial for creating adaptive AI systems that can apply specific sets of logical frameworks to distinct problem domains, thereby greatly enhancing their versatility. The combination of neural fluency with rule-based structure gives LLMs the ability to conduct more advanced reasoning, ultimately making them more reliable and effective in domains where accuracy and logical consistency are critical.

By implementing a graph of rules, LLMs are empowered to perform deductive reasoning alongside their generative capabilities, creating responses that are not only compelling but also logically aligned with the structured knowledge available in the system. This further enhances their potential applications in fields such as law, engineering, finance, and scientific research — domains where logical consistency is as important as linguistic coherence.

Enhancing LLMs with Symbolic Reasoning

Now, with LLMs like GPT-4 being mainstream, there is an emerging need to add real reasoning capabilities to them. This is where neurosymbolic approaches shine. Instead of pitting neural networks against symbolic reasoning, these methods combine the best of both worlds. The neural aspect provides language fluency and recognition of complex patterns, while the symbolic side offers real reasoning power through formal logic and rule-based frameworks.

Personal Knowledge Graphs (PKGs) come into play here as well. Knowledge graphs are data structures that encode entities and their relationships — they’re essentially semantic networks that allow for structured information retrieval. When integrated with neurosymbolic approaches, LLMs can use these graphs to answer questions in a far more contextual and precise way. By retrieving relevant information from a knowledge graph, they can ground their responses in well-defined relationships, thus improving both the relevance and the logical consistency of their answers.

Imagine combining an LLM with a graph of rules that allow it to reason through the relationships encoded in a personal knowledge graph. This could involve using deductive databases to form a sophisticated way to represent and reason with symbolic data — essentially constructing a powerful hybrid system that uses LLM capabilities for language fluency and rule-based logic for structured problem-solving.

My Research on Deductive Databases and Knowledge Graphs

I recently did some research on modeling knowledge graphs using deductive databases, such as DataLog — which can be thought of as a limited, data-oriented version of Prolog. What I’ve found is that it’s possible to use formal logic to model knowledge graphs, ontologies, and complex relationships elegantly as rules in a deductive system. Unlike classical RDF or traditional ontology-based models, which sometimes struggle with complex or evolving relationships, a deductive approach is more flexible and can easily support dynamic rules and reasoning.

Prolog and similar logic-driven frameworks can complement LLMs by handling the parts of reasoning where explicit rule-following is required. LLMs can benefit from these rule-based systems for tasks like entity recognition, logical inferences, and constructing or traversing knowledge graphs. We can even create a graph of rules that governs how relationships are formed or how logical deductions can be performed.

The future is really about creating an AI that is capable of both deep contextual understanding (using the powerful generative capacity of LLMs) and true reasoning (through symbolic systems and knowledge graphs). With the neurosymbolic approach, these AIs could be equipped not just to generate information but to explain their reasoning, form logical conclusions, and even improve their own understanding over time — getting us a step closer to true artificial general intelligence.

Why It Matters for LLM Employment

Using neurosymbolic RAG (retrieval-augmented generation) in conjunction with personal knowledge graphs could revolutionize how LLMs work in real-world applications. Imagine an LLM that understands not just language but also the relationships between different concepts — one that can navigate, reason, and explain complex knowledge domains by actively engaging with a personalized set of facts and rules.

This could lead to practical applications in areas like healthcare, finance, legal reasoning, or even personal productivity — where LLMs can help users solve complex problems logically, providing relevant information and well-justified reasoning paths. The combination of neural fluency with symbolic accuracy and deductive power is precisely the bridge we need to move beyond purely predictive AI to truly intelligent systems.

Let's explore these ideas further if you’re as fascinated by this as I am. Feel free to reach out, follow my YouTube channel, or check out some articles I’ll link below. And if you’re working on anything in this field, I’d love to collaborate!

Until next time, folks. Stay curious, and keep pushing the boundaries of AI!

@ 04c915da:3dfbecc9

Capitalism is the most effective system for scaling innovation. The pursuit of profit is an incredibly powerful human incentive. Most major improvements to human society and quality of life have resulted from this base incentive. Market competition often results in the best outcomes for all.

That said, some projects can never be monetized. They are open in nature and a business model would centralize control. Open protocols like bitcoin and nostr are not owned by anyone and if they were it would destroy the key value propositions they provide. No single entity can or should control their use. Anyone can build on them without permission.

As a result, open protocols must depend on donation based grant funding from the people and organizations that rely on them. This model works but it is slow and uncertain, a grind where sustainability is never fully reached but rather constantly sought. As someone who has been incredibly active in the open source grant funding space, I do not think people truly appreciate how difficult it is to raise charitable money and deploy it efficiently.

Projects that can be monetized should be. Profitability is a super power. When a business can generate revenue, it taps into a self sustaining cycle. Profit fuels growth and development while providing projects independence and agency. This flywheel effect is why companies like Google, Amazon, and Apple have scaled to global dominance. The profit incentive aligns human effort with efficiency. Businesses must innovate, cut waste, and deliver value to survive.

Contrast this with non monetized projects. Without profit, they lean on external support, which can dry up or shift with donor priorities. A profit driven model, on the other hand, is inherently leaner and more adaptable. It is not charity but survival. When survival is tied to delivering what people want, scale follows naturally.

The real magic happens when profitable, sustainable businesses are built on top of open protocols and software. Consider the many startups building on open source software stacks, such as Start9, Mempool, and Primal, offering premium services on top of the open source software they build out and maintain. Think of companies like Block or Strike, which leverage bitcoin’s open protocol to offer their services on top. These businesses amplify the open software and protocols they build on, driving adoption and improvement at a pace donations alone could never match.

When you combine open software and protocols with profit driven business the result are lean, sustainable companies that grow faster and serve more people than either could alone. Bitcoin’s network, for instance, benefits from businesses that profit off its existence, while nostr will expand as developers monetize apps built on the protocol.

Capitalism scales best because competition results in efficiency. Donation funded protocols and software lay the groundwork, while market driven businesses build on top. The profit incentive acts as a filter, ensuring resources flow to what works, while open systems keep the playing field accessible, empowering users and builders. Together, they create a flywheel of innovation, growth, and global benefit.

@ 39cc53c9:27168656

Read the original blog post

Bitcoin enthusiasts frequently and correctly remark how much value it adds to Bitcoin not to have a face, a leader, or a central authority behind it. This particularity means there isn't a single person to exert control over, or a single human point of failure who could become corrupt or harmful to the project.

Because of this, it is said that no other coin can be equally valuable as Bitcoin in terms of decentralization and trustworthiness. Bitcoin is unique not just for being first, but also because of how the events behind its inception developed. This implies that, from Bitcoin onwards, any coin created would have been created by someone, consequently having an authority behind it. For this and some other reasons, some people refer to Bitcoin as "The Immaculate Conception".

While other coins may have their own unique features and advantages, they may not be able to replicate Bitcoin's community-driven nature. However, one other cryptocurrency shares a similar story of mystery behind its creation: Monero.

History of Monero

Bytecoin and CryptoNote

In March 2014, a Bitcointalk thread titled "Bytecoin. Secure, private, untraceable since 2012" was initiated by a user under the nickname "DStrange"^1^. DStrange presented Bytecoin (BCN) as a unique cryptocurrency, in operation since July 2012. Unlike Bitcoin, it employed a new algorithm known as CryptoNote.

DStrange apparently stumbled upon the Bytecoin website by chance while mining a dying bitcoin fork, and decided to create a thread on Bitcointalk^1^. This sparked curiosity among some users, who wondered how could Bytecoin remain unnoticed since its alleged launch in 2012 until then^2^.

Some time after, a user brought up the "CryptoNote v2.0" whitepaper for the first time, underlining its innovative features^4^. Authored by the pseudonymous Nicolas van Saberhagen in October 2013, the CryptoNote v2 whitepaper^5^ highlighted the traceability and privacy problems in Bitcoin. Saberhagen argued that these flaws could not be quickly fixed, suggesting it would be more efficient to start a new project rather than trying to patch the original^5^, an statement simmilar to the one from Satoshi Nakamoto^6^.

Checking with Saberhagen's digital signature, the release date of the whitepaper seemed correct, which would mean that Cryptonote (v1) was created in 2012^7^, although there's an important detail: "Signing time is from the clock on the signer's computer" ^9^.

Moreover, the whitepaper v1 contains a footnote link to a Bitcointalk post dated May 5, 2013^10^, making it impossible for the whitepaper to have been signed and released on December 12, 2012.

As the narrative developed, users discovered that a significant 80% portion of Bytecoin had been pre-mined^11^ and blockchain dates seemed to be faked to make it look like it had been operating since 2012, leading to controversy surrounding the project.

The origins of CryptoNote and Bytecoin remain mysterious, leaving suspicions of a possible scam attempt, although the whitepaper had a good amount of work and thought on it.

The fork

In April 2014, the Bitcointalk user thankful_for_today, who had also participated in the Bytecoin thread^12^, announced plans to launch a Bytecoin fork named Bitmonero^13^.

The primary motivation behind this fork was "Because there is a number of technical and marketing issues I wanted to do differently. And also because I like ideas and technology and I want it to succeed"^14^. This time Bitmonero did things different from Bytecoin: there was no premine or instamine, and no portion of the block reward went to development.

However, thankful_for_today proposed controversial changes that the community disagreed with. Johnny Mnemonic relates the events surrounding Bitmonero and thankful_for_today in a Bitcointalk comment^15^:

When thankful_for_today launched BitMonero [...] he ignored everything that was discussed and just did what he wanted. The block reward was considerably steeper than what everyone was expecting. He also moved forward with 1-minute block times despite everyone's concerns about the increase of orphan blocks. He also didn't address the tail emission concern that should've (in my opinion) been in the code at launch time. Basically, he messed everything up. Then, he disappeared.

After disappearing for a while, thankful_for_today returned to find that the community had taken over the project. Johnny Mnemonic continues:

I, and others, started working on new forks that were closer to what everyone else was hoping for. [...] it was decided that the BitMonero project should just be taken over. There were like 9 or 10 interested parties at the time if my memory is correct. We voted on IRC to drop the "bit" from BitMonero and move forward with the project. Thankful_for_today suddenly resurfaced, and wasn't happy to learn the community had assumed control of the coin. He attempted to maintain his own fork (still calling it "BitMonero") for a while, but that quickly fell into obscurity.

The unfolding of these events show us the roots of Monero. Much like Satoshi Nakamoto, the creators behind CryptoNote/Bytecoin and thankful_for_today remain a mystery^17^, having disappeared without a trace. This enigma only adds to Monero's value.

Since community took over development, believing in the project's potential and its ability to be guided in a better direction, Monero was given one of Bitcoin's most important qualities: a leaderless nature. With no single face or entity directing its path, Monero is safe from potential corruption or harm from a "central authority".

The community continued developing Monero until today. Since then, Monero has undergone a lot of technological improvements, migrations and achievements such as RingCT and RandomX. It also has developed its own Community Crowdfundinc System, conferences such as MoneroKon and Monerotopia are taking place every year, and has a very active community around it.

Monero continues to develop with goals of privacy and security first, ease of use and efficiency second. ^16^

This stands as a testament to the power of a dedicated community operating without a central figure of authority. This decentralized approach aligns with the original ethos of cryptocurrency, making Monero a prime example of community-driven innovation. For this, I thank all the people involved in Monero, that lead it to where it is today.

If you find any information that seems incorrect, unclear or any missing important events, please contact me and I will make the necessary changes.

Sources of interest

• https://forum.getmonero.org/20/general-discussion/211/history-of-monero
• https://monero.stackexchange.com/questions/852/what-is-the-origin-of-monero-and-its-relationship-to-bytecoin
• https://en.wikipedia.org/wiki/Monero
• https://bitcointalk.org/index.php?topic=583449.0
• https://bitcointalk.org/index.php?topic=563821.0
• https://bitcointalk.org/index.php?action=profile;u=233561
• https://bitcointalk.org/index.php?topic=512747.0
• https://bitcointalk.org/index.php?topic=740112.0
• https://monero.stackexchange.com/a/1024
• https://inspec2t-project.eu/cryptocurrency-with-a-focus-on-anonymity-these-facts-are-known-about-monero/
• https://medium.com/coin-story/coin-perspective-13-riccardo-spagni-69ef82907bd1
• https://www.getmonero.org/resources/about/
• https://www.wired.com/2017/01/monero-drug-dealers-cryptocurrency-choice-fire/
• https://www.monero.how/why-monero-vs-bitcoin
• https://old.reddit.com/r/Monero/comments/u8e5yr/satoshi_nakamoto_talked_about_privacy_features/

@ e6817453:b0ac3c39

Introduction: Personal Knowledge Graphs and Linked Data

We will explore the world of personal knowledge graphs and discuss how they can be used to model complex information structures. Personal knowledge graphs aren’t just abstract collections of nodes and edges—they encode meaningful relationships, contextualizing data in ways that enrich our understanding of it. While the core structure might be a directed graph, we layer semantic meaning on top, enabling nuanced connections between data points.

The origin of knowledge graphs is deeply tied to concepts from linked data and the semantic web, ideas that emerged to better link scattered pieces of information across the web. This approach created an infrastructure where data islands could connect — facilitating everything from more insightful AI to improved personal data management.

In this article, we will explore how these ideas have evolved into tools for modeling AI’s semantic memory and look at how knowledge graphs can serve as a flexible foundation for encoding rich data contexts. We’ll specifically discuss three major paradigms: RDF (Resource Description Framework), property graphs, and a third way of modeling entities as graphs of graphs. Let’s get started.

Intro to RDF

The Resource Description Framework (RDF) has been one of the fundamental standards for linked data and knowledge graphs. RDF allows data to be modeled as triples: subject, predicate, and object. Essentially, you can think of it as a structured way to describe relationships: “X has a Y called Z.” For instance, “Berlin has a population of 3.5 million.” This modeling approach is quite flexible because RDF uses unique identifiers — usually URIs — to point to data entities, making linking straightforward and coherent.

RDFS, or RDF Schema, extends RDF to provide a basic vocabulary to structure the data even more. This lets us describe not only individual nodes but also relationships among types of data entities, like defining a class hierarchy or setting properties. For example, you could say that “Berlin” is an instance of a “City” and that cities are types of “Geographical Entities.” This kind of organization helps establish semantic meaning within the graph.

RDF and Advanced Topics

Lists and Sets in RDF

RDF also provides tools to model more complex data structures such as lists and sets, enabling the grouping of nodes. This extension makes it easier to model more natural, human-like knowledge, for example, describing attributes of an entity that may have multiple values. By adding RDF Schema and OWL (Web Ontology Language), you gain even more expressive power — being able to define logical rules or even derive new relationships from existing data.

Graph of Graphs

A significant feature of RDF is the ability to form complex nested structures, often referred to as graphs of graphs. This allows you to create “named graphs,” essentially subgraphs that can be independently referenced. For example, you could create a named graph for a particular dataset describing Berlin and another for a different geographical area. Then, you could connect them, allowing for more modular and reusable knowledge modeling.

Property Graphs

While RDF provides a robust framework, it’s not always the easiest to work with due to its heavy reliance on linking everything explicitly. This is where property graphs come into play. Property graphs are less focused on linking everything through triples and allow more expressive properties directly within nodes and edges.

For example, instead of using triples to represent each detail, a property graph might let you store all properties about an entity (e.g., “Berlin”) directly in a single node. This makes property graphs more intuitive for many developers and engineers because they more closely resemble object-oriented structures: you have entities (nodes) that possess attributes (properties) and are connected to other entities through relationships (edges).

The significant benefit here is a condensed representation, which speeds up traversal and queries in some scenarios. However, this also introduces a trade-off: while property graphs are more straightforward to query and maintain, they lack some complex relationship modeling features RDF offers, particularly when connecting properties to each other.

Graph of Graphs and Subgraphs for Entity Modeling

A third approach — which takes elements from RDF and property graphs — involves modeling entities using subgraphs or nested graphs. In this model, each entity can be represented as a graph. This allows for a detailed and flexible description of attributes without exploding every detail into individual triples or lump them all together into properties.

For instance, consider a person entity with a complex employment history. Instead of representing every employment detail in one node (as in a property graph), or as several linked nodes (as in RDF), you can treat the employment history as a subgraph. This subgraph could then contain nodes for different jobs, each linked with specific properties and connections. This approach keeps the complexity where it belongs and provides better flexibility when new attributes or entities need to be added.

Hypergraphs and Metagraphs

When discussing more advanced forms of graphs, we encounter hypergraphs and metagraphs. These take the idea of relationships to a new level. A hypergraph allows an edge to connect more than two nodes, which is extremely useful when modeling scenarios where relationships aren’t just pairwise. For example, a “Project” could connect multiple “People,” “Resources,” and “Outcomes,” all in a single edge. This way, hypergraphs help in reducing the complexity of modeling high-order relationships.

Metagraphs, on the other hand, enable nodes and edges to themselves be represented as graphs. This is an extremely powerful feature when we consider the needs of artificial intelligence, as it allows for the modeling of relationships between relationships, an essential aspect for any system that needs to capture not just facts, but their interdependencies and contexts.

Balancing Structure and Properties

One of the recurring challenges when modeling knowledge is finding the balance between structure and properties. With RDF, you get high flexibility and standardization, but complexity can quickly escalate as you decompose everything into triples. Property graphs simplify the representation by using attributes but lose out on the depth of connection modeling. Meanwhile, the graph-of-graphs approach and hypergraphs offer advanced modeling capabilities at the cost of increased computational complexity.

So, how do you decide which model to use? It comes down to your use case. RDF and nested graphs are strong contenders if you need deep linkage and are working with highly variable data. For more straightforward, engineer-friendly modeling, property graphs shine. And when dealing with very complex multi-way relationships or meta-level knowledge, hypergraphs and metagraphs provide the necessary tools.

The key takeaway is that only some approaches are perfect. Instead, it’s all about the modeling goals: how do you want to query the graph, what relationships are meaningful, and how much complexity are you willing to manage?

Conclusion

Modeling AI semantic memory using knowledge graphs is a challenging but rewarding process. The different approaches — RDF, property graphs, and advanced graph modeling techniques like nested graphs and hypergraphs — each offer unique strengths and weaknesses. Whether you are building a personal knowledge graph or scaling up to AI that integrates multiple streams of linked data, it’s essential to understand the trade-offs each approach brings.

In the end, the choice of representation comes down to the nature of your data and your specific needs for querying and maintaining semantic relationships. The world of knowledge graphs is vast, with many tools and frameworks to explore. Stay connected and keep experimenting to find the balance that works for your projects.

@ 08f96856:ffe59a09

เมื่อพูดถึง Bitcoin Standard หลายคนมักนึกถึงภาพโลกอนาคตที่ทุกคนใช้บิตคอยน์ซื้อกาแฟหรือของใช้ในชีวิตประจำวัน ภาพแบบนั้นดูเหมือนไกลตัวและเป็นไปไม่ได้ในความเป็นจริง หลายคนถึงกับพูดว่า “คงไม่ทันเห็นในช่วงชีวิตนี้หรอก” แต่ในมุมมองของผม Bitcoin Standard อาจไม่ได้เริ่มต้นจากการที่เราจ่ายบิตคอยน์โดยตรงในร้านค้า แต่อาจเริ่มจากบางสิ่งที่เงียบกว่า ลึกกว่า และเกิดขึ้นแล้วในขณะนี้ นั่นคือ การล่มสลายทีละน้อยของระบบเฟียตที่เราใช้กันอยู่

ระบบเงินที่อิงกับอำนาจรัฐกำลังเข้าสู่ช่วงขาลง รัฐบาลทั่วโลกกำลังจมอยู่ในภาระหนี้ระดับประวัติการณ์ แม้แต่ประเทศมหาอำนาจก็เริ่มแสดงสัญญาณของภาวะเสี่ยงผิดนัดชำระหนี้ อัตราเงินเฟ้อกลายเป็นปัญหาเรื้อรังที่ไม่มีท่าทีจะหายไป ธนาคารที่เคยโอนฟรีเริ่มกลับมาคิดค่าธรรมเนียม และประชาชนก็เริ่มรู้สึกถึงการเสื่อมศรัทธาในระบบการเงินดั้งเดิม แม้จะยังพูดกันไม่เต็มเสียงก็ตาม

ในขณะเดียวกัน บิตคอยน์เองก็กำลังพัฒนาแบบเงียบ ๆ เงียบ... แต่ไม่เคยหยุด โดยเฉพาะในระดับ Layer 2 ที่เริ่มแสดงศักยภาพอย่างจริงจัง Lightning Network เป็น Layer 2 ที่เปิดใช้งานมาได้ระยะเวลสหนึ่ง และยังคงมีบทบาทสำคัญที่สุดในระบบนิเวศของบิตคอยน์ มันทำให้การชำระเงินเร็วขึ้น มีต้นทุนต่ำ และไม่ต้องบันทึกทุกธุรกรรมลงบล็อกเชน เครือข่ายนี้กำลังขยายตัวทั้งในแง่ของโหนดและการใช้งานจริงทั่วโลก

ขณะเดียวกัน Layer 2 ทางเลือกอื่นอย่าง Ark Protocol ก็กำลังพัฒนาเพื่อตอบโจทย์ด้านความเป็นส่วนตัวและประสบการณ์ใช้งานที่ง่าย BitVM เปิดแนวทางใหม่ให้บิตคอยน์รองรับ smart contract ได้ในระดับ Turing-complete ซึ่งทำให้เกิดความเป็นไปได้ในกรณีใช้งานอีกมากมาย และเทคโนโลยีที่น่าสนใจอย่าง Taproot Assets, Cashu และ Fedimint ก็ทำให้การออกโทเคนหรือสกุลเงินที่อิงกับบิตคอยน์เป็นจริงได้บนโครงสร้างของบิตคอยน์เอง

เทคโนโลยีเหล่านี้ไม่ใช่การเติบโตแบบปาฏิหาริย์ แต่มันคืบหน้าอย่างต่อเนื่องและมั่นคง และนั่นคือเหตุผลที่มันจะ “อยู่รอด” ได้ในระยะยาว เมื่อฐานของความน่าเชื่อถือไม่ใช่บริษัท รัฐบาล หรือทุน แต่คือสิ่งที่ตรวจสอบได้และเปลี่ยนกฎไม่ได้

แน่นอนว่าบิตคอยน์ต้องแข่งขันกับ stable coin, เงินดิจิทัลของรัฐ และ cryptocurrency อื่น ๆ แต่สิ่งที่ทำให้มันเหนือกว่านั้นไม่ใช่ฟีเจอร์ หากแต่เป็นความทนทาน และความมั่นคงของกฎที่ไม่มีใครเปลี่ยนได้ ไม่มีทีมพัฒนา ไม่มีบริษัท ไม่มีประตูปิด หรือการยึดบัญชี มันยืนอยู่บนคณิตศาสตร์ พลังงาน และเวลา

หลายกรณีใช้งานที่เคยถูกทดลองในโลกคริปโตจะค่อย ๆ เคลื่อนเข้ามาสู่บิตคอยน์ เพราะโครงสร้างของมันแข็งแกร่งกว่า ไม่ต้องการทีมพัฒนาแกนกลาง ไม่ต้องพึ่งกลไกเสี่ยงต่อการผูกขาด และไม่ต้องการ “ความเชื่อใจ” จากใครเลย

Bitcoin Standard ที่ผมพูดถึงจึงไม่ใช่การเปลี่ยนแปลงแบบพลิกหน้ามือเป็นหลังมือ แต่คือการ “เปลี่ยนฐานของระบบ” ทีละชั้น ระบบการเงินใหม่ที่อิงอยู่กับบิตคอยน์กำลังเกิดขึ้นแล้ว มันไม่ใช่โลกที่ทุกคนถือเหรียญบิตคอยน์ แต่มันคือโลกที่คนใช้อาจไม่รู้ตัวด้วยซ้ำว่า “สิ่งที่เขาใช้นั้นอิงอยู่กับบิตคอยน์”

ผู้คนอาจใช้เงินดิจิทัลที่สร้างบน Layer 3 หรือ Layer 4 ผ่านแอป ผ่านแพลตฟอร์ม หรือผ่านสกุลเงินใหม่ที่ดูไม่ต่างจากเดิม แต่เบื้องหลังของระบบจะผูกไว้กับบิตคอยน์

และถ้ามองในเชิงพัฒนาการ บิตคอยน์ก็เหมือนกับอินเทอร์เน็ต ครั้งหนึ่งอินเทอร์เน็ตก็ถูกมองว่าเข้าใจยาก ต้องพิมพ์ http ต้องรู้จัก TCP/IP ต้องตั้ง proxy เอง แต่ปัจจุบันผู้คนใช้งานอินเทอร์เน็ตโดยไม่รู้ว่าเบื้องหลังมีอะไรเลย บิตคอยน์กำลังเดินตามเส้นทางเดียวกัน โปรโตคอลกำลังถอยออกจากสายตา และวันหนึ่งเราจะ “ใช้มัน” โดยไม่ต้องรู้ว่ามันคืออะไร

หากนับจากช่วงเริ่มต้นของอินเทอร์เน็ตในยุค 1990 จนกลายเป็นโครงสร้างหลักของโลกในสองทศวรรษ เส้นเวลาของบิตคอยน์ก็กำลังเดินตามรอยเท้าของอินเทอร์เน็ต และถ้าเราเชื่อว่าวัฏจักรของเทคโนโลยีมีจังหวะของมันเอง เราก็จะรู้ว่า Bitcoin Standard นั้นไม่ใช่เรื่องของอนาคตไกลโพ้น แต่มันเกิดขึ้นแล้ว

@ 39cc53c9:27168656

Read the original blog post

I've been thinking about how to improve my seed backup in a cheap and cool way, mostly for fun. Until now, I had the seed written on a piece of paper in a desk drawer, and I wanted something more durable and fire-proof.

Show me the final result!

After searching online, I found two options I liked the most: the Cryptosteel Capsule and the Trezor Keep. These products are nice but quite expensive, and I didn't want to spend that much on my seed backup. Privacy is also important, and sharing details like a shipping address makes me uncomfortable. This concern has grown since the Ledger incident^1. A $5 wrench attack^2 seems too cheap, even if you only hold a few sats.

Upon seeing the design of Cryptosteel, I considered creating something similar at home. Although it may not be as cool as their device, it could offer almost the same in terms of robustness and durability.

Step 1: Get the materials and tools

When choosing the materials, you will want to go with stainless steel. It is durable, resistant to fire, water, and corrosion, very robust, and does not rust. Also, its price point is just right; it's not the cheapest, but it's cheap for the value you get.

I went to a material store and bought:

• Two bolts
• Two hex nuts and head nuts for the bolts
• A bag of 30 washers

All items were made of stainless steel. The total price was around €6. This is enough for making two seed backups.

You will also need:

• A set of metal letter stamps (I bought a 2mm-size letter kit since my washers were small, 6mm in diameter)
  • You can find these in local stores or online marketplaces. The set I bought cost me €13.
• A good hammer
• A solid surface to stamp on

Total spent: 19€ for two backups

Step 2: Stamp and store

Once you have all the materials, you can start stamping your words. There are many videos on the internet that use fancy 3D-printed tools to get the letters nicely aligned, but I went with the free-hand option. The results were pretty decent.

I only stamped the first 4 letters for each word since the BIP-39 wordlist allows for this. Because my stamping kit did not include numbers, I used alphabet letters to define the order. This way, if all the washers were to fall off, I could still reassemble the seed correctly.

The final result

So this is the final result. I added two smaller washers as protection and also put the top washer reversed so the letters are not visible:

Compared to the Cryptosteel or the Trezor Keep, its size is much more compact. This makes for an easier-to-hide backup, in case you ever need to hide it inside your human body.

Some ideas

Tamper-evident seal

To enhance the security this backup, you can consider using a tamper-evident seal. This can be easily achieved by printing a unique image or using a specific day's newspaper page (just note somewhere what day it was).

Apply a thin layer of glue to the washer's surface and place the seal over it. If someone attempts to access the seed, they will be forced to destroy the seal, which will serve as an evident sign of tampering.

This simple measure will provide an additional layer of protection and allow you to quickly identify any unauthorized access attempts.

Note that this method is not resistant to outright theft. The tamper-evident seal won't stop a determined thief but it will prevent them from accessing your seed without leaving any trace.

Redundancy

Make sure to add redundancy. Make several copies of this cheap backup, and store them in separate locations.

Unique wordset

Another layer of security could be to implement your own custom mnemonic dictionary. However, this approach has the risk of permanently losing access to your funds if not implemented correctly.

If done properly, you could potentially end up with a highly secure backup, as no one else would be able to derive the seed phrase from it. To create your custom dictionary, assign a unique number from 1 to 2048 to a word of your choice. Maybe you could use a book, and index the first 2048 unique words that appear. Make sure to store this book and even get a couple copies of it (digitally and phisically).

This self-curated set of words will serve as your personal BIP-39 dictionary. When you need to translate between your custom dictionary and the official BIP-39 wordlist, simply use the index number to find the corresponding word in either list.

Never write the idex or words on your computer (Do not use Ctr+F)

@ e6817453:b0ac3c39

The temporal semantics and temporal and time-aware knowledge graphs. We have different memory models for artificial intelligence agents. We all try to mimic somehow how the brain works, or at least how the declarative memory of the brain works. We have the split of episodic memory and semantic memory. And we also have a lot of theories, right?

Declarative Memory of the Human Brain

How is the semantic memory formed? We all know that our brain stores semantic memory quite close to the concept we have with the personal knowledge graphs, that it’s connected entities. They form a connection with each other and all those things. So far, so good. And actually, then we have a lot of concepts, how the episodic memory and our experiences gets transmitted to the semantic:

• hippocampus indexing and retrieval
• sanitization of episodic memories
• episodic-semantic shift theory

They all give a different perspective on how different parts of declarative memory cooperate.

We know that episodic memories get semanticized over time. You have semantic knowledge without the notion of time, and probably, your episodic memory is just decayed.

But, you know, it’s still an open question:

do we want to mimic an AI agent’s memory as a human brain memory, or do we want to create something different?

It’s an open question to which we have no good answer. And if you go to the theory of neuroscience and check how episodic and semantic memory interfere, you will still find a lot of theories, yeah?

Some of them say that you have the hippocampus that keeps the indexes of the memory. Some others will say that you semantic the episodic memory. Some others say that you have some separate process that digests the episodic and experience to the semantics. But all of them agree on the plan that it’s operationally two separate areas of memories and even two separate regions of brain, and the semantic, it’s more, let’s say, protected.

So it’s harder to forget the semantical facts than the episodes and everything. And what I’m thinking about for a long time, it’s this, you know, the semantic memory.

Temporal Semantics

It’s memory about the facts, but you somehow mix the time information with the semantics. I already described a lot of things, including how we could combine time with knowledge graphs and how people do it.

There are multiple ways we could persist such information, but we all hit the wall because the complexity of time and the semantics of time are highly complex concepts.

Time in a Semantic context is not a timestamp.

What I mean is that when you have a fact, and you just mentioned that I was there at this particular moment, like, I don’t know, 15:40 on Monday, it’s already awake because we don’t know which Monday, right? So you need to give the exact date, but usually, you do not have experiences like that.

You do not record your memories like that, except you do the journaling and all of the things. So, usually, you have no direct time references. What I mean is that you could say that I was there and it was some event, blah, blah, blah.

Somehow, we form a chain of events that connect with each other and maybe will be connected to some period of time if we are lucky enough. This means that we could not easily represent temporal-aware information as just a timestamp or validity and all of the things.

For sure, the validity of the knowledge graphs (simple quintuple with start and end dates)is a big topic, and it could solve a lot of things. It could solve a lot of the time cases. It’s super simple because you give the end and start dates, and you are done, but it does not answer facts that have a relative time or time information in facts . It could solve many use cases but struggle with facts in an indirect temporal context. I like the simplicity of this idea. But the problem of this approach that in most cases, we simply don’t have these timestamps. We don’t have the timestamp where this information starts and ends. And it’s not modeling many events in our life, especially if you have the processes or ongoing activities or recurrent events.

I’m more about thinking about the time of semantics, where you have a time model as a hybrid clock or some global clock that does the partial ordering of the events. It’s mean that you have the chain of the experiences and you have the chain of the facts that have the different time contexts.

We could deduct the time from this chain of the events. But it’s a big, big topic for the research. But what I want to achieve, actually, it’s not separation on episodic and semantic memory. It’s having something in between.

Blockchain of connected events and facts

I call it temporal-aware semantics or time-aware knowledge graphs, where we could encode the semantic fact together with the time component.I doubt that time should be the simple timestamp or the region of the two timestamps. For me, it is more a chain for facts that have a partial order and form a blockchain like a database or a partially ordered Acyclic graph of facts that are temporally connected. We could have some notion of time that is understandable to the agent and a model that allows us to order the events and focus on what the agent knows and how to order this time knowledge and create the chains of the events.

Time anchors

We may have a particular time in the chain that allows us to arrange a more concrete time for the rest of the events. But it’s still an open topic for research. The temporal semantics gets split into a couple of domains. One domain is how to add time to the knowledge graphs. We already have many different solutions. I described them in my previous articles.

Another domain is the agent's memory and how the memory of the artificial intelligence treats the time. This one, it’s much more complex. Because here, we could not operate with the simple timestamps. We need to have the representation of time that are understandable by model and understandable by the agent that will work with this model. And this one, it’s way bigger topic for the research.”

@ 39cc53c9:27168656

Read the original blog post

kycnot.me features a somewhat hidden tool that some users may not be aware of. Every month, an automated job crawls every listed service's Terms of Service (ToS) and FAQ pages and conducts an AI-driven analysis, generating a comprehensive overview that highlights key points related to KYC and user privacy.

Here's an example: Changenow's Tos Review

Why?

ToS pages typically contain a lot of complicated text. Since the first versions of kycnot.me, I have tried to provide users a comprehensive overview of what can be found in such documents. This automated method keeps the information up-to-date every month, which was one of the main challenges with manual updates.

A significant part of the time I invest in investigating a service for kycnot.me involves reading the ToS and looking for any clauses that might indicate aggressive KYC practices or privacy concerns. For the past four years, I performed this task manually. However, with advancements in language models, this process can now be somewhat automated. I still manually review the ToS for a quick check and regularly verify the AI’s findings. However, over the past three months, this automated method has proven to be quite reliable.

Having a quick ToS overview section allows users to avoid reading the entire ToS page. Instead, you can quickly read the important points that are grouped, summarized, and referenced, making it easier and faster to understand the key information.

Limitations

This method has a key limitation: JS-generated pages. For this reason, I was using Playwright in my crawler implementation. I plan to make a release addressing this issue in the future. There are also sites that don't have ToS/FAQ pages, but these sites already include a warning in that section.

Another issue is false positives. Although not very common, sometimes the AI might incorrectly interpret something harmless as harmful. Such errors become apparent upon reading; it's clear when something marked as bad should not be categorized as such. I manually review these cases regularly, checking for anything that seems off and then removing any inaccuracies.

Overall, the automation provides great results.

How?

There have been several iterations of this tool. Initially, I started with GPT-3.5, but the results were not good in any way. It made up many things, and important thigs were lost on large ToS pages. I then switched to GPT-4 Turbo, but it was expensive. Eventually, I settled on Claude 3 Sonnet, which provides a quality compromise between GPT-3.5 and GPT-4 Turbo at a more reasonable price, while allowing a generous 200K token context window.

I designed a prompt, which is open source^1, that has been tweaked many times and will surely be adjusted further in the future.

For the ToS scraping part, I initially wrote a scraper API using Playwright^2, but I replaced it with Jina AI Reader^3, which works quite well and is designed for this task.

Non-conflictive ToS

All services have a dropdown in the ToS section called "Non-conflictive ToS Reviews." These are the reviews that the AI flagged as not needing a user warning. I still provide these because I think they may be interesting to read.

Feedback and contributing

You can give me feedback on this tool, or share any inaccuraties by either opening an issue on Codeberg^4 or by contacting me ^5.

You can contribute with pull requests, which are always welcome, or you can support this project with any of the listed ways.

@ 39cc53c9:27168656

Read the original blog post

These reviews are sponsored, yet the sponsorship does not influence the outcome of the evaluations. Sponsored reviews are independent from the kycnot.me list, being only part of the blog. The reviews have no impact on the scores of the listings or their continued presence on the list. Should any issues arise, I will not hesitate to remove any listing. Reviews are in collaboration with Orangefren.

The review

Swapter.io is an all-purpose instant exchange. They entered the scene in the depths of the bear market about 2 years ago in June of 2022.

| Pros | Cons | | --------------- | ---------------------------------- | | Low fees | Shotgun KYC with opaque triggers | | Large liquidity | Relies on 3rd party liquidity | | Works over Tor | Front-end not synced with back-end | | Pretty UI | |

Rating: ★★★☆☆ Service Website: swapter.io

⚠️ There is an ongoing issue with this service: read more on Reddit.

Test Trades

During our testing we performed a trade from XMR to LTC, and then back to XMR.

Our first trade had the ID of: mpUitpGemhN8jjNAjQuo6EvQ. We were promised 0.8 LTC for sending 0.5 XMR, before we sent the Monero. When the Monero arrived we were sent 0.799 LTC.

On the return journey we performed trade with ID: yaCRb5pYcRKAZcBqg0AzEGYg. This time we were promised 0.4815 XMR for sending 0.799 LTC. After Litecoin arrived we were sent 0.4765 XMR.

As such we saw a discrepancy of ~0.1% in the first trade and ~1% in the second trade. Considering those trades were floating we determine the estimates presented in the UI to be highly accurate and honest.

Of course Swapter could've been imposing a large fee on their estimates, but we checked their estimates against CoinGecko and found the difference to be equivalent to a fee of just over 0.5%. Perfectly in line with other swapping services.

Trading

Swapter supports BTC, LTC, XMR and well over a thousand other coins. Sadly they don't support the Lightning Network. For the myriad of currencies they deal with they provide massive upper limits. You could exchange tens, or even hundreds, of thousands of dollars worth of cryptocurrency in a single trade (although we wouldn't recommend it).

The flip side to this is that Swapter relies on 3rd party liquidity. Aside from the large liqudity this also benefits the user insofar as it allows for very low fees. However, it also comes with a negative - the 3rd party gets to see all your trades. Unfortunately Swapter opted not to share where they source their liquidity in their Privacy Policy or Terms of Service.

KYC & AML policies

Swapter reserves the right to require its users to provide their full name, their date of birth, their address and government-issued ID. A practice known as "shotgun KYC". This should not happen often - in our testing it never did - however it's not clear when exactly it could happen. The AML & KYC policy provided on Swapter's website simply states they will put your trade on hold if their "risk scoring system [deems it] as suspicious".

Worse yet, if they determine that "any of the information [the] customer provided is incorrect, false, outdated, or incomplete" then Swapter may decide to terminate all of the services they provide to the user. What exactly would happen to their funds in such a case remains unclear.

The only clarity we get is that the Swapter policy outlines a designated 3rd party that will verify the information provided by the user. The third party's name is Sum & Substance Ltd, also simply known as samsub and available at sumsub.com

It's understandable that some exchanges will decide on a policy of this sort, especially when they rely on external liquidity, but we would prefer more clarity be given. When exactly is a trade suspicious?

Tor

We were pleased to discover Swapter works over Tor. However, they do not provide a Tor mirror, nor do they work without JavaScript. Additionally, we found that some small features, such as the live chat, did not work over Tor. Fortunately, other means of contacting their support are still available.

UI

We have found the Swapter UI to be very modern, straightforward and simple to use. It's available in 4 languages (English, French, Dutch and Russian), although we're unable to vouch for the quality of some of those, the ones that we used seemed perfectly serviceable.

Our only issue with the UI was that it claims the funds have been sent following the trade, when in reality it seems to take the backend a minute or so to actually broadcast the transaction.

Getting in touch

Swapter's team has a chat on their website, a support email address and a support Telegram. Their social media presence in most active on Telegram and X (formerly Twitter).

Disclaimer

None of the above should be understood as investment or financial advice. The views are our own only and constitute a faithful representation of our experience in using and investigating this exchange. This review is not a guarantee of any kind on the services rendered by the exchange. Do your own research before using any service.

@ d360efec:14907b5f

🚀📉 #BTC วิเคราะห์ H2! พุ่งชน 105K แล้วเจอแรงขาย... จับตา FVG 100.5K เป็นจุดวัดใจ! 👀📊

จากากรวิเคราะห์ทางเทคนิคสำหรับ #Bitcoin ในกรอบเวลา H2:

สัปดาห์ที่แล้ว #BTC ได้เบรคและพุ่งขึ้นอย่างแข็งแกร่งค่ะ 📈⚡ แต่เมื่อวันจันทร์ที่ผ่านมา ราคาได้ขึ้นไปชนแนวต้านบริเวณ 105,000 ดอลลาร์ แล้วเจอแรงขายย่อตัวลงมาตลอดทั้งวันค่ะ 🧱📉

ตอนนี้ ระดับที่น่าจับตาอย่างยิ่งคือโซน H4 FVG (Fair Value Gap ในกราฟ 4 ชั่วโมง) ที่ 100,500 ดอลลาร์ ค่ะ 🎯 (FVG คือโซนที่ราคาวิ่งผ่านไปเร็วๆ และมักเป็นบริเวณที่ราคามีโอกาสกลับมาทดสอบ/เติมเต็ม)

👇 โซน FVG ที่ 100.5K นี้ ยังคงเป็น Area of Interest ที่น่าสนใจสำหรับมองหาจังหวะ Long เพื่อลุ้นการขึ้นในคลื่นลูกถัดไปค่ะ!

🤔💡 อย่างไรก็ตาม การตัดสินใจเข้า Long หรือเทรดที่บริเวณนี้ ขึ้นอยู่กับว่าราคา แสดงปฏิกิริยาอย่างไรเมื่อมาถึงโซน 100.5K นี้ เพื่อยืนยันสัญญาณสำหรับการเคลื่อนไหวที่จะขึ้นสูงกว่าเดิมค่ะ!

เฝ้าดู Price Action ที่ระดับนี้อย่างใกล้ชิดนะคะ! 📍

BTC #Bitcoin #Crypto #คริปโต #TechnicalAnalysis #Trading #FVG #FairValueGap #PriceAction #MarketAnalysis #ลงทุนคริปโต #วิเคราะห์กราฟ #TradeSetup #ข่าวคริปโต #ตลาดคริปโต

@ 39cc53c9:27168656

Read the original blog post

“The future is there... staring back at us. Trying to make sense of the fiction we will have become.” — William Gibson.

This month is the 4th anniversary of kycnot.me. Thank you for being here.

Fifteen years ago, Satoshi Nakamoto introduced Bitcoin, a peer-to-peer electronic cash system: a decentralized currency free from government and institutional control. Nakamoto's whitepaper showed a vision for a financial system based on trustless transactions, secured by cryptography. Some time forward and KYC (Know Your Customer), AML (Anti-Money Laundering), and CTF (Counter-Terrorism Financing) regulations started to come into play.

What a paradox: to engage with a system designed for decentralization, privacy, and independence, we are forced to give away our personal details. Using Bitcoin in the economy requires revealing your identity, not just to the party you interact with, but also to third parties who must track and report the interaction. You are forced to give sensitive data to entities you don't, can't, and shouldn't trust. Information can never be kept 100% safe; there's always a risk. Information is power, who knows about you has control over you.

Information asymmetry creates imbalances of power. When entities have detailed knowledge about individuals, they can manipulate, influence, or exploit this information to their advantage. The accumulation of personal data by corporations and governments enables extensive surveillances.

Such practices, moreover, exclude individuals from traditional economic systems if their documentation doesn't meet arbitrary standards, reinforcing a dystopian divide. Small businesses are similarly burdened by the costs of implementing these regulations, hindering free market competition^1:

How will they keep this information safe? Why do they need my identity? Why do they force businesses to enforce such regulations? It's always for your safety, to protect you from the "bad". Your life is perpetually in danger: terrorists, money launderers, villains... so the government steps in to save us.

‟Hush now, baby, baby, don't you cry Mamma's gonna make all of your nightmares come true Mamma's gonna put all of her fears into you Mamma's gonna keep you right here, under her wing She won't let you fly, but she might let you sing Mamma's gonna keep baby cosy and warm” — Mother, Pink Floyd

We must resist any attack on our privacy and freedom. To do this, we must collaborate.

If you have a service, refuse to ask for KYC; find a way. Accept cryptocurrencies like Bitcoin and Monero. Commit to circular economies. Remove the need to go through the FIAT system. People need fiat money to use most services, but we can change that.

If you're a user, donate to and prefer using services that accept such currencies. Encourage your friends to accept cryptocurrencies as well. Boycott FIAT system to the greatest extent you possibly can.

This may sound utopian, but it can be achieved. This movement can't be stopped. Go kick the hornet's nest.

“We must defend our own privacy if we expect to have any. We must come together and create systems which allow anonymous transactions to take place. People have been defending their own privacy for centuries with whispers, darkness, envelopes, closed doors, secret handshakes, and couriers. The technologies of the past did not allow for strong privacy, but electronic technologies do.” — Eric Hughes, A Cypherpunk's Manifesto

The anniversary

Four years ago, I began exploring ways to use crypto without KYC. I bookmarked a few favorite services and thought sharing them to the world might be useful. That was the first version of kycnot.me — a simple list of about 15 services. Since then, I've added services, rewritten it three times, and improved it to what it is now.

kycnot.me has remained 100% independent and 100% open source^2 all these years. I've received offers to buy the site, all of which I have declined and will continue to decline. It has been DDoS attacked many times, but we made it through. I have also rewritten the whole site almost once per year (three times in four years).

The code and scoring algorithm are open source (contributions are welcome) and I can't arbitrarly change a service's score without adding or removing attributes, making any arbitrary alterations obvious if they were fake. You can even see the score summary for any service's score.

I'm a one-person team, dedicating my free time to this project. I hope to keep doing so for many more years. Again, thank you for being part of this.

@ a39d19ec:3d88f61e

A state-controlled money supply can influence the development of socialist policies and practices in various ways. Although the relationship is not deterministic, state control over the money supply can contribute to a larger role of the state in the economy and facilitate the implementation of socialist ideals.

Fiscal Policy Capabilities

When the state manages the money supply, it gains the ability to implement fiscal policies that can lead to an expansion of social programs and welfare initiatives. Funding these programs by creating money can enhance the state's influence over the economy and move it closer to a socialist model. The Soviet Union, for instance, had a centralized banking system that enabled the state to fund massive industrialization and social programs, significantly expanding the state's role in the economy.

Wealth Redistribution

Controlling the money supply can also allow the state to influence economic inequality through monetary policies, effectively redistributing wealth and reducing income disparities. By implementing low-interest loans or providing financial assistance to disadvantaged groups, the state can narrow the wealth gap and promote social equality, as seen in many European welfare states.

Central Planning

A state-controlled money supply can contribute to increased central planning, as the state gains more influence over the economy. Central banks, which are state-owned or heavily influenced by the state, play a crucial role in managing the money supply and facilitating central planning. This aligns with socialist principles that advocate for a planned economy where resources are allocated according to social needs rather than market forces.

Incentives for Staff

Staff members working in state institutions responsible for managing the money supply have various incentives to keep the system going. These incentives include job security, professional expertise and reputation, political alignment, regulatory capture, institutional inertia, and legal and administrative barriers. While these factors can differ among individuals, they can collectively contribute to the persistence of a state-controlled money supply system.

In conclusion, a state-controlled money supply can facilitate the development of socialist policies and practices by enabling fiscal policies, wealth redistribution, and central planning. The staff responsible for managing the money supply have diverse incentives to maintain the system, further ensuring its continuation. However, it is essential to note that many factors influence the trajectory of an economic system, and the relationship between state control over the money supply and socialism is not inevitable.

@ d360efec:14907b5f

@ d360efec:14907b5f

Disclaimer: * การวิเคราะห์นี้เป็นเพียงแนวทาง ไม่ใช่คำแนะนำในการซื้อขาย * การลงทุนมีความเสี่ยง ผู้ลงทุนควรตัดสินใจด้วยตนเอง

@ 39cc53c9:27168656

Read the original blog post

Silent.link is an anonymous eSIM provider. They offer pay-as-you-go roaming in 160+ countries.

Pros

• Anonymous
• Private payment options
• High performance
• Global availability

Cons

• Need to select the right networks sometimes
• Latency
• Data and incoming SMS & call only

Rating

★★★★★

Service website

Silent.link

---

eSIMs replace traditional, physical SIM cards, if you have a fairly new phone, odds are it supports them. Since most people change their mobile carrier very rarely, the most common use case for these new eSIMs is their use in travel. Although their use as a piece of a larger OPSEC puzzle to improve privacy when using the internet from your phone is increasingly popular too.

Silent.link is not the only eSIM provider out there. Yet, they’re so unique that even Twitter’s (now X) founder Jack Dorsey recommends them.

Let’s start off with a quick explanation of how Silent.link works and what pay-as-you-go means. Most other eSIM providers will sell you packages of GBs with an expiration date. For instance imagine you’re visiting France then going to the UK after a few months. With other providers you might buy a 10GB in France package valid for 7 days, then after some months a 10GB in the UK package also valid for 7 days. You likely won’t use up the full package in either country and the remaining capacity will be voided as the package expires.

Silent.link’s pay-as-you-go is different. There are no geographic packages. There are no expiration dates. You simply have a balance denominated in USD and are charged as you use up the data according to the pricing of whichever local carrier you’re connecting via.

Preparing for the same trips from the example above you’d simply top-up your Silent.link balance with $10. Then you’d use Silent.link in France paying $1.33/GB, you’d only be charged for the exact amount used, then you’d go to the UK and pay $1.54/GB from the balance you had left over from France. It doesn’t matter how much time passes between the trips, because Silent.link balances don’t expire. If you have a balance left over you can use it on a future trip, or simply use it up in your home country.

---

Pros

Anonymity

Silent.link is anonymous. Most other eSIM providers require some form of identification. This can be a traditional, full KYC, procedure involving your ID or passport numbers or, as seemingly innocent, as verifying your phone number with your main carrier. Regardless, a link between the eSIM you bought online and your identity is established.

In some countries you’ll be able to pick up a traditional SIM (or the new eSIM) from a local carrier without undergoing this verification. This can still be a hassle though. You’ll need to look up the laws before travelling, you’ll need to find a local store selling them, you’ll need to decide how you’ll pay privately, etc. And that’s the best case, that’s assuming the country you want to get the SIM in allows you to buy one anonymously.

Private payment methods

Silent.link only accepts cryptocurrency and according to their stats, most payments are made with Bitcoin (either onchain or using the Lightning Network) or with Monero. As such paying anonymously is not a problem. The use a self-hosted instance of BTCPay Server to process payments and operate their own LN node. The entire checkout process can be completed over Tor.

---

Cons

Network selection

Although you can skip the hassle of buying a new eSIM every time you travel it’s a good idea to look up the pricing of different mobile networks in the country you’re going to. The differences can be trivial, but can also be 100x. If a specific mobile network offers a much better deal, you’ll probably want to dive into your phone’s settings to make sure it only connects to that network.

High prices for some regions

Second issue can be that, especially for poorer countries, Silent.link might not have the best prices. For instance if you travel to Angola you’ll end up paying $155.44/GB. But if you search around for other providers you’ll find eSIM that offer much lower prices for that same country.

Data & incoming SMS & calls only

These eSIMs are either data-only or only offer data and inbound sms and calls. You can’t use Silent.link eSIMs to send texts or make phone calls.

Latency

For most use-cases this shouldn’t matter, but the way roaming works is that when you’re abroad your data is first sent to your home country then sent out into the internet from there. For instance if you’re a Brit on holiday in Spain wherever you open up a website your phone communicates with the Spanish network who forwards the request to your home network in the UK and only there does the request start going towards the website you’re trying to load. The response takes the same path in reverse.

The home network for the Silent.link eSIMs is Poland. To take an extreme (antipodal) example, if you’re in Chile loading a Chilean website your request will go to Poland then back from Poland to the website’s server in Chile, then the response will go from Chile to Poland to you (in Chile). All those trips add latency. In our testing, done during the recent OrangeFren.com meetup in Istanbul, the difference was an additional 73ms. The bandwidth, however, was exceptional, easily surpassing 100 Mbps.

This latency issue isn’t unique to Silent.link, other eSIM providers usually suffer from it too, though their home network may be better suited for your latency needs. If you need the best latency we recommend a SIM from a local provider (or WiFi).

This proxy behaviour isn’t all negative however. It may potentially allow you to circumvent censorship or geoblocking if you’re trying to access resources available from Poland, but unavailable elsewhere.

Besides Istanbul one of the countries we also tested Silent.link in was Northern Cyprus. This territory is mostly unrecognized. It’s a country that, depending on who you ask, is or isn’t real. Despite this unresolved geopolitical status Silent.link performed without any issues.

---

Installation

If you decide to give Silent.link a try, you'll need to select if you want a data-only plan or a plan with inbound SMS & calling, once you complete the payment simply scan the QR code on the order confirmation page with your phone. Make sure to save the url of that order confirmation page somewhere! You will need it to top up your eSIM and check your remaining balance.

Getting in touch

The preferred way of contacting Silent.link's support is using the website's built-in chat function. Alternative methods include X (formerly Twitter), Matrix and email.

Their support is online from 09:00 - 21:00 UTC although even when testing outside of those hours we got a reply within a minute.

NOTE: These reviews are sponsored, yet the sponsorship does not influence the outcome of the evaluations. Sponsored reviews are independent from the kycnot.me list, being only part of the blog. The reviews have no impact on the scores of the listings or their continued presence on the list. Should any issues arise, I will not hesitate to remove any listing.

@ d360efec:14907b5f

สวัสดีค่ะเพื่อนๆ นักเทรดที่น่ารักทุกคน! 💕 Lina Engword กลับมาพร้อมกับการวิเคราะห์ BTCUSDT.P แบบเจาะลึกเพื่อเตรียมพร้อมสำหรับเทรดวันนี้ค่ะ! 🚀

วันนี้ 12 พฤษภาคม 2568 เวลา 08.15น. ราคา BTCUSDT.P อยู่ที่ 104,642.8 USDT ค่ะ โดยมี Previous Weekly High (PWH) อยู่ที่ 104,967.8 Previous Weekly Low (PWL) ที่ 93,338 ค่ะ

✨ ภาพรวมตลาดวันนี้ ✨

จากการวิเคราะห์ด้วยเครื่องมือคู่ใจของเรา ทั้ง SMC/ICT (Demand/Supply Zone, Order Block, Liquidity), EMA 50/200, Trend Strength, Money Flow, Chart/Price Pattern, Premium/Discount Zone, Trend line, Fibonacci, Elliott Wave และ Dow Theory ใน Timeframe ตั้งแต่ 15m ไปจนถึง Week! 📊 เราพบว่าภาพใหญ่ของ BTCUSDT.P ยังคงอยู่ในแนวโน้มขาขึ้นที่แข็งแกร่งมากๆ ค่ะ 👍 โดยเฉพาะใน Timeframe Day และ Week ที่สัญญาณทุกอย่างสนับสนุนทิศทางขาขึ้นอย่างชัดเจน Money Flow ยังไหลเข้าอย่างต่อเนื่อง และเราเห็นโครงสร้างตลาดแบบ Dow Theory ที่ยก High ยก Low ขึ้นไปเรื่อยๆ ค่ะ

อย่างไรก็ตาม... ใน Timeframe สั้นๆ อย่าง 15m และ 1H เริ่มเห็นสัญญาณของการชะลอตัวและการพักฐานบ้างแล้วค่ะ 📉 อาจมีการสร้าง Buyside และ Sellside Liquidity รอให้ราคาไปกวาดก่อนที่จะเลือกทางใดทางหนึ่ง ซึ่งเป็นเรื่องปกติของการเดินทางของ Smart Money ค่ะ

⚡ เปรียบเทียบแนวโน้มแต่ละ Timeframe ⚡

🪙 แนวโน้มตรงกัน Timeframe 4H, Day, Week ส่วนใหญ่ชี้ไปทาง "ขาขึ้น" ค่ะ ทุกเครื่องมือสนับสนุนแนวโน้มนี้อย่างแข็งแกร่ง 💪 เป้าหมายต่อไปคือการไปทดสอบ PWH และ High เดิม เพื่อสร้าง All-Time High ใหม่ค่ะ! 🪙 แนวโน้มต่างกัน Timeframe 15m, 1H ยังค่อนข้าง "Sideways" หรือ "Sideways Down เล็กน้อย" ค่ะ มีการบีบตัวของราคาและอาจมีการพักฐานสั้นๆ ซึ่งเป็นโอกาสในการหาจังหวะเข้า Long ที่ราคาดีขึ้นค่ะ

💡 วิธีคิดแบบ Market Slayer 💡

เมื่อแนวโน้มใหญ่เป็นขาขึ้นที่แข็งแกร่ง เราจะเน้นหาจังหวะเข้า Long เป็นหลักค่ะ การย่อตัวลงมาในระยะสั้นคือโอกาสของเราในการเก็บของ! 🛍️ เราจะใช้หลักการ SMC/ICT หาโซน Demand หรือ Order Block ที่ Smart Money อาจจะเข้ามาดันราคาขึ้น และรอสัญญาณ Price Action ยืนยันการกลับตัวค่ะ

สรุปแนวโน้มวันนี้:

🪙 ระยะสั้น: Sideways to Sideways Down (โอกาส 55%) ↔️↘️ 🪙 ระยะกลาง: ขาขึ้น (โอกาส 70%) ↗️ 🪙 ระยะยาว: ขาขึ้น (โอกาส 85%) 🚀 🪙 วันนี้: มีโอกาสย่อตัวเล็กน้อยก่อนจะมีแรงซื้อกลับเข้ามาเพื่อไปทดสอบ PWH (โอกาส Sideways Down เล็กน้อย สลับกับ Sideways Up: 60%) 🎢

🗓️ Daily Trade Setup ประจำวันนี้ 🗓️

นี่คือตัวอย่าง Setup ที่ Lina เตรียมไว้ให้พิจารณาค่ะ (เน้นย้ำว่าเป็นเพียงแนวทาง ไม่ใช่คำแนะนำลงทุนนะคะ)

1️⃣ ตัวอย่างที่ 1: รอรับที่โซน Demand (ปลอดภัย, รอยืนยัน)

🪙 Enter: รอราคาย่อตัวลงมาในโซน Demand Zone หรือ Bullish Order Block ที่น่าสนใจใน TF 1H/4H (ดูจากกราฟประกอบนะคะ) และเกิดสัญญาณ Bullish Price Action ที่ชัดเจน เช่น แท่งเทียนกลืนกิน (Engulfing) หรือ Hammer 🪙 TP: บริเวณ PWH 104,967.8 หรือ Buyside Liquidity ถัดไป 🎯 🪙 SL: ใต้ Low ที่เกิดก่อนสัญญาณกลับตัวเล็กน้อย หรือใต้ Demand Zone ที่เข้า 🛡️ 🪙 RRR: ประมาณ 1:2.5 ขึ้นไป ✨ 🪙 อธิบาย: Setup นี้เราจะใจเย็นๆ รอให้ราคาลงมาในโซนที่มีโอกาสเจอแรงซื้อเยอะๆ ตามหลัก SMC/ICT แล้วค่อยเข้า เพื่อให้ได้ราคาที่ดีและความเสี่ยงต่ำค่ะ ต้องรอสัญญาณ Price Action ยืนยันก่อนนะคะ ✍️

2️⃣ ตัวอย่างที่ 2: Follow Breakout (สายบู๊, รับความเสี่ยงได้)

🪙 Enter: เข้า Long ทันทีเมื่อราคาสามารถ Breakout เหนือ High ล่าสุดใน TF 15m หรือ 1H พร้อม Volume ที่เพิ่มขึ้นอย่างมีนัยสำคัญ 🔥 🪙 TP: บริเวณ PWH 104,967.8 หรือ Buyside Liquidity ถัดไป 🚀 🪙 SL: ใต้ High ก่อนหน้าที่ถูก Breakout เล็กน้อย 🚧 🪙 RRR: ประมาณ 1:3 ขึ้นไป ✨ 🪙 อธิบาย: Setup นี้เหมาะกับคนที่อยากเข้าไวเมื่อเห็นโมเมนตัมแรงๆ ค่ะ เราจะเข้าเมื่อราคา Breakout แนวต้านระยะสั้นพร้อม Volume เป็นสัญญาณว่าแรงซื้อกำลังมาค่ะ เข้าได้เลยด้วยการตั้ง Limit Order หรือ Market Order เมื่อเห็นการ Breakout ที่ชัดเจนค่ะ 💨

3️⃣ ตัวอย่างที่ 3: พิจารณา Short สั้นๆ ในโซน Premium (สวนเทรนด์หลัก, ความเสี่ยงสูง)

🪙 Enter: หากราคาขึ้นไปในโซน Premium ใน TF 15m หรือ 1H และเกิดสัญญาณ Bearish Price Action ที่ชัดเจน เช่น แท่งเทียน Shooting Star หรือ Bearish Engulfing บริเวณ Supply Zone หรือ Bearish Order Block 🐻 🪙 TP: พิจารณาแนวรับถัดไป หรือ Sellside Liquidity ใน TF เดียวกัน 🎯 🪙 SL: เหนือ High ของสัญญาณ Bearish Price Action เล็กน้อย 💀 🪙 RRR: ประมาณ 1:1.5 ขึ้นไป (เน้นย้ำว่าเป็นการเทรดสวนเทรนด์หลัก ควรใช้ RRR ต่ำและบริหารขนาด Lot อย่างเข้มงวด!) 🪙 อธิบาย: Setup นี้สำหรับคนที่เห็นโอกาสในการทำกำไรจากการย่อตัวระยะสั้นค่ะ เราจะเข้า Short เมื่อเห็นสัญญาณว่าราคาอาจจะมีการพักฐานในโซนที่ถือว่า "แพง" ในกรอบสั้นๆ ค่ะ ต้องตั้ง Stop Loss ใกล้มากๆ และจับตาดูใกล้ชิดนะคะ 🚨

⚠️ Disclaimer: การวิเคราะห์นี้เป็นเพียงความคิดเห็นส่วนตัวของ Lina เท่านั้น ไม่ถือเป็นคำแนะนำในการลงทุนนะคะ การลงทุนมีความเสี่ยง ผู้ลงทุนควรศึกษาข้อมูลเพิ่มเติมและตัดสินใจด้วยความรอบคอบค่ะ 🙏

ขอให้ทุกท่านโชคดีกับการเทรดในวันนี้ค่ะ! มีคำถามอะไรเพิ่มเติม ถามมาได้เลยนะคะ ยินดีเสมอค่ะ! 😊

Bitcoin #BTCUSDT #Crypto #Trading #TechnicalAnalysis #SMC #ICT #MarketSlayer #TradeSetup #คริปโต #เทรดคริปโต #วิเคราะห์กราฟ #LinaEngword 😉

@ d61f3bc5:0da6ef4a

I remember the first gathering of Nostr devs two years ago in Costa Rica. We were all psyched because Nostr appeared to solve the problem of self-sovereign online identity and decentralized publishing. The protocol seemed well-suited for textual content, but it wasn't really designed to handle binary files, like images or video.

The Problem

When I publish a note that contains an image link, the note itself is resilient thanks to Nostr, but if the hosting service disappears or takes my image down, my note will be broken forever. We need a way to publish binary data without relying on a single hosting provider.

We were discussing how there really was no reliable solution to this problem even outside of Nostr. Peer-to-peer attempts like IPFS simply didn't work; they were hopelessly slow and unreliable in practice. Torrents worked for popular files like movies, but couldn't be relied on for general file hosting.

Awesome Blossom

A year later, I attended the Sovereign Engineering demo day in Madeira, organized by Pablo and Gigi. Many projects were presented over a three hour demo session that day, but one really stood out for me.

Introduced by hzrd149 and Stu Bowman, Blossom blew my mind because it showed how we can solve complex problems easily by simply relying on the fact that Nostr exists. Having an open user directory, with the corresponding social graph and web of trust is an incredible building block.

Since we can easily look up any user on Nostr and read their profile metadata, we can just get them to simply tell us where their files are stored. This, combined with hash-based addressing (borrowed from IPFS), is all we need to solve our problem.

How Blossom Works

The Blossom protocol (Blobs Stored Simply on Mediaservers) is formally defined in a series of BUDs (Blossom Upgrade Documents). Yes, Blossom is the most well-branded protocol in the history of protocols. Feel free to refer to the spec for details, but I will provide a high level explanation here.

The main idea behind Blossom can be summarized in three points:

1. Users specify which media server(s) they use via their public Blossom settings published on Nostr;
2. All files are uniquely addressable via hashes;
3. If an app fails to load a file from the original URL, it simply goes to get it from the server(s) specified in the user's Blossom settings.

Just like Nostr itself, the Blossom protocol is dead-simple and it works!

Let's use this image as an example:

If you look at the URL for this image, you will notice that it looks like this:

blossom.primal.net/c1aa63f983a44185d039092912bfb7f33adcf63ed3cae371ebe6905da5f688d0.jpg

All Blossom URLs follow this format:

[server]/[file-hash].[extension]

The file hash is important because it uniquely identifies the file in question. Apps can use it to verify that the file they received is exactly the file they requested. It also gives us the ability to reliably get the same file from a different server.

Nostr users declare which media server(s) they use by publishing their Blossom settings. If I store my files on Server A, and they get removed, I can simply upload them to Server B, update my public Blossom settings, and all Blossom-capable apps will be able to find them at the new location. All my existing notes will continue to display media content without any issues.

Blossom Mirroring

Let's face it, re-uploading files to another server after they got removed from the original server is not the best user experience. Most people wouldn't have the backups of all the files, and/or the desire to do this work.

This is where Blossom's mirroring feature comes handy. In addition to the primary media server, a Blossom user can set one one or more mirror servers. Under this setup, every time a file is uploaded to the primary server the Nostr app issues a mirror request to the primary server, directing it to copy the file to all the specified mirrors. This way there is always a copy of all content on multiple servers and in case the primary becomes unavailable, Blossom-capable apps will automatically start loading from the mirror.

Mirrors are really easy to setup (you can do it in two clicks in Primal) and this arrangement ensures robust media handling without any central points of failure. Note that you can use professional media hosting services side by side with self-hosted backup servers that anyone can run at home.

Using Blossom Within Primal

Blossom is natively integrated into the entire Primal stack and enabled by default. If you are using Primal 2.2 or later, you don't need to do anything to enable Blossom, all your media uploads are blossoming already.

To enhance user privacy, all Primal apps use the "/media" endpoint per BUD-05, which strips all metadata from uploaded files before they are saved and optionally mirrored to other Blossom servers, per user settings. You can use any Blossom server as your primary media server in Primal, as well as setup any number of mirrors:

## Conclusion

For such a simple protocol, Blossom gives us three major benefits:

1. Verifiable authenticity. All Nostr notes are always signed by the note author. With Blossom, the signed note includes a unique hash for each referenced media file, making it impossible to falsify.
2. File hosting redundancy. Having multiple live copies of referenced media files (via Blossom mirroring) greatly increases the resiliency of media content published on Nostr.
3. Censorship resistance. Blossom enables us to seamlessly switch media hosting providers in case of censorship.

Thanks for reading; and enjoy! 🌸

@ a39d19ec:3d88f61e

This week's functional 3d print is the "Dino Clip".

Dino Clip

I printed it some years ago for my son, so he would have his own clip for cereal bags.

Now it is used to hold a bag of dog food close.

The design by "Sneaks" is a so called "print in place". This means that the whole clip with moving parts is printed in one part, without the need for assembly after the print. The clip is very strong, and I would print it again if I need a "heavy duty" clip for more rigid or big bags. Link to the file at Printables

@ a367f9eb:0633efea

Last week, an investigation by Reuters revealed that Chinese researchers have been using open-source AI tools to build nefarious-sounding models that may have some military application.

The reporting purports that adversaries in the Chinese Communist Party and its military wing are taking advantage of the liberal software licensing of American innovations in the AI space, which could someday have capabilities to presumably harm the United States.

In a June paper reviewed by Reuters, six Chinese researchers from three institutions, including two under the People’s Liberation Army’s (PLA) leading research body, the Academy of Military Science (AMS), detailed how they had used an early version of Meta’s Llama as a base for what it calls “ChatBIT”.

The researchers used an earlier Llama 13B large language model (LLM) from Meta, incorporating their own parameters to construct a military-focused AI tool to gather and process intelligence, and offer accurate and reliable information for operational decision-making.

While I’m doubtful that today’s existing chatbot-like tools will be the ultimate battlefield for a new geopolitical war (queue up the computer-simulated war from the Star Trek episode “A Taste of Armageddon“), this recent exposé requires us to revisit why large language models are released as open-source code in the first place.

Added to that, should it matter that an adversary is having a poke around and may ultimately use them for some purpose we may not like, whether that be China, Russia, North Korea, or Iran?

The number of open-source AI LLMs continues to grow each day, with projects like Vicuna, LLaMA, BLOOMB, Falcon, and Mistral available for download. In fact, there are over one million open-source LLMs available as of writing this post. With some decent hardware, every global citizen can download these codebases and run them on their computer.

With regard to this specific story, we could assume it to be a selective leak by a competitor of Meta which created the LLaMA model, intended to harm its reputation among those with cybersecurity and national security credentials. There are potentially trillions of dollars on the line.

Or it could be the revelation of something more sinister happening in the military-sponsored labs of Chinese hackers who have already been caught attacking American infrastructure, data, and yes, your credit history?

As consumer advocates who believe in the necessity of liberal democracies to safeguard our liberties against authoritarianism, we should absolutely remain skeptical when it comes to the communist regime in Beijing. We’ve written as much many times.

At the same time, however, we should not subrogate our own critical thinking and principles because it suits a convenient narrative.

Consumers of all stripes deserve technological freedom, and innovators should be free to provide that to us. And open-source software has provided the very foundations for all of this.

Open-source matters When we discuss open-source software and code, what we’re really talking about is the ability for people other than the creators to use it.

The various licensing schemes – ranging from GNU General Public License (GPL) to the MIT License and various public domain classifications – determine whether other people can use the code, edit it to their liking, and run it on their machine. Some licenses even allow you to monetize the modifications you’ve made.

While many different types of software will be fully licensed and made proprietary, restricting or even penalizing those who attempt to use it on their own, many developers have created software intended to be released to the public. This allows multiple contributors to add to the codebase and to make changes to improve it for public benefit.

Open-source software matters because anyone, anywhere can download and run the code on their own. They can also modify it, edit it, and tailor it to their specific need. The code is intended to be shared and built upon not because of some altruistic belief, but rather to make it accessible for everyone and create a broad base. This is how we create standards for technologies that provide the ground floor for further tinkering to deliver value to consumers.

Open-source libraries create the building blocks that decrease the hassle and cost of building a new web platform, smartphone, or even a computer language. They distribute common code that can be built upon, assuring interoperability and setting standards for all of our devices and technologies to talk to each other.

I am myself a proponent of open-source software. The server I run in my home has dozens of dockerized applications sourced directly from open-source contributors on GitHub and DockerHub. When there are versions or adaptations that I don’t like, I can pick and choose which I prefer. I can even make comments or add edits if I’ve found a better way for them to run.

Whether you know it or not, many of you run the Linux operating system as the base for your Macbook or any other computer and use all kinds of web tools that have active repositories forked or modified by open-source contributors online. This code is auditable by everyone and can be scrutinized or reviewed by whoever wants to (even AI bots).

This is the same software that runs your airlines, powers the farms that deliver your food, and supports the entire global monetary system. The code of the first decentralized cryptocurrency Bitcoin is also open-source, which has allowed thousands of copycat protocols that have revolutionized how we view money.

You know what else is open-source and available for everyone to use, modify, and build upon?

PHP, Mozilla Firefox, LibreOffice, MySQL, Python, Git, Docker, and WordPress. All protocols and languages that power the web. Friend or foe alike, anyone can download these pieces of software and run them how they see fit.

Open-source code is speech, and it is knowledge.

We build upon it to make information and technology accessible. Attempts to curb open-source, therefore, amount to restricting speech and knowledge.

Open-source is for your friends, and enemies In the context of Artificial Intelligence, many different developers and companies have chosen to take their large language models and make them available via an open-source license.

At this very moment, you can click on over to Hugging Face, download an AI model, and build a chatbot or scripting machine suited to your needs. All for free (as long as you have the power and bandwidth).

Thousands of companies in the AI sector are doing this at this very moment, discovering ways of building on top of open-source models to develop new apps, tools, and services to offer to companies and individuals. It’s how many different applications are coming to life and thousands more jobs are being created.

We know this can be useful to friends, but what about enemies?

As the AI wars heat up between liberal democracies like the US, the UK, and (sluggishly) the European Union, we know that authoritarian adversaries like the CCP and Russia are building their own applications.

The fear that China will use open-source US models to create some kind of military application is a clear and present danger for many political and national security researchers, as well as politicians.

A bipartisan group of US House lawmakers want to put export controls on AI models, as well as block foreign access to US cloud servers that may be hosting AI software.

If this seems familiar, we should also remember that the US government once classified cryptography and encryption as “munitions” that could not be exported to other countries (see The Crypto Wars). Many of the arguments we hear today were invoked by some of the same people as back then.

Now, encryption protocols are the gold standard for many different banking and web services, messaging, and all kinds of electronic communication. We expect our friends to use it, and our foes as well. Because code is knowledge and speech, we know how to evaluate it and respond if we need to.

Regardless of who uses open-source AI, this is how we should view it today. These are merely tools that people will use for good or ill. It’s up to governments to determine how best to stop illiberal or nefarious uses that harm us, rather than try to outlaw or restrict building of free and open software in the first place.

Limiting open-source threatens our own advancement If we set out to restrict and limit our ability to create and share open-source code, no matter who uses it, that would be tantamount to imposing censorship. There must be another way.

If there is a “Hundred Year Marathon” between the United States and liberal democracies on one side and autocracies like the Chinese Communist Party on the other, this is not something that will be won or lost based on software licenses. We need as much competition as possible.

The Chinese military has been building up its capabilities with trillions of dollars’ worth of investments that span far beyond AI chatbots and skip logic protocols.

The theft of intellectual property at factories in Shenzhen, or in US courts by third-party litigation funding coming from China, is very real and will have serious economic consequences. It may even change the balance of power if our economies and countries turn to war footing.

But these are separate issues from the ability of free people to create and share open-source code which we can all benefit from. In fact, if we want to continue our way our life and continue to add to global productivity and growth, it’s demanded that we defend open-source.

If liberal democracies want to compete with our global adversaries, it will not be done by reducing the freedoms of citizens in our own countries.

Last week, an investigation by Reuters revealed that Chinese researchers have been using open-source AI tools to build nefarious-sounding models that may have some military application.

The reporting purports that adversaries in the Chinese Communist Party and its military wing are taking advantage of the liberal software licensing of American innovations in the AI space, which could someday have capabilities to presumably harm the United States.

In a June paper reviewed by Reuters, six Chinese researchers from three institutions, including two under the People’s Liberation Army’s (PLA) leading research body, the Academy of Military Science (AMS), detailed how they had used an early version of Meta’s Llama as a base for what it calls “ChatBIT”.

The researchers used an earlier Llama 13B large language model (LLM) from Meta, incorporating their own parameters to construct a military-focused AI tool to gather and process intelligence, and offer accurate and reliable information for operational decision-making.

While I’m doubtful that today’s existing chatbot-like tools will be the ultimate battlefield for a new geopolitical war (queue up the computer-simulated war from the Star Trek episode “A Taste of Armageddon“), this recent exposé requires us to revisit why large language models are released as open-source code in the first place.

Added to that, should it matter that an adversary is having a poke around and may ultimately use them for some purpose we may not like, whether that be China, Russia, North Korea, or Iran?

The number of open-source AI LLMs continues to grow each day, with projects like Vicuna, LLaMA, BLOOMB, Falcon, and Mistral available for download. In fact, there are over one million open-source LLMs available as of writing this post. With some decent hardware, every global citizen can download these codebases and run them on their computer.

With regard to this specific story, we could assume it to be a selective leak by a competitor of Meta which created the LLaMA model, intended to harm its reputation among those with cybersecurity and national security credentials. There are potentially trillions of dollars on the line.

Or it could be the revelation of something more sinister happening in the military-sponsored labs of Chinese hackers who have already been caught attacking American infrastructure, data, and yes, your credit history?

As consumer advocates who believe in the necessity of liberal democracies to safeguard our liberties against authoritarianism, we should absolutely remain skeptical when it comes to the communist regime in Beijing. We’ve written as much many times.

At the same time, however, we should not subrogate our own critical thinking and principles because it suits a convenient narrative.

Consumers of all stripes deserve technological freedom, and innovators should be free to provide that to us. And open-source software has provided the very foundations for all of this.

Open-source matters

When we discuss open-source software and code, what we’re really talking about is the ability for people other than the creators to use it.

The various licensing schemes – ranging from GNU General Public License (GPL) to the MIT License and various public domain classifications – determine whether other people can use the code, edit it to their liking, and run it on their machine. Some licenses even allow you to monetize the modifications you’ve made.

While many different types of software will be fully licensed and made proprietary, restricting or even penalizing those who attempt to use it on their own, many developers have created software intended to be released to the public. This allows multiple contributors to add to the codebase and to make changes to improve it for public benefit.

Open-source software matters because anyone, anywhere can download and run the code on their own. They can also modify it, edit it, and tailor it to their specific need. The code is intended to be shared and built upon not because of some altruistic belief, but rather to make it accessible for everyone and create a broad base. This is how we create standards for technologies that provide the ground floor for further tinkering to deliver value to consumers.

Open-source libraries create the building blocks that decrease the hassle and cost of building a new web platform, smartphone, or even a computer language. They distribute common code that can be built upon, assuring interoperability and setting standards for all of our devices and technologies to talk to each other.

I am myself a proponent of open-source software. The server I run in my home has dozens of dockerized applications sourced directly from open-source contributors on GitHub and DockerHub. When there are versions or adaptations that I don’t like, I can pick and choose which I prefer. I can even make comments or add edits if I’ve found a better way for them to run.

Whether you know it or not, many of you run the Linux operating system as the base for your Macbook or any other computer and use all kinds of web tools that have active repositories forked or modified by open-source contributors online. This code is auditable by everyone and can be scrutinized or reviewed by whoever wants to (even AI bots).

This is the same software that runs your airlines, powers the farms that deliver your food, and supports the entire global monetary system. The code of the first decentralized cryptocurrency Bitcoin is also open-source, which has allowed thousands of copycat protocols that have revolutionized how we view money.

You know what else is open-source and available for everyone to use, modify, and build upon?

PHP, Mozilla Firefox, LibreOffice, MySQL, Python, Git, Docker, and WordPress. All protocols and languages that power the web. Friend or foe alike, anyone can download these pieces of software and run them how they see fit.

Open-source code is speech, and it is knowledge.

We build upon it to make information and technology accessible. Attempts to curb open-source, therefore, amount to restricting speech and knowledge.

Open-source is for your friends, and enemies

In the context of Artificial Intelligence, many different developers and companies have chosen to take their large language models and make them available via an open-source license.

At this very moment, you can click on over to Hugging Face, download an AI model, and build a chatbot or scripting machine suited to your needs. All for free (as long as you have the power and bandwidth).

Thousands of companies in the AI sector are doing this at this very moment, discovering ways of building on top of open-source models to develop new apps, tools, and services to offer to companies and individuals. It’s how many different applications are coming to life and thousands more jobs are being created.

We know this can be useful to friends, but what about enemies?

As the AI wars heat up between liberal democracies like the US, the UK, and (sluggishly) the European Union, we know that authoritarian adversaries like the CCP and Russia are building their own applications.

The fear that China will use open-source US models to create some kind of military application is a clear and present danger for many political and national security researchers, as well as politicians.

A bipartisan group of US House lawmakers want to put export controls on AI models, as well as block foreign access to US cloud servers that may be hosting AI software.

If this seems familiar, we should also remember that the US government once classified cryptography and encryption as “munitions” that could not be exported to other countries (see The Crypto Wars). Many of the arguments we hear today were invoked by some of the same people as back then.

Now, encryption protocols are the gold standard for many different banking and web services, messaging, and all kinds of electronic communication. We expect our friends to use it, and our foes as well. Because code is knowledge and speech, we know how to evaluate it and respond if we need to.

Regardless of who uses open-source AI, this is how we should view it today. These are merely tools that people will use for good or ill. It’s up to governments to determine how best to stop illiberal or nefarious uses that harm us, rather than try to outlaw or restrict building of free and open software in the first place.

Limiting open-source threatens our own advancement

If we set out to restrict and limit our ability to create and share open-source code, no matter who uses it, that would be tantamount to imposing censorship. There must be another way.

If there is a “Hundred Year Marathon” between the United States and liberal democracies on one side and autocracies like the Chinese Communist Party on the other, this is not something that will be won or lost based on software licenses. We need as much competition as possible.

The Chinese military has been building up its capabilities with trillions of dollars’ worth of investments that span far beyond AI chatbots and skip logic protocols.

The theft of intellectual property at factories in Shenzhen, or in US courts by third-party litigation funding coming from China, is very real and will have serious economic consequences. It may even change the balance of power if our economies and countries turn to war footing.

But these are separate issues from the ability of free people to create and share open-source code which we can all benefit from. In fact, if we want to continue our way our life and continue to add to global productivity and growth, it’s demanded that we defend open-source.

If liberal democracies want to compete with our global adversaries, it will not be done by reducing the freedoms of citizens in our own countries.

Originally published on the website of the Consumer Choice Center.

@ c1e9ab3a:9cb56b43

I. Historical Foundations of U.S. Monetary Architecture

The early monetary system of the United States was built atop inherited commodity money conventions from Europe’s maritime economies. Silver and gold coins—primarily Spanish pieces of eight, Dutch guilders, and other foreign specie—formed the basis of colonial commerce. These units were already integrated into international trade and piracy networks and functioned with natural compatibility across England, France, Spain, and Denmark. Lacking a centralized mint or formal currency, the U.S. adopted these forms de facto.

As security risks and the practical constraints of physical coinage mounted, banks emerged to warehouse specie and issue redeemable certificates. These certificates evolved into fiduciary media—claims on specie not actually in hand. Banks observed over time that substantial portions of reserves remained unclaimed for years. This enabled fractional reserve banking: issuing more claims than reserves held, so long as redemption demand stayed low. The practice was inherently unstable, prone to panics and bank runs, prompting eventual centralization through the formation of the Federal Reserve in 1913.

Following the Civil War and unstable reinstatements of gold convertibility, the U.S. sought global monetary stability. After World War II, the Bretton Woods system formalized the U.S. dollar as the global reserve currency. The dollar was nominally backed by gold, but most international dollars were held offshore and recycled into U.S. Treasuries. The Nixon Shock of 1971 eliminated the gold peg, converting the dollar into pure fiat. Yet offshore dollar demand remained, sustained by oil trade mandates and the unique role of Treasuries as global reserve assets.

II. The Structure of Fiduciary Media and Treasury Demand

Under this system, foreign trade surpluses with the U.S. generate excess dollars. These surplus dollars are parked in U.S. Treasuries, thereby recycling trade imbalances into U.S. fiscal liquidity. While technically loans to the U.S. government, these purchases act like interest-only transfers—governments receive yield, and the U.S. receives spendable liquidity without principal repayment due in the short term. Debt is perpetually rolled over, rarely extinguished.

This creates an illusion of global subsidy: U.S. deficits are financed via foreign capital inflows that, in practice, function more like financial tribute systems than conventional debt markets. The underlying asset—U.S. Treasury debt—functions as the base reserve asset of the dollar system, replacing gold in post-Bretton Woods monetary logic.

III. Emergence of Tether and the Parastatal Dollar

Tether (USDT), as a private issuer of dollar-denominated tokens, mimics key central bank behaviors while operating outside the regulatory perimeter. It mints tokens allegedly backed 1:1 by U.S. dollars or dollar-denominated securities (mostly Treasuries). These tokens circulate globally, often in jurisdictions with limited banking access, and increasingly serve as synthetic dollar substitutes.

If USDT gains dominance as the preferred medium of exchange—due to technological advantages, speed, programmability, or access—it displaces Federal Reserve Notes (FRNs) not through devaluation, but through functional obsolescence. Gresham’s Law inverts: good money (more liquid, programmable, globally transferable USDT) displaces bad (FRNs) even if both maintain a nominal 1:1 parity.

Over time, this preference translates to a systemic demand shift. Actors increasingly use Tether instead of FRNs, especially in global commerce, digital marketplaces, or decentralized finance. Tether tokens effectively become shadow base money.

IV. Interaction with Commercial Banking and Redemption Mechanics

Under traditional fractional reserve systems, commercial banks issue loans denominated in U.S. dollars, expanding the money supply. When borrowers repay loans, this destroys the created dollars and contracts monetary elasticity. If borrowers repay in USDT instead of FRNs:

• Banks receive a non-Fed liability (USDT).
• USDT is not recognized as reserve-eligible within the Federal Reserve System.
• Banks must either redeem USDT for FRNs, or demand par-value conversion from Tether to settle reserve requirements and balance their books.

This places redemption pressure on Tether and threatens its 1:1 peg under stress. If redemption latency, friction, or cost arises, USDT’s equivalence to FRNs is compromised. Conversely, if banks are permitted or compelled to hold USDT as reserve or regulatory capital, Tether becomes a de facto reserve issuer.

In this scenario, banks may begin demanding loans in USDT, mirroring borrower behavior. For this to occur sustainably, banks must secure Tether liquidity. This creates two options: - Purchase USDT from Tether or on the secondary market, collateralized by existing fiat. - Borrow USDT directly from Tether, using bank-issued debt as collateral.

The latter mirrors Federal Reserve discount window operations. Tether becomes a lender of first resort, providing monetary elasticity to the banking system by creating new tokens against promissory assets—exactly how central banks function.

V. Structural Consequences: Parallel Central Banking

If Tether begins lending to commercial banks, issuing tokens backed by bank notes or collateralized debt obligations: - Tether controls the expansion of broad money through credit issuance. - Its balance sheet mimics a central bank, with Treasuries and bank debt as assets and tokens as liabilities. - It intermediates between sovereign debt and global liquidity demand, replacing the Federal Reserve’s open market operations with its own issuance-redemption cycles.

Simultaneously, if Tether purchases U.S. Treasuries with FRNs received through token issuance, it: - Supplies the Treasury with new liquidity (via bond purchases). - Collects yield on government debt. - Issues a parallel form of U.S. dollars that never require redemption—an interest-only loan to the U.S. government from a non-sovereign entity.

In this context, Tether performs monetary functions of both a central bank and a sovereign wealth fund, without political accountability or regulatory transparency.

VI. Endgame: Institutional Inversion and Fed Redundancy

This paradigm represents an institutional inversion:

• The Federal Reserve becomes a legacy issuer.
• Tether becomes the operational base money provider in both retail and interbank contexts.
• Treasuries remain the foundational reserve asset, but access to them is mediated by a private intermediary.
• The dollar persists, but its issuer changes. The State becomes a fiscal agent of a decentralized financial ecosystem, not its monetary sovereign.

Unless the Federal Reserve reasserts control—either by absorbing Tether, outlawing its instruments, or integrating its tokens into the reserve framework—it risks becoming irrelevant in the daily function of money.

Tether, in this configuration, is no longer a derivative of the dollar—it is the dollar, just one level removed from sovereign control. The future of monetary sovereignty under such a regime is post-national and platform-mediated.

@ 4ba8e86d:89d32de4

Tutorial feito por nostr:nostr:npub1rc56x0ek0dd303eph523g3chm0wmrs5wdk6vs0ehd0m5fn8t7y4sqra3tk poste original abaixo:

Parte 1 : http://xh6liiypqffzwnu5734ucwps37tn2g6npthvugz3gdoqpikujju525yd.onion/263585/tutorial-debloat-de-celulares-android-via-adb-parte-1

Parte 2 : http://xh6liiypqffzwnu5734ucwps37tn2g6npthvugz3gdoqpikujju525yd.onion/index.php/263586/tutorial-debloat-de-celulares-android-via-adb-parte-2

Quando o assunto é privacidade em celulares, uma das medidas comumente mencionadas é a remoção de bloatwares do dispositivo, também chamado de debloat. O meio mais eficiente para isso sem dúvidas é a troca de sistema operacional. Custom Rom’s como LineageOS, GrapheneOS, Iodé, CalyxOS, etc, já são bastante enxutos nesse quesito, principalmente quanto não é instalado os G-Apps com o sistema. No entanto, essa prática pode acabar resultando em problemas indesejados como a perca de funções do dispositivo, e até mesmo incompatibilidade com apps bancários, tornando este método mais atrativo para quem possui mais de um dispositivo e separando um apenas para privacidade.   Pensando nisso, pessoas que possuem apenas um único dispositivo móvel, que são necessitadas desses apps ou funções, mas, ao mesmo tempo, tem essa visão em prol da privacidade, buscam por um meio-termo entre manter a Stock rom, e não ter seus dados coletados por esses bloatwares. Felizmente, a remoção de bloatwares é possível e pode ser realizada via root, ou mais da maneira que este artigo irá tratar, via adb.

O que são bloatwares?

Bloatware é a junção das palavras bloat (inchar) + software (programa), ou seja, um bloatware é basicamente um programa inútil ou facilmente substituível — colocado em seu dispositivo previamente pela fabricante e operadora — que está no seu dispositivo apenas ocupando espaço de armazenamento, consumindo memória RAM e pior, coletando seus dados e enviando para servidores externos, além de serem mais pontos de vulnerabilidades.

O que é o adb?

O Android Debug Brigde, ou apenas adb, é uma ferramenta que se utiliza das permissões de usuário shell e permite o envio de comandos vindo de um computador para um dispositivo Android exigindo apenas que a depuração USB esteja ativa, mas também pode ser usada diretamente no celular a partir do Android 11, com o uso do Termux e a depuração sem fio (ou depuração wifi). A ferramenta funciona normalmente em dispositivos sem root, e também funciona caso o celular esteja em Recovery Mode.

Requisitos:

Para computadores:

• Depuração USB ativa no celular; • Computador com adb; • Cabo USB;

Para celulares:

• Depuração sem fio (ou depuração wifi) ativa no celular; • Termux; • Android 11 ou superior;

Para ambos:

• Firewall NetGuard instalado e configurado no celular; • Lista de bloatwares para seu dispositivo;

Ativação de depuração:

Para ativar a Depuração USB em seu dispositivo, pesquise como ativar as opções de desenvolvedor de seu dispositivo, e lá ative a depuração. No caso da depuração sem fio, sua ativação irá ser necessária apenas no momento que for conectar o dispositivo ao Termux.

Instalação e configuração do NetGuard

O NetGuard pode ser instalado através da própria Google Play Store, mas de preferência instale pela F-Droid ou Github para evitar telemetria.

F-Droid: https://f-droid.org/packages/eu.faircode.netguard/

Github: https://github.com/M66B/NetGuard/releases

Após instalado, configure da seguinte maneira:

Configurações → padrões (lista branca/negra) → ative as 3 primeiras opções (bloquear wifi, bloquear dados móveis e aplicar regras ‘quando tela estiver ligada’);

Configurações → opções avançadas → ative as duas primeiras (administrar aplicativos do sistema e registrar acesso a internet);

Com isso, todos os apps estarão sendo bloqueados de acessar a internet, seja por wifi ou dados móveis, e na página principal do app basta permitir o acesso a rede para os apps que você vai usar (se necessário). Permita que o app rode em segundo plano sem restrição da otimização de bateria, assim quando o celular ligar, ele já estará ativo.

Lista de bloatwares

Nem todos os bloatwares são genéricos, haverá bloatwares diferentes conforme a marca, modelo, versão do Android, e até mesmo região.

Para obter uma lista de bloatwares de seu dispositivo, caso seu aparelho já possua um tempo de existência, você encontrará listas prontas facilmente apenas pesquisando por elas. Supondo que temos um Samsung Galaxy Note 10 Plus em mãos, basta pesquisar em seu motor de busca por:

Samsung Galaxy Note 10 Plus bloatware list

Provavelmente essas listas já terão inclusas todos os bloatwares das mais diversas regiões, lhe poupando o trabalho de buscar por alguma lista mais específica.

Caso seu aparelho seja muito recente, e/ou não encontre uma lista pronta de bloatwares, devo dizer que você acaba de pegar em merda, pois é chato para um caralho pesquisar por cada aplicação para saber sua função, se é essencial para o sistema ou se é facilmente substituível.

De antemão já aviso, que mais para frente, caso vossa gostosura remova um desses aplicativos que era essencial para o sistema sem saber, vai acabar resultando na perda de alguma função importante, ou pior, ao reiniciar o aparelho o sistema pode estar quebrado, lhe obrigando a seguir com uma formatação, e repetir todo o processo novamente.

Download do adb em computadores

Para usar a ferramenta do adb em computadores, basta baixar o pacote chamado SDK platform-tools, disponível através deste link: https://developer.android.com/tools/releases/platform-tools. Por ele, você consegue o download para Windows, Mac e Linux.

Uma vez baixado, basta extrair o arquivo zipado, contendo dentro dele uma pasta chamada platform-tools que basta ser aberta no terminal para se usar o adb.

Download do adb em celulares com Termux.

Para usar a ferramenta do adb diretamente no celular, antes temos que baixar o app Termux, que é um emulador de terminal linux, e já possui o adb em seu repositório. Você encontra o app na Google Play Store, mas novamente recomendo baixar pela F-Droid ou diretamente no Github do projeto.

F-Droid: https://f-droid.org/en/packages/com.termux/

Github: https://github.com/termux/termux-app/releases

Processo de debloat

Antes de iniciarmos, é importante deixar claro que não é para você sair removendo todos os bloatwares de cara sem mais nem menos, afinal alguns deles precisam antes ser substituídos, podem ser essenciais para você para alguma atividade ou função, ou até mesmo são insubstituíveis.

Alguns exemplos de bloatwares que a substituição é necessária antes da remoção, é o Launcher, afinal, é a interface gráfica do sistema, e o teclado, que sem ele só é possível digitar com teclado externo. O Launcher e teclado podem ser substituídos por quaisquer outros, minha recomendação pessoal é por aqueles que respeitam sua privacidade, como Pie Launcher e Simple Laucher, enquanto o teclado pelo OpenBoard e FlorisBoard, todos open-source e disponíveis da F-Droid.

Identifique entre a lista de bloatwares, quais você gosta, precisa ou prefere não substituir, de maneira alguma você é obrigado a remover todos os bloatwares possíveis, modifique seu sistema a seu bel-prazer. O NetGuard lista todos os apps do celular com o nome do pacote, com isso você pode filtrar bem qual deles não remover.

Um exemplo claro de bloatware insubstituível e, portanto, não pode ser removido, é o com.android.mtp, um protocolo onde sua função é auxiliar a comunicação do dispositivo com um computador via USB, mas por algum motivo, tem acesso a rede e se comunica frequentemente com servidores externos. Para esses casos, e melhor solução mesmo é bloquear o acesso a rede desses bloatwares com o NetGuard.

MTP tentando comunicação com servidores externos:

Executando o adb shell

No computador

Faça backup de todos os seus arquivos importantes para algum armazenamento externo, e formate seu celular com o hard reset. Após a formatação, e a ativação da depuração USB, conecte seu aparelho e o pc com o auxílio de um cabo USB. Muito provavelmente seu dispositivo irá apenas começar a carregar, por isso permita a transferência de dados, para que o computador consiga se comunicar normalmente com o celular.

Já no pc, abra a pasta platform-tools dentro do terminal, e execute o seguinte comando:

./adb start-server

O resultado deve ser:

daemon not running; starting now at tcp:5037 daemon started successfully

E caso não apareça nada, execute:

./adb kill-server

E inicie novamente.

Com o adb conectado ao celular, execute:

./adb shell

Para poder executar comandos diretamente para o dispositivo. No meu caso, meu celular é um Redmi Note 8 Pro, codinome Begonia.

Logo o resultado deve ser:

begonia:/ $

Caso ocorra algum erro do tipo:

adb: device unauthorized. This adb server’s $ADB_VENDOR_KEYS is not set Try ‘adb kill-server’ if that seems wrong. Otherwise check for a confirmation dialog on your device.

Verifique no celular se apareceu alguma confirmação para autorizar a depuração USB, caso sim, autorize e tente novamente. Caso não apareça nada, execute o kill-server e repita o processo.

No celular

Após realizar o mesmo processo de backup e hard reset citado anteriormente, instale o Termux e, com ele iniciado, execute o comando:

pkg install android-tools

Quando surgir a mensagem “Do you want to continue? [Y/n]”, basta dar enter novamente que já aceita e finaliza a instalação

Agora, vá até as opções de desenvolvedor, e ative a depuração sem fio. Dentro das opções da depuração sem fio, terá uma opção de emparelhamento do dispositivo com um código, que irá informar para você um código em emparelhamento, com um endereço IP e porta, que será usado para a conexão com o Termux.

Para facilitar o processo, recomendo que abra tanto as configurações quanto o Termux ao mesmo tempo, e divida a tela com os dois app’s, como da maneira a seguir:

Para parear o Termux com o dispositivo, não é necessário digitar o ip informado, basta trocar por “localhost”, já a porta e o código de emparelhamento, deve ser digitado exatamente como informado. Execute:

adb pair localhost:porta CódigoDeEmparelhamento

De acordo com a imagem mostrada anteriormente, o comando ficaria “adb pair localhost:41255 757495”.

Com o dispositivo emparelhado com o Termux, agora basta conectar para conseguir executar os comandos, para isso execute:

adb connect localhost:porta

Obs: a porta que você deve informar neste comando não é a mesma informada com o código de emparelhamento, e sim a informada na tela principal da depuração sem fio.

Pronto! Termux e adb conectado com sucesso ao dispositivo, agora basta executar normalmente o adb shell:

adb shell

Remoção na prática Com o adb shell executado, você está pronto para remover os bloatwares. No meu caso, irei mostrar apenas a remoção de um app (Google Maps), já que o comando é o mesmo para qualquer outro, mudando apenas o nome do pacote.

Dentro do NetGuard, verificando as informações do Google Maps:

Podemos ver que mesmo fora de uso, e com a localização do dispositivo desativado, o app está tentando loucamente se comunicar com servidores externos, e informar sabe-se lá que peste. Mas sem novidades até aqui, o mais importante é que podemos ver que o nome do pacote do Google Maps é com.google.android.apps.maps, e para o remover do celular, basta executar:

pm uninstall –user 0 com.google.android.apps.maps

E pronto, bloatware removido! Agora basta repetir o processo para o resto dos bloatwares, trocando apenas o nome do pacote.

Para acelerar o processo, você pode já criar uma lista do bloco de notas com os comandos, e quando colar no terminal, irá executar um atrás do outro.

Exemplo de lista:

Caso a donzela tenha removido alguma coisa sem querer, também é possível recuperar o pacote com o comando:

cmd package install-existing nome.do.pacote

Pós-debloat

Após limpar o máximo possível o seu sistema, reinicie o aparelho, caso entre no como recovery e não seja possível dar reboot, significa que você removeu algum app “essencial” para o sistema, e terá que formatar o aparelho e repetir toda a remoção novamente, desta vez removendo poucos bloatwares de uma vez, e reiniciando o aparelho até descobrir qual deles não pode ser removido. Sim, dá trabalho… quem mandou querer privacidade?

Caso o aparelho reinicie normalmente após a remoção, parabéns, agora basta usar seu celular como bem entender! Mantenha o NetGuard sempre executando e os bloatwares que não foram possíveis remover não irão se comunicar com servidores externos, passe a usar apps open source da F-Droid e instale outros apps através da Aurora Store ao invés da Google Play Store.

Referências: Caso você seja um Australopithecus e tenha achado este guia difícil, eis uma videoaula (3:14:40) do Anderson do canal Ciberdef, realizando todo o processo: http://odysee.com/@zai:5/Como-remover-at%C3%A9-200-APLICATIVOS-que-colocam-a-sua-PRIVACIDADE-E-SEGURAN%C3%87A-em-risco.:4?lid=6d50f40314eee7e2f218536d9e5d300290931d23

Pdf’s do Anderson citados na videoaula: créditos ao anon6837264 http://eternalcbrzpicytj4zyguygpmkjlkddxob7tptlr25cdipe5svyqoqd.onion/file/3863a834d29285d397b73a4af6fb1bbe67c888d72d30/t-05e63192d02ffd.pdf

Processo de instalação do Termux e adb no celular: https://youtu.be/APolZrPHSms

@ 39cc53c9:27168656

Read the original blog post

After almost 3 months of work, we've completed the redesign of kycnot.me. More modern and with many new features.

Privacy remains the foundation - everything still works with JavaScript disabled. If you enable JS, you will get some nice-to-have features like lazy loading and smoother page transitions, but nothing essential requires it.

User Accounts

We've introduced user accounts that require zero personal information:

• Secret user tokens - no email, no phone number, no personal data
• Randomly generated usernames for default privacy and fairness
• Karma system that rewards contributions and unlocks features: custom display names, profile pictures, and more.

Reviews and Community Discussions

On the previous sites, I was using third party open source tools for the comments and discussions. This time, I've built my own from scratch, fully integrated into the site, without JavaScript requirements.

Everyone can share their experiences and help others make informed decisions:

• Ratings: Comments can have a 1-5 star rating attached. You can have one rating per service and it will affect the overall user score.
• Discussions: These are normal comments, you can add them on any listed service.

Comment Moderation

I was strugling to keep up with moderation on the old site. For this, we've implemented an AI-powered moderation system that:

• Auto-approves legitimate comments instantly
• Flags suspicious content for human review
• Keeps discussions valuable by minimizing spam

The AI still can mark comments for human review, but most comments will get approved automatically by this system. The AI also makes summaries of the comments to help you understand the overall sentiment of the community.

Powerful Search & Filtering

Finding exactly what you need is now easier:

• Advanced filtering system with many parameters. You can even filter by attributes to pinpoint services with specific features.

The results are dynamic and shuffle services with identical scores for fairness.

See all listings

Listings are now added as 'Community Contributed' by default. This means that you can still find them in the search results, but they will be clearly marked as such.

Updated Scoring System

New dual-score approach provides more nuanced service evaluations:

• Privacy Score: Measures how well a service protects your personal information and data

• Trust Score: Assesses reliability, security, and overall reputation

• Combined into a weighted Overall Score for quick comparisons

• Completely transparent and open source calculation algorithm. No manual tweaking or hidden factors.

AI-Powered Terms of Service Analysis

Basically, a TLDR summary for Terms of Service:

• Automated system extracts the most important points from complex ToS documents
• Clear summaries
• Updated monthly to catch any changes

The ToS document is hashed and only will be updated if there are any changes.

Service Events and Timelines

Track the complete history of any service, on each service page you can see the timeline of events. There are two types of events:

• Automatic events: Created by the system whenever something about a service changes, like its description, supported currencies, attributes, verification status…
• Manual events: Added by admins when there’s important news, such as a service going offline, being hacked, acquired, shut down, or other major updates.

There is also a global timeline view available at /events

Notification System

Since we now have user accounts, we built a notifiaction system so you can stay informed about anything:

• Notifications for comment replies and status changes
• Watch any comment to get notified for new replies.
• Subscribe to services to monitor events and updates
• Notification customization.

Coming soon: Third-party privacy-preserving notifications integration with Telegram, Ntfy.sh, webhooks...

Service Suggestions

Anyone with an account can suggest a new service via the suggestion form. After submitting, you'll receive a tracking page where you can follow the status of your suggestion and communicate directly with admins.

All new suggestions start as "unlisted" — they won't appear in search results until reviewed. Our team checks each submission to ensure it's not spam or inappropriate. If similar services already exist, you'll be shown possible duplicates and can choose to submit your suggestion as an edit instead.

You can always check the progress of your suggestion, respond to moderator questions, and see when it goes live, everything will also be notified to your account. This process ensures high-quality listings and a collaborative approach to building the directory.

---

These are some of the main features we already have, but there are many more small changes and improvements that you will find when using the site.

What's Next?

This is just the beginning. We will be constantly working to improve KYCnot.me and add more features that help you preserve your privacy.

Remember: True financial freedom requires the right to privacy. Stay KYC-free!

@ cefb08d1:f419beff

https://stacker.news/items/990192

@ 09fbf8f3:fa3d60f0

> ### 第三方API合集：

免责申明:

在此推荐的 OpenAI API Key 由第三方代理商提供，所以我们不对 API Key 的 有效性 和 安全性 负责，请你自行承担购买和使用 API Key 的风险。

| 服务商 | 特性说明 | Proxy 代理地址 | 链接 | | --- | --- | --- | --- | | AiHubMix | 使用 OpenAI 企业接口，全站模型价格为官方 86 折（含 GPT-4 ）| https://aihubmix.com/v1 | 官网 | | OpenAI-HK | OpenAI的API官方计费模式为，按每次API请求内容和返回内容tokens长度来定价。每个模型具有不同的计价方式，以每1,000个tokens消耗为单位定价。其中1,000个tokens约为750个英文单词（约400汉字）| https://api.openai-hk.com/ | 官网 | | CloseAI | CloseAI是国内规模最大的商用级OpenAI代理平台，也是国内第一家专业OpenAI中转服务，定位于企业级商用需求，面向企业客户的线上服务提供高质量稳定的官方OpenAI API 中转代理，是百余家企业和多家科研机构的专用合作平台。 | https://api.openai-proxy.org | 官网 | | OpenAI-SB | 需要配合Telegram 获取api key | https://api.openai-sb.com | 官网 |

持续更新。。。

---

推广：

访问不了openai，去低调云购买VPN。

官网：https://didiaocloud.xyz

邀请码：w9AjVJit

价格低至1元。

@ 3f770d65:7a745b24

At the recent Launch Music Festival and Conference in Lancaster, PA, featuring over 120 musicians across three days, I volunteered my time with Tunestr and Phantom Power Music's initiative to introduce artists to Bitcoin, Nostr, and the value-for-value model. Tunestr sponsored a stage, live-streaming 21 bands to platforms like Tunestr.io, Fountain.fm and other Nostr/Podcasting 2.0 apps and on-boarding as many others as possible at our conference booth. You may have seen me spamming about this over the last few days.

V4V Earnings

Day 1: 180,000 sats

Day 2: 300,000 sats

Day 3: Over 500,000 sats

Who?

Here are the artists that were on-boarded to Fountain and were live streaming on the Value-for-Value stage:

nostr:npub1cruu4z0hwg7n3r2k7262vx8jsmra3xpku85frl5fnfvrwz7rd7mq7e403w nostr:npub12xeh3n7w8700z4tpd6xlhlvg4vtg4pvpxd584ll5sva539tutc3q0tn3tz nostr:npub1rc80p4v60uzfhvdgxemhvcqnzdj7t59xujxdy0lcjxml3uwdezyqtrpe0j @npub16vxr4pc2ww3yaez9q4s53zkejjfd0djs9lfe55sjhnqkh nostr:npub10uspdzg4fl7md95mqnjszxx82ckdly8ezac0t3s06a0gsf4f3lys8ypeak nostr:npub1gnyzexr40qut0za2c4a0x27p4e3qc22wekhcw3uvdx8mwa3pen0s9z90wk nostr:npub13qrrw2h4z52m7jh0spefrwtysl4psfkfv6j4j672se5hkhvtyw7qu0almy nostr:npub1p0kuqxxw2mxczc90vcurvfq7ljuw2394kkqk6gqnn2cq0y9eq5nq87jtkk nostr:npub182kq0sdp7chm67uq58cf4vvl3lk37z8mm5k5067xe09fqqaaxjsqlcazej nostr:npub162hr8kd96vxlanvggl08hmyy37qsn8ehgj7za7squl83um56epnswkr399 nostr:npub17jzk5ex2rafres09c4dnn5mm00eejye6nrurnlla6yn22zcpl7vqg6vhvx nostr:npub176rnksulheuanfx8y8cr2mrth4lh33svvpztggjjm6j2pqw6m56sq7s9vz nostr:npub1akv7t7xpalhsc4nseljs0c886jzuhq8u42qdcwvu972f3mme9tjsgp5xxk nostr:npub18x0gv872489lrczp9d9m4hx59r754x7p9rg2jkgvt7ul3kuqewtqsssn24

Many more musicians were on-boarded to Fountain, however, we were unable to obtain all of their npubs.

THANK YOU TO ALL ZAPPERS AND BOOSTERS!

Musicians “Get It”

My key takeaway was the musicians' absolute understanding that the current digital landscape along with legacy social media is failing them. Every artist I spoke with recognized how algorithms hinder fan connection and how gatekeepers prevent fair compensation for their work. They all use Spotify, but they only do so out of necessity. They felt the music industry is primed for both a social and monetary revolution. Some of them were even speaking my language…

Because of this, concepts like decentralization, censorship resistance, owning your content, and controlling your social graph weren't just understood by them, they were instantly embraced. The excitement was real; they immediately saw the potential and agreed with me. Bitcoin and Nostr felt genuinely punk rock and that helped a lot of them identify with what we were offering them.

The Tools and the Issues

While the Nostr ecosystem offers a wide variety of tools, we focused on introducing three key applications at this event to keep things clear for newcomers:

1. Fountain, with a music focus, was the primary tool for onboarding attendees onto Nostr. Fountain was also chosen thanks to Fountain’s built-in Lightning wallet.
2. Primal, as a social alternative, was demonstrated to show how users can take their Nostr identity and content seamlessly between different applications.
3. Tunestr.io, lastly was showcased for its live video streaming capabilities.

Although we highlighted these three, we did inform attendees about the broader range of available apps and pointed them to nostrapps.com if they wanted to explore further, aiming to educate without overwhelming them.

This review highlights several UX issues with the Fountain app, particularly concerning profile updates, wallet functionality, and user discovery. While Fountain does work well, these minor hiccups make it extremely hard for on-boarding and education.

• Profile Issues:
• When a user edits their profile (e.g., Username/Nostr address, Lightning address) either during or after creation, the changes don't appear to consistently update across the app or sync correctly with Nostr relays.
• Specifically, the main profile display continues to show the old default Username/Nostr address and Lightning address inside Fountain and on other Nostr clients.
• However, the updated Username/Nostr address does appear on https://fountain.fm (chosen-username@fountain.fm) and is visible within the "Edit Profile" screen itself in the app.
• This inconsistency is confusing for users, as they see their updated information in some places but not on their main public-facing profile within the app. I confirmed this by observing a new user sign up and edit their username – the edit screen showed the new name, but the profile display in Fountain did not update and we did not see it inside Primal, Damus, Amethyst, etc.
• Wallet Limitations:
• The app's built-in wallet cannot scan Lightning address QR codes to initiate payments.
• This caused problems during the event where users imported Bitcoin from Azte.co vouchers into their Fountain wallets. When they tried to Zap a band by scanning a QR code on the live tally board, Fountain displayed an error message stating the invoice or QR code was invalid.
• While suggesting musicians install Primal as a second Nostr app was a potential fix for the QR code issue, (and I mentioned it to some), the burden of onboarding users onto two separate applications, potentially managing two different wallets, and explaining which one works for specific tasks creates a confusing and frustrating user experience.
• Search Difficulties:
• Finding other users within the Fountain app is challenging. I was unable to find profiles from brand new users by entering their chosen Fountain username.
• To find a new user, I had to resort to visiting their profile on the web (fountain.fm/username) to retrieve their npub. Then, open Primal and follow them. Finally, when searching for their username, since I was now following them, I was able to find their profile.
• This search issue is compounded by the profile syncing problem mentioned earlier, as even if found via other clients, their displayed information is outdated.
• Searching for the event to Boost/Zap inside Fountain was harder than it should have been the first two days as the live stream did not appear at the top of the screen inside the tap. This was resolved on the third day of the event.

Improving the Onboarding Experience

To better support user growth, educators and on-boarders need more feature complete and user-friendly applications. I love our developers and I will always sing their praises from the highest mountain tops, however I also recognize that the current tools present challenges that hinder a smooth onboarding experience.

One potential approach explored was guiding users to use Primal (including its built-in wallet) in conjunction with Wavlake via Nostr Wallet Connect (NWC). While this could facilitate certain functions like music streaming, zaps, and QR code scanning (which require both Primal and Wavlake apps), Wavlake itself has usability issues. These include inconsistent or separate profiles between web and mobile apps, persistent "Login" buttons even when logged in on the mobile app with a Nostr identity, and the minor inconvenience of needing two separate applications. Although NWC setup is relatively easy and helps streamline the process, the need to switch between apps adds complexity, especially when time is limited and we’re aiming to showcase the benefits of this new system.

Ultimately, we need applications that are more feature-complete and intuitive for mainstream users to improve the onboarding experience significantly.

Looking forward to the future

I anticipate that most of these issues will be resolved when these applications address them in the near future. Specifically, this would involve Fountain fixing its profile issues and integrating Nostr Wallet Connect (NWC) to allow users to utilize their Primal wallet, or by enabling the scanning of QR codes that pay out to Lightning addresses. Alternatively, if Wavlake resolves the consistency problems mentioned earlier, this would also significantly improve the situation giving us two viable solutions for musicians.

My ideal onboarding event experience would involve having all the previously mentioned issues resolved. Additionally, I would love to see every attendee receive a $5 or $10 voucher to help them start engaging with value-for-value, rather than just the limited number we distributed recently. The goal is to have everyone actively zapping and sending Bitcoin throughout the event. Maybe we can find a large sponsor to facilitate this in the future?

What's particularly exciting is the Launch conference's strong interest in integrating value-for-value across their entire program for all musicians and speakers at their next event in Dallas, Texas, coming later this fall. This presents a significant opportunity to onboard over 100+ musicians to Bitcoin and Nostr, which in turn will help onboard their fans and supporters.

We need significantly more zaps and more zappers! It's unreasonable to expect the same dedicated individuals to continuously support new users; they are being bled dry. A shift is needed towards more people using bitcoin for everyday transactions, treating it as money. This brings me back to my ideal onboarding experience: securing a sponsor to essentially give participants bitcoin funds specifically for zapping and tipping artists. This method serves as a practical lesson in using bitcoin as money and showcases the value-for-value principle from the outset.

@ 4c48cf05:07f52b80

I believe that five years from now, access to artificial intelligence will be akin to what access to the Internet represents today. It will be the greatest differentiator between the haves and have nots. Unequal access to artificial intelligence will exacerbate societal inequalities and limit opportunities for those without access to it.

Back in April, the AI Index Steering Committee at the Institute for Human-Centered AI from Stanford University released The AI Index 2024 Annual Report.

Out of the extensive report (502 pages), I chose to focus on the chapter dedicated to Public Opinion. People involved with AI live in a bubble. We all know and understand AI and therefore assume that everyone else does. But, is that really the case once you step out of your regular circles in Seattle or Silicon Valley and hit Main Street?

Two thirds of global respondents have a good understanding of what AI is

The exact number is 67%. My gut feeling is that this number is way too high to be realistic. At the same time, 63% of respondents are aware of ChatGPT so maybe people are confounding AI with ChatGPT?

If so, there is so much more that they won't see coming.

This number is important because you need to see every other questions and response of the survey through the lens of a respondent who believes to have a good understanding of what AI is.

A majority are nervous about AI products and services

52% of global respondents are nervous about products and services that use AI. Leading the pack are Australians at 69% and the least worried are Japanise at 23%. U.S.A. is up there at the top at 63%.

Japan is truly an outlier, with most countries moving between 40% and 60%.

Personal data is the clear victim

Exaclty half of the respondents believe that AI companies will protect their personal data. And the other half believes they won't.

Expected benefits

Again a majority of people (57%) think that it will change how they do their jobs. As for impact on your life, top hitters are getting things done faster (54%) and more entertainment options (51%).

The last one is a head scratcher for me. Are people looking forward to AI generated movies?

Concerns

Remember the 57% that thought that AI will change how they do their jobs? Well, it looks like 37% of them expect to lose it. Whether or not this is what will happen, that is a very high number of people who have a direct incentive to oppose AI.

Other key concerns include:

• Misuse for nefarious purposes: 49%
• Violation of citizens' privacy: 45%

Conclusion

This is the first time I come across this report and I wil make sure to follow future annual reports to see how these trends evolve.

Overall, people are worried about AI. There are many things that could go wrong and people perceive that both jobs and privacy are on the line.

---

Full citation: Nestor Maslej, Loredana Fattorini, Raymond Perrault, Vanessa Parli, Anka Reuel, Erik Brynjolfsson, John Etchemendy, Katrina Ligett, Terah Lyons, James Manyika, Juan Carlos Niebles, Yoav Shoham, Russell Wald, and Jack Clark, “The AI Index 2024 Annual Report,” AI Index Steering Committee, Institute for Human-Centered AI, Stanford University, Stanford, CA, April 2024.

The AI Index 2024 Annual Report by Stanford University is licensed under Attribution-NoDerivatives 4.0 International.

@ 5ea46480:450da5bd

Understanding or grasping Nostr can be deceptively difficult. At the very least it is non-trivial. At first glance, looking at NIP-01, the protocol is rather straight forward. But those are just the basics; yes the beauty of Nostr is its ‘simplicity’, but that does not mean the system that results from it is not complex. Conway's Game of Life only has a hand full of rules, yet you can, in theory at least, create any complex system imaginable. And this is where the deception lies; the less you define from the outset, the more you imply on what follows.

It appears that as it stands, Nostr suffers from this deceptiveness. You can reason through all these implications, but that is still an exercise that has to be performed and where mistakes can be made. Worse, this exercise has been a group effort from the start that is still in progress. Currently there is no clear cut ‘authoritative’ example of all the implications that have been ‘discovered’ thus far.

A good example of the implications following Nostr’s primitives is what we now refer to as the ‘outbox model’. The reason we ‘now’ refer to it as such, is because initially it was called the ‘Gossip model’ derived from the client that first implemented the idea. Outbox is fundamental to Nostr, but it was never explicitly stated in the initial protocol description. The result is that roughly five years into this Nostr endeavor, it is still not universally implemented; worse yet, some developers appear to be in no rush to do so. Now the reason they will give you is probably one based on priority, yet I can’t shake the feeling that they apparently don’t ‘get it’.

My point here is not to play some blame game or hold anyone to account. I am just concluding they don’t actually get the new paradigm that we have all stumbled into. To expand on this specific outbox example, its significance only becomes really apparent further along in the ‘reasoning through all the implications’ exercise. In relation to one aspect, but there are more: The point is not ‘just’ censorship-resistance for users, but the freedom for relays that comes with it to apply whatever policy on what they store and make available; it is this discrimination or curation that can add value by making finding relevant information easier in a straightforward manner. But it relies on outbox to avoid isolation; something that only becomes apparent once you are reasoning through all the implications on how we discover and consume content.

To be clear, this piece is not supposed to a crusade on the outbox model, my point here is that there is an inherent logic to Nostr stemming from putting cryptography front and center. It is a logic that has to be applied and will subsequently carry you through all the challenges we face in reconstructing the entirety of the web. This is not to say there is only one obvious path, and different schools of thought are bound to emerge. But it behooves us all, faced with this new paradigm, to continuously reflect on the mental image we have cultivated of what Nostr is; actively re-performing that exercise of exploring the implications this simple set of protocol rules creates.

Unfortunately I can not escape my own folly. After all, I am just an armchair asshole that never wrote a single line of code in his life. Obviously this minds-eye bullshit is not even half the story, the bulk of the effort is translating it into software, the tangible, the real. It is in that effort ultimately the real exploration of this paradigm occurs. All I can do is build castles in the sky.

@ e3ba5e1a:5e433365

Prelude

I wrote this post differently than any of my others. It started with a discussion with AI on an OPSec-inspired review of separation of powers, and evolved into quite an exciting debate! I asked Grok to write up a summary in my overall writing style, which it got pretty well. I've decided to post it exactly as-is. Ultimately, I think there are two solid ideas driving my stance here:

1. Perfect is the enemy of the good
2. Failure is the crucible of success

Beyond that, just some hard-core belief in freedom, separation of powers, and operating from self-interest.

Intro

Alright, buckle up. I’ve been chewing on this idea for a while, and it’s time to spit it out. Let’s look at the U.S. government like I’d look at a codebase under a cybersecurity audit—OPSEC style, no fluff. Forget the endless debates about what politicians should do. That’s noise. I want to talk about what they can do, the raw powers baked into the system, and why we should stop pretending those powers are sacred. If there’s a hole, either patch it or exploit it. No half-measures. And yeah, I’m okay if the whole thing crashes a bit—failure’s a feature, not a bug.

The Filibuster: A Security Rule with No Teeth

You ever see a firewall rule that’s more theater than protection? That’s the Senate filibuster. Everyone acts like it’s this untouchable guardian of democracy, but here’s the deal: a simple majority can torch it any day. It’s not a law; it’s a Senate preference, like choosing tabs over spaces. When people call killing it the “nuclear option,” I roll my eyes. Nuclear? It’s a button labeled “press me.” If a party wants it gone, they’ll do it. So why the dance?

I say stop playing games. Get rid of the filibuster. If you’re one of those folks who thinks it’s the only thing saving us from tyranny, fine—push for a constitutional amendment to lock it in. That’s a real patch, not a Post-it note. Until then, it’s just a vulnerability begging to be exploited. Every time a party threatens to nuke it, they’re admitting it’s not essential. So let’s stop pretending and move on.

Supreme Court Packing: Because Nine’s Just a Number

Here’s another fun one: the Supreme Court. Nine justices, right? Sounds official. Except it’s not. The Constitution doesn’t say nine—it’s silent on the number. Congress could pass a law tomorrow to make it 15, 20, or 42 (hitchhiker’s reference, anyone?). Packing the court is always on the table, and both sides know it. It’s like a root exploit just sitting there, waiting for someone to log in.

So why not call the bluff? If you’re in power—say, Trump’s back in the game—say, “I’m packing the court unless we amend the Constitution to fix it at nine.” Force the issue. No more shadowboxing. And honestly? The court’s got way too much power anyway. It’s not supposed to be a super-legislature, but here we are, with justices’ ideologies driving the bus. That’s a bug, not a feature. If the court weren’t such a kingmaker, packing it wouldn’t even matter. Maybe we should be talking about clipping its wings instead of just its size.

The Executive Should Go Full Klingon

Let’s talk presidents. I’m not saying they should wear Klingon armor and start shouting “Qapla’!”—though, let’s be real, that’d be awesome. I’m saying the executive should use every scrap of power the Constitution hands them. Enforce the laws you agree with, sideline the ones you don’t. If Congress doesn’t like it, they’ve got tools: pass new laws, override vetoes, or—here’s the big one—cut the budget. That’s not chaos; that’s the system working as designed.

Right now, the real problem isn’t the president overreaching; it’s the bureaucracy. It’s like a daemon running in the background, eating CPU and ignoring the user. The president’s supposed to be the one steering, but the administrative state’s got its own agenda. Let the executive flex, push the limits, and force Congress to check it. Norms? Pfft. The Constitution’s the spec sheet—stick to it.

Let the System Crash

Here’s where I get a little spicy: I’m totally fine if the government grinds to a halt. Deadlock isn’t a disaster; it’s a feature. If the branches can’t agree, let the president veto, let Congress starve the budget, let enforcement stall. Don’t tell me about “essential services.” Nothing’s so critical it can’t take a breather. Shutdowns force everyone to the table—debate, compromise, or expose who’s dropping the ball. If the public loses trust? Good. They’ll vote out the clowns or live with the circus they elected.

Think of it like a server crash. Sometimes you need a hard reboot to clear the cruft. If voters keep picking the same bad admins, well, the country gets what it deserves. Failure’s the best teacher—way better than limping along on autopilot.

States Are the Real MVPs

If the feds fumble, states step up. Right now, states act like junior devs waiting for the lead engineer to sign off. Why? Federal money. It’s a leash, and it’s tight. Cut that cash, and states will remember they’re autonomous. Some will shine, others will tank—looking at you, California. And I’m okay with that. Let people flee to better-run states. No bailouts, no excuses. States are like competing startups: the good ones thrive, the bad ones pivot or die.

Could it get uneven? Sure. Some states might turn into sci-fi utopias while others look like a post-apocalyptic vidya game. That’s the point—competition sorts it out. Citizens can move, markets adjust, and failure’s a signal to fix your act.

Chaos Isn’t the Enemy

Yeah, this sounds messy. States ignoring federal law, external threats poking at our seams, maybe even a constitutional crisis. I’m not scared. The Supreme Court’s there to referee interstate fights, and Congress sets the rules for state-to-state play. But if it all falls apart? Still cool. States can sort it without a babysitter—it’ll be ugly, but freedom’s worth it. External enemies? They’ll either unify us or break us. If we can’t rally, we don’t deserve the win.

Centralizing power to avoid this is like rewriting your app in a single thread to prevent race conditions—sure, it’s simpler, but you’re begging for a deadlock. Decentralized chaos lets states experiment, lets people escape, lets markets breathe. States competing to cut regulations to attract businesses? That’s a race to the bottom for red tape, but a race to the top for innovation—workers might gripe, but they’ll push back, and the tension’s healthy. Bring it—let the cage match play out. The Constitution’s checks are enough if we stop coddling the system.

Why This Matters

I’m not pitching a utopia. I’m pitching a stress test. The U.S. isn’t a fragile porcelain doll; it’s a rugged piece of hardware built to take some hits. Let it fail a little—filibuster, court, feds, whatever. Patch the holes with amendments if you want, or lean into the grind. Either way, stop fearing the crash. It’s how we debug the republic.

So, what’s your take? Ready to let the system rumble, or got a better way to secure the code? Hit me up—I’m all ears.

@ 84b0c46a:417782f5

MAKIMONO

Simple Long Form Content Editor (NIP-23)

機能

• nostr:npub1sjcvg64knxkrt6ev52rywzu9uzqakgy8ehhk8yezxmpewsthst6sw3jqcw や、 nostr:nevent1qvzqqqqqqypzq4jsz7zew5j7jr4pdfxh483nwq9vyw9ph6wm706sjwrzj2we58nqqyxhwumn8ghj77tpvf6jumt9qys8wumn8ghj7un9d3shjtt2wqhxummnw3ezuamfwfjkgmn9wshx5uqpr4mhxue69uhhyetvv9ujumn0wd68ytnhd9ex2erwv46zu6nsqyxhwumn8ghj7mn0wvhxcmmvqqsgcn99jyn5tevxz5zxsrkd7h0sx8fwnqztula423xh83j9wau7cms3vg9c7 のようにnostr:要素を挿入できる （メニューのNアイコンから挿入またはnostr:note～～のように手動で入力）

• :monoice:のようにカスタム絵文字を挿入できる(メニューの🙂アイコンから)

:monopaca_kao:

:kubipaca_karada:

• 新規記事作成と、既存記事の修正ができる

やることやったこと

• [x] nostr:を投稿するときにtagにいれる

• [x] 画像をアップロードできるようにする（NIP-96） できる

• [x] 投稿しましたログとかをトースト的なやつでだすようにする
• [ ] レイアウトを整える
• [ ] あとなんか

@ 91bea5cd:1df4451c

Básico

bash lsblk # Lista todos os diretorios montados.

Para criar o sistema de arquivos:

bash mkfs.btrfs -L "ThePool" -f /dev/sdx

Criando um subvolume:

bash btrfs subvolume create SubVol

Montando Sistema de Arquivos:

bash mount -o compress=zlib,subvol=SubVol,autodefrag /dev/sdx /mnt

Lista os discos formatados no diretório:

bash btrfs filesystem show /mnt

Adiciona novo disco ao subvolume:

bash btrfs device add -f /dev/sdy /mnt

Lista novamente os discos do subvolume:

bash btrfs filesystem show /mnt

Exibe uso dos discos do subvolume:

bash btrfs filesystem df /mnt

Balancea os dados entre os discos sobre raid1:

bash btrfs filesystem balance start -dconvert=raid1 -mconvert=raid1 /mnt

Scrub é uma passagem por todos os dados e metadados do sistema de arquivos e verifica as somas de verificação. Se uma cópia válida estiver disponível (perfis de grupo de blocos replicados), a danificada será reparada. Todas as cópias dos perfis replicados são validadas.

iniciar o processo de depuração :

bash btrfs scrub start /mnt

ver o status do processo de depuração Btrfs em execução:

bash btrfs scrub status /mnt

ver o status do scrub Btrfs para cada um dos dispositivos

bash btrfs scrub status -d / data btrfs scrub cancel / data

Para retomar o processo de depuração do Btrfs que você cancelou ou pausou:

btrfs scrub resume / data

Listando os subvolumes:

bash btrfs subvolume list /Reports

Criando um instantâneo dos subvolumes:

Aqui, estamos criando um instantâneo de leitura e gravação chamado snap de marketing do subvolume de marketing.

bash btrfs subvolume snapshot /Reports/marketing /Reports/marketing-snap

Além disso, você pode criar um instantâneo somente leitura usando o sinalizador -r conforme mostrado. O marketing-rosnap é um instantâneo somente leitura do subvolume de marketing

bash btrfs subvolume snapshot -r /Reports/marketing /Reports/marketing-rosnap

Forçar a sincronização do sistema de arquivos usando o utilitário 'sync'

Para forçar a sincronização do sistema de arquivos, invoque a opção de sincronização conforme mostrado. Observe que o sistema de arquivos já deve estar montado para que o processo de sincronização continue com sucesso.

bash btrfs filsystem sync /Reports

Para excluir o dispositivo do sistema de arquivos, use o comando device delete conforme mostrado.

bash btrfs device delete /dev/sdc /Reports

Para sondar o status de um scrub, use o comando scrub status com a opção -dR .

bash btrfs scrub status -dR / Relatórios

Para cancelar a execução do scrub, use o comando scrub cancel .

bash $ sudo btrfs scrub cancel / Reports

Para retomar ou continuar com uma depuração interrompida anteriormente, execute o comando de cancelamento de depuração

bash sudo btrfs scrub resume /Reports

mostra o uso do dispositivo de armazenamento:

btrfs filesystem usage /data

Para distribuir os dados, metadados e dados do sistema em todos os dispositivos de armazenamento do RAID (incluindo o dispositivo de armazenamento recém-adicionado) montados no diretório /data , execute o seguinte comando:

sudo btrfs balance start --full-balance /data

Pode demorar um pouco para espalhar os dados, metadados e dados do sistema em todos os dispositivos de armazenamento do RAID se ele contiver muitos dados.

Opções importantes de montagem Btrfs

Nesta seção, vou explicar algumas das importantes opções de montagem do Btrfs. Então vamos começar.

As opções de montagem Btrfs mais importantes são:

**1. acl e noacl

**ACL gerencia permissões de usuários e grupos para os arquivos/diretórios do sistema de arquivos Btrfs.

A opção de montagem acl Btrfs habilita ACL. Para desabilitar a ACL, você pode usar a opção de montagem noacl .

Por padrão, a ACL está habilitada. Portanto, o sistema de arquivos Btrfs usa a opção de montagem acl por padrão.

**2. autodefrag e noautodefrag

**Desfragmentar um sistema de arquivos Btrfs melhorará o desempenho do sistema de arquivos reduzindo a fragmentação de dados.

A opção de montagem autodefrag permite a desfragmentação automática do sistema de arquivos Btrfs.

A opção de montagem noautodefrag desativa a desfragmentação automática do sistema de arquivos Btrfs.

Por padrão, a desfragmentação automática está desabilitada. Portanto, o sistema de arquivos Btrfs usa a opção de montagem noautodefrag por padrão.

**3. compactar e compactar-forçar

**Controla a compactação de dados no nível do sistema de arquivos do sistema de arquivos Btrfs.

A opção compactar compacta apenas os arquivos que valem a pena compactar (se compactar o arquivo economizar espaço em disco).

A opção compress-force compacta todos os arquivos do sistema de arquivos Btrfs, mesmo que a compactação do arquivo aumente seu tamanho.

O sistema de arquivos Btrfs suporta muitos algoritmos de compactação e cada um dos algoritmos de compactação possui diferentes níveis de compactação.

Os algoritmos de compactação suportados pelo Btrfs são: lzo , zlib (nível 1 a 9) e zstd (nível 1 a 15).

Você pode especificar qual algoritmo de compactação usar para o sistema de arquivos Btrfs com uma das seguintes opções de montagem:

• compress=algoritmo:nível
• compress-force=algoritmo:nível

Para obter mais informações, consulte meu artigo Como habilitar a compactação do sistema de arquivos Btrfs .

**4. subvol e subvolid

**Estas opções de montagem são usadas para montar separadamente um subvolume específico de um sistema de arquivos Btrfs.

A opção de montagem subvol é usada para montar o subvolume de um sistema de arquivos Btrfs usando seu caminho relativo.

A opção de montagem subvolid é usada para montar o subvolume de um sistema de arquivos Btrfs usando o ID do subvolume.

Para obter mais informações, consulte meu artigo Como criar e montar subvolumes Btrfs .

**5. dispositivo

A opção de montagem de dispositivo** é usada no sistema de arquivos Btrfs de vários dispositivos ou RAID Btrfs.

Em alguns casos, o sistema operacional pode falhar ao detectar os dispositivos de armazenamento usados em um sistema de arquivos Btrfs de vários dispositivos ou RAID Btrfs. Nesses casos, você pode usar a opção de montagem do dispositivo para especificar os dispositivos que deseja usar para o sistema de arquivos de vários dispositivos Btrfs ou RAID.

Você pode usar a opção de montagem de dispositivo várias vezes para carregar diferentes dispositivos de armazenamento para o sistema de arquivos de vários dispositivos Btrfs ou RAID.

Você pode usar o nome do dispositivo (ou seja, sdb , sdc ) ou UUID , UUID_SUB ou PARTUUID do dispositivo de armazenamento com a opção de montagem do dispositivo para identificar o dispositivo de armazenamento.

Por exemplo,

• dispositivo=/dev/sdb
• dispositivo=/dev/sdb,dispositivo=/dev/sdc
• dispositivo=UUID_SUB=490a263d-eb9a-4558-931e-998d4d080c5d
• device=UUID_SUB=490a263d-eb9a-4558-931e-998d4d080c5d,device=UUID_SUB=f7ce4875-0874-436a-b47d-3edef66d3424

**6. degraded

A opção de montagem degradada** permite que um RAID Btrfs seja montado com menos dispositivos de armazenamento do que o perfil RAID requer.

Por exemplo, o perfil raid1 requer a presença de 2 dispositivos de armazenamento. Se um dos dispositivos de armazenamento não estiver disponível em qualquer caso, você usa a opção de montagem degradada para montar o RAID mesmo que 1 de 2 dispositivos de armazenamento esteja disponível.

**7. commit

A opção commit** mount é usada para definir o intervalo (em segundos) dentro do qual os dados serão gravados no dispositivo de armazenamento.

O padrão é definido como 30 segundos.

Para definir o intervalo de confirmação para 15 segundos, você pode usar a opção de montagem commit=15 (digamos).

**8. ssd e nossd

A opção de montagem ssd** informa ao sistema de arquivos Btrfs que o sistema de arquivos está usando um dispositivo de armazenamento SSD, e o sistema de arquivos Btrfs faz a otimização SSD necessária.

A opção de montagem nossd desativa a otimização do SSD.

O sistema de arquivos Btrfs detecta automaticamente se um SSD é usado para o sistema de arquivos Btrfs. Se um SSD for usado, a opção de montagem de SSD será habilitada. Caso contrário, a opção de montagem nossd é habilitada.

**9. ssd_spread e nossd_spread

A opção de montagem ssd_spread** tenta alocar grandes blocos contínuos de espaço não utilizado do SSD. Esse recurso melhora o desempenho de SSDs de baixo custo (baratos).

A opção de montagem nossd_spread desativa o recurso ssd_spread .

O sistema de arquivos Btrfs detecta automaticamente se um SSD é usado para o sistema de arquivos Btrfs. Se um SSD for usado, a opção de montagem ssd_spread será habilitada. Caso contrário, a opção de montagem nossd_spread é habilitada.

**10. descarte e nodiscard

Se você estiver usando um SSD que suporte TRIM enfileirado assíncrono (SATA rev3.1), a opção de montagem de descarte** permitirá o descarte de blocos de arquivos liberados. Isso melhorará o desempenho do SSD.

Se o SSD não suportar TRIM enfileirado assíncrono, a opção de montagem de descarte prejudicará o desempenho do SSD. Nesse caso, a opção de montagem nodiscard deve ser usada.

Por padrão, a opção de montagem nodiscard é usada.

**11. norecovery

Se a opção de montagem norecovery** for usada, o sistema de arquivos Btrfs não tentará executar a operação de recuperação de dados no momento da montagem.

**12. usebackuproot e nousebackuproot

Se a opção de montagem usebackuproot for usada, o sistema de arquivos Btrfs tentará recuperar qualquer raiz de árvore ruim/corrompida no momento da montagem. O sistema de arquivos Btrfs pode armazenar várias raízes de árvore no sistema de arquivos. A opção de montagem usebackuproot** procurará uma boa raiz de árvore e usará a primeira boa que encontrar.

A opção de montagem nousebackuproot não verificará ou recuperará raízes de árvore inválidas/corrompidas no momento da montagem. Este é o comportamento padrão do sistema de arquivos Btrfs.

**13. space_cache, space_cache=version, nospace_cache e clear_cache

A opção de montagem space_cache** é usada para controlar o cache de espaço livre. O cache de espaço livre é usado para melhorar o desempenho da leitura do espaço livre do grupo de blocos do sistema de arquivos Btrfs na memória (RAM).

O sistema de arquivos Btrfs suporta 2 versões do cache de espaço livre: v1 (padrão) e v2

O mecanismo de cache de espaço livre v2 melhora o desempenho de sistemas de arquivos grandes (tamanho de vários terabytes).

Você pode usar a opção de montagem space_cache=v1 para definir a v1 do cache de espaço livre e a opção de montagem space_cache=v2 para definir a v2 do cache de espaço livre.

A opção de montagem clear_cache é usada para limpar o cache de espaço livre.

Quando o cache de espaço livre v2 é criado, o cache deve ser limpo para criar um cache de espaço livre v1 .

Portanto, para usar o cache de espaço livre v1 após a criação do cache de espaço livre v2 , as opções de montagem clear_cache e space_cache=v1 devem ser combinadas: clear_cache,space_cache=v1

A opção de montagem nospace_cache é usada para desabilitar o cache de espaço livre.

Para desabilitar o cache de espaço livre após a criação do cache v1 ou v2 , as opções de montagem nospace_cache e clear_cache devem ser combinadas: clear_cache,nosapce_cache

**14. skip_balance

Por padrão, a operação de balanceamento interrompida/pausada de um sistema de arquivos Btrfs de vários dispositivos ou RAID Btrfs será retomada automaticamente assim que o sistema de arquivos Btrfs for montado. Para desabilitar a retomada automática da operação de equilíbrio interrompido/pausado em um sistema de arquivos Btrfs de vários dispositivos ou RAID Btrfs, você pode usar a opção de montagem skip_balance .**

**15. datacow e nodatacow

A opção datacow** mount habilita o recurso Copy-on-Write (CoW) do sistema de arquivos Btrfs. É o comportamento padrão.

Se você deseja desabilitar o recurso Copy-on-Write (CoW) do sistema de arquivos Btrfs para os arquivos recém-criados, monte o sistema de arquivos Btrfs com a opção de montagem nodatacow .

**16. datasum e nodatasum

A opção datasum** mount habilita a soma de verificação de dados para arquivos recém-criados do sistema de arquivos Btrfs. Este é o comportamento padrão.

Se você não quiser que o sistema de arquivos Btrfs faça a soma de verificação dos dados dos arquivos recém-criados, monte o sistema de arquivos Btrfs com a opção de montagem nodatasum .

Perfis Btrfs

Um perfil Btrfs é usado para informar ao sistema de arquivos Btrfs quantas cópias dos dados/metadados devem ser mantidas e quais níveis de RAID devem ser usados para os dados/metadados. O sistema de arquivos Btrfs contém muitos perfis. Entendê-los o ajudará a configurar um RAID Btrfs da maneira que você deseja.

Os perfis Btrfs disponíveis são os seguintes:

single : Se o perfil único for usado para os dados/metadados, apenas uma cópia dos dados/metadados será armazenada no sistema de arquivos, mesmo se você adicionar vários dispositivos de armazenamento ao sistema de arquivos. Assim, 100% do espaço em disco de cada um dos dispositivos de armazenamento adicionados ao sistema de arquivos pode ser utilizado.

dup : Se o perfil dup for usado para os dados/metadados, cada um dos dispositivos de armazenamento adicionados ao sistema de arquivos manterá duas cópias dos dados/metadados. Assim, 50% do espaço em disco de cada um dos dispositivos de armazenamento adicionados ao sistema de arquivos pode ser utilizado.

raid0 : No perfil raid0 , os dados/metadados serão divididos igualmente em todos os dispositivos de armazenamento adicionados ao sistema de arquivos. Nesta configuração, não haverá dados/metadados redundantes (duplicados). Assim, 100% do espaço em disco de cada um dos dispositivos de armazenamento adicionados ao sistema de arquivos pode ser usado. Se, em qualquer caso, um dos dispositivos de armazenamento falhar, todo o sistema de arquivos será corrompido. Você precisará de pelo menos dois dispositivos de armazenamento para configurar o sistema de arquivos Btrfs no perfil raid0 .

raid1 : No perfil raid1 , duas cópias dos dados/metadados serão armazenadas nos dispositivos de armazenamento adicionados ao sistema de arquivos. Nesta configuração, a matriz RAID pode sobreviver a uma falha de unidade. Mas você pode usar apenas 50% do espaço total em disco. Você precisará de pelo menos dois dispositivos de armazenamento para configurar o sistema de arquivos Btrfs no perfil raid1 .

raid1c3 : No perfil raid1c3 , três cópias dos dados/metadados serão armazenadas nos dispositivos de armazenamento adicionados ao sistema de arquivos. Nesta configuração, a matriz RAID pode sobreviver a duas falhas de unidade, mas você pode usar apenas 33% do espaço total em disco. Você precisará de pelo menos três dispositivos de armazenamento para configurar o sistema de arquivos Btrfs no perfil raid1c3 .

raid1c4 : No perfil raid1c4 , quatro cópias dos dados/metadados serão armazenadas nos dispositivos de armazenamento adicionados ao sistema de arquivos. Nesta configuração, a matriz RAID pode sobreviver a três falhas de unidade, mas você pode usar apenas 25% do espaço total em disco. Você precisará de pelo menos quatro dispositivos de armazenamento para configurar o sistema de arquivos Btrfs no perfil raid1c4 .

raid10 : No perfil raid10 , duas cópias dos dados/metadados serão armazenadas nos dispositivos de armazenamento adicionados ao sistema de arquivos, como no perfil raid1 . Além disso, os dados/metadados serão divididos entre os dispositivos de armazenamento, como no perfil raid0 .

O perfil raid10 é um híbrido dos perfis raid1 e raid0 . Alguns dos dispositivos de armazenamento formam arrays raid1 e alguns desses arrays raid1 são usados para formar um array raid0 . Em uma configuração raid10 , o sistema de arquivos pode sobreviver a uma única falha de unidade em cada uma das matrizes raid1 .

Você pode usar 50% do espaço total em disco na configuração raid10 . Você precisará de pelo menos quatro dispositivos de armazenamento para configurar o sistema de arquivos Btrfs no perfil raid10 .

raid5 : No perfil raid5 , uma cópia dos dados/metadados será dividida entre os dispositivos de armazenamento. Uma única paridade será calculada e distribuída entre os dispositivos de armazenamento do array RAID.

Em uma configuração raid5 , o sistema de arquivos pode sobreviver a uma única falha de unidade. Se uma unidade falhar, você pode adicionar uma nova unidade ao sistema de arquivos e os dados perdidos serão calculados a partir da paridade distribuída das unidades em execução.

Você pode usar 1 00x(N-1)/N % do total de espaços em disco na configuração raid5 . Aqui, N é o número de dispositivos de armazenamento adicionados ao sistema de arquivos. Você precisará de pelo menos três dispositivos de armazenamento para configurar o sistema de arquivos Btrfs no perfil raid5 .

raid6 : No perfil raid6 , uma cópia dos dados/metadados será dividida entre os dispositivos de armazenamento. Duas paridades serão calculadas e distribuídas entre os dispositivos de armazenamento do array RAID.

Em uma configuração raid6 , o sistema de arquivos pode sobreviver a duas falhas de unidade ao mesmo tempo. Se uma unidade falhar, você poderá adicionar uma nova unidade ao sistema de arquivos e os dados perdidos serão calculados a partir das duas paridades distribuídas das unidades em execução.

Você pode usar 100x(N-2)/N % do espaço total em disco na configuração raid6 . Aqui, N é o número de dispositivos de armazenamento adicionados ao sistema de arquivos. Você precisará de pelo menos quatro dispositivos de armazenamento para configurar o sistema de arquivos Btrfs no perfil raid6 .

@ 9223d2fa:b57e3de7

12,600 steps

@ b7274d28:c99628cb

A few months ago, a nostrich was switching from iOS to Android and asked for suggestions for #Nostr apps to try out. nostr:npub18ams6ewn5aj2n3wt2qawzglx9mr4nzksxhvrdc4gzrecw7n5tvjqctp424 offered the following as his response:

nostr:nevent1qvzqqqqqqypzq0mhp4ja8fmy48zuk5p6uy37vtk8tx9dqdwcxm32sy8nsaa8gkeyqydhwumn8ghj7un9d3shjtnwdaehgunsd3jkyuewvdhk6tcpz4mhxue69uhhyetvv9ujuerpd46hxtnfduhszythwden5te0dehhxarj9emkjmn99uqzpwwts6n28eyvjpcwvu5akkwu85eg92dpvgw7cgmpe4czdadqvnv984rl0z

Yes. #Android users are fortunate to have some powerful Nostr apps and tools at our disposal that simply have no comparison over on the iOS side. However, a tool is only as good as the knowledge of the user, who must have an understanding of how best to wield it for maximum effect. This fact was immediately evidenced by replies to Derek asking, "What is the use case for Citrine?" and "This is the first time I'm hearing about Citrine and Pokey. Can you give me links for those?"

Well, consider this tutorial your Nostr starter-kit for Android. We'll go over installing and setting up Amber, Amethyst, Citrine, and Pokey, and as a bonus we'll be throwing in the Zapstore and Coinos to boot. We will assume no previous experience with any of the above, so if you already know all about one or more of these apps, you can feel free to skip that tutorial.

So many apps...

You may be wondering, "Why do I need so many apps to use Nostr?" That's perfectly valid, and the honest answer is, you don't. You can absolutely just install a Nostr client from the Play Store, have it generate your Nostr identity for you, and stick with the default relays already set up in that app. You don't even need to connect a wallet, if you don't want to. However, you won't experience all that Nostr has to offer if that is as far as you go, any more than you would experience all that Italian cuisine has to offer if you only ever try spaghetti.

Nostr is not just one app that does one thing, like Facebook, Twitter, or TikTok. It is an entire ecosystem of applications that are all built on top of a protocol that allows them to be interoperable. This set of tools will help you make the most out of that interoperability, which you will never get from any of the big-tech social platforms. It will provide a solid foundation for you to build upon as you explore more and more of what Nostr has to offer.

So what do these apps do?

Fundamental to everything you do on Nostr is the need to cryptographically sign with your private key. If you aren't sure what that means, just imagine that you had to enter your password every time you hit the "like" button on Facebook, or every time you commented on the latest dank meme. That would get old really fast, right? That's effectively what Nostr requires, but on steroids.

To keep this from being something you manually have to do every 5 seconds when you post a note, react to someone else's note, or add a comment, Nostr apps can store your private key and use it to sign behind the scenes for you. This is very convenient, but it means you are trusting that app to not do anything with your private key that you don't want it to. You are also trusting it to not leak your private key, because anyone who gets their hands on it will be able to post as you, see your private messages, and effectively be you on Nostr. The more apps you give your private key to, the greater your risk that it will eventually be compromised.

Enter #Amber, an application that will store your private key in only one app, and all other compatible Nostr apps can communicate with it to request a signature, without giving any of those other apps access to your private key.

Most Nostr apps for Android now support logging in and signing with Amber, and you can even use it to log into apps on other devices, such as some of the web apps you use on your PC. It's an incredible tool given to us by nostr:npub1w4uswmv6lu9yel005l3qgheysmr7tk9uvwluddznju3nuxalevvs2d0jr5, and only available for Android users. Those on iPhone are incredibly jealous that they don't have anything comparable, yet.

Speaking of nostr:npub1w4uswmv6lu9yel005l3qgheysmr7tk9uvwluddznju3nuxalevvs2d0jr5, the next app is also one of his making.

All Nostr data is stored on relays, which are very simple servers that Nostr apps read notes from and write notes to. In most forms of social media, it can be a pain to get your own data out to keep a backup. That's not the case on Nostr. Anyone can run their own relay, either for the sake of backing up their personal notes, or for others to post their notes to, as well.

Since Nostr notes take up very little space, you can actually run a relay on your phone. I have been on Nostr for almost 2 and a half years, and I have 25,000+ notes of various kinds on my relay, and a backup of that full database is just 24MB on my phone's storage.

Having that backup can save your bacon if you try out a new Nostr client and it doesn't find your existing follow list for some reason, so it writes a new one and you suddenly lose all of the people you were following. Just pop into your #Citrine relay, confirm it still has your correct follow list or import it from a recent backup, then have Citrine restore it. Done.

Additionally, there are things you may want to only save to a relay you control, such as draft messages that you aren't ready to post publicly, or eCash tokens, which can actually be saved to Nostr relays now. Citrine can also be used with Amber for signing into certain Nostr applications that use a relay to communicate with Amber.

If you are really adventurous, you can also expose Citrine over Tor to be used as an outbox relay, or used for peer-to-peer private messaging, but that is far more involved than the scope of this tutorial series.

You can't get far in Nostr without a solid and reliable client to interact with. #Amethyst is the client we will be using for this tutorial because there simply isn't another Android client that comes close, so far. Moreover, it can be a great client for new users to get started on, and yet it has a ton of features for power-users to take advantage of as well.

There are plenty of other good clients to check out over time, such as Coracle, YakiHonne, Voyage, Olas, Flotilla and others, but I keep coming back to Amethyst, and by the time you finish this tutorial, I think you'll see why. nostr:npub1gcxzte5zlkncx26j68ez60fzkvtkm9e0vrwdcvsjakxf9mu9qewqlfnj5z and others who have contributed to Amethyst have really built something special in this client, and it just keeps improving with every update that's shipped.

Most social media apps have some form of push notifications, and some Nostr apps do, too. Where the issue comes in is that Nostr apps are all interoperable. If you have more than one application, you're going to have both of them notifying you. Nostr users are known for having five or more Nostr apps that they use regularly. If all of them had notifications turned on, it would be a nightmare. So maybe you limit it to only one of your Nostr apps having notifications turned on, but then you are pretty well locked-in to opening that particular app when you tap on the notification.

Pokey, by nostr:npub1v3tgrwwsv7c6xckyhm5dmluc05jxd4yeqhpxew87chn0kua0tjzqc6yvjh, solves this issue, allowing you to turn notifications off for all of your Nostr apps, and have Pokey handle them all for you. Then, when you tap on a Pokey notification, you can choose which Nostr app to open it in.

Pokey also gives you control over the types of things you want to be notified about. Maybe you don't care about reactions, and you just want to know about zaps, comments, and direct messages. Pokey has you covered. It even supports multiple accounts, so you can get notifications for all the npubs you control.

One of the most unique and incredibly fun aspects of Nostr is the ability to send and receive #zaps. Instead of merely giving someone a 👍️ when you like something they said, you can actually send them real value in the form of sats, small portions of a Bitcoin. There is nothing quite like the experience of receiving your first zap and realizing that someone valued what you said enough to send you a small amount (and sometimes not so small) of #Bitcoin, the best money mankind has ever known.

To be able to have that experience, though, you are going to need a wallet that can send and receive zaps, and preferably one that is easy to connect to Nostr applications. My current preference for that is Alby Hub, but not everyone wants to deal with all that comes along with running a #Lightning node. That being the case, I have opted to use nostr:npub1h2qfjpnxau9k7ja9qkf50043xfpfy8j5v60xsqryef64y44puwnq28w8ch for this tutorial, because they offer one of the easiest wallets to set up, and it connects to most Nostr apps by just copy/pasting a connection string from the settings in the wallet into the settings in your Nostr app of choice.

Additionally, even though #Coinos is a custodial wallet, you can have it automatically transfer any #sats over a specified threshold to a separate wallet, allowing you to mitigate the custodial risk without needing to keep an eye on your balance and make the transfer manually.

Most of us on Android are used to getting all of our mobile apps from one souce: the Google Play Store. That's not possible for this tutorial series. Only one of the apps mentioned above is available in Google's permissioned playground. However, on Android we have the advantage of being able to install whatever we want on our device, just by popping into our settings and flipping a toggle. Indeed, thumbing our noses at big-tech is at the heart of the Nostr ethos, so why would we make ourselves beholden to Google for installing Nostr apps?

The nostr:npub10r8xl2njyepcw2zwv3a6dyufj4e4ajx86hz6v4ehu4gnpupxxp7stjt2p8 is an alternative app store made by nostr:npub1wf4pufsucer5va8g9p0rj5dnhvfeh6d8w0g6eayaep5dhps6rsgs43dgh9 as a resource for all sorts of open-source apps, but especially Nostr apps. What is more, you can log in with Amber, connect a wallet like Coinos, and support the developers of your favorite Nostr apps directly within the #Zapstore by zapping their app releases.

One of the biggest features of the Zapstore is the fact that developers can cryptographically sign their app releases using their Nostr keys, so you know that the app you are downloading is the one they actually released and hasn't been altered in any way. The Zapstore will warn you and won't let you install the app if the signature is invalid.

Getting Started

Since the Zapstore will be the source we use for installing most of the other apps mentioned, we will start with installing the Zapstore.

We will then use the Zapstore to install Amber and set it up with our Nostr account, either by creating a new private key, or by importing one we already have. We'll also use it to log into the Zapstore.

Next, we will install Amethyst from the Zapstore and log into it via Amber.

After this, we will install Citrine from the Zapstore and add it as a local relay on Amethyst.

Because we want to be able to send and receive zaps, we will set up a wallet with CoinOS and connect it to Amethyst and the Zapstore using Nostr Wallet Connect.

Finally, we will install Pokey using the Zapstore, log into it using Amber, and set up the notifications we want to receive.

By the time you are done with this series, you will have a great head-start on your Nostr journey compared to muddling through it all on your own. Moreover, you will have developed a familiarity with how things generally work on Nostr that can be applied to other apps you try out in the future.

Continue to Part 2: The Zapstore. Nostr Link: nostr:naddr1qvzqqqr4gupzpde8f55w86vrhaeqmd955y4rraw8aunzxgxstsj7eyzgntyev2xtqydhwumn8ghj7un9d3shjtnzwf5kw6r5vfhkcapwdejhgtcqp5cnwdphxv6rwwp3xvmnzvqgty5au

@ 40bdcc08:ad00fd2c

Introduction

Bitcoin’s OP_RETURN opcode, a mechanism for embedding small data in transactions, has ignited a significant debate within the Bitcoin community. Originally designed to support limited metadata while preserving Bitcoin’s role as a peer-to-peer electronic cash system, OP_RETURN is now at the center of proposals that could redefine Bitcoin’s identity. The immutable nature of Bitcoin’s timechain makes it an attractive platform for data storage, creating tension with those who prioritize its monetary function. This discussion, particularly around Bitcoin Core pull request #32406 (GitHub PR #32406), highlights a critical juncture for Bitcoin’s future.

What is OP_RETURN?

Introduced in 2014, OP_RETURN allows users to attach up to 80 bytes of data to a Bitcoin transaction. Unlike other transaction outputs, OP_RETURN outputs are provably unspendable, meaning they don’t burden the Unspent Transaction Output (UTXO) set—a critical database for Bitcoin nodes. This feature was a compromise to provide a standardized, less harmful way to include metadata, addressing earlier practices that embedded data in ways that bloated the UTXO set. The 80-byte limit and restriction to one OP_RETURN output per transaction are part of Bitcoin Core’s standardness rules, which guide transaction relay and mining but are not enforced by the network’s consensus rules (Bitcoin Stack Exchange).

Standardness vs. Consensus Rules

Standardness rules are Bitcoin Core’s default policies for relaying and mining transactions. They differ from consensus rules, which define what transactions are valid across the entire network. For OP_RETURN: - Consensus Rules: Allow OP_RETURN outputs with data up to the maximum script size (approximately 10,000 bytes) and multiple outputs per transaction (Bitcoin Stack Exchange). - Standardness Rules: Limit OP_RETURN data to 80 bytes and one output per transaction to discourage excessive data storage and maintain network efficiency.

Node operators can adjust these policies using settings like -datacarrier (enables/disables OP_RETURN relay) and -datacarriersize (sets the maximum data size, defaulting to 83 bytes to account for the OP_RETURN opcode and pushdata byte). These settings allow flexibility but reflect Bitcoin Core’s default stance on limiting data usage.

The Proposal: Pull Request #32406

Bitcoin Core pull request #32406, proposed by developer instagibbs, seeks to relax these standardness restrictions (GitHub PR #32406). Key changes include: - Removing Default Size Limits: The default -datacarriersize would be uncapped, allowing larger OP_RETURN data without a predefined limit. - Allowing Multiple Outputs: The restriction to one OP_RETURN output per transaction would be lifted, with the total data size across all outputs subject to a configurable limit. - Deprecating Configuration Options: The -datacarrier and -datacarriersize settings are marked as deprecated, signaling potential removal in future releases, which could limit node operators’ ability to enforce custom restrictions.

This proposal does not alter consensus rules, meaning miners and nodes can already accept transactions with larger or multiple OP_RETURN outputs. Instead, it changes Bitcoin Core’s default relay policy to align with existing practices, such as miners accepting non-standard transactions via services like Marathon Digital’s Slipstream (CoinDesk).

Node Operator Flexibility

Currently, node operators can customize OP_RETURN handling: - Default Settings: Relay transactions with one OP_RETURN output up to 80 bytes. - Custom Settings: Operators can disable OP_RETURN relay (-datacarrier=0) or adjust the size limit (e.g., -datacarriersize=100). These options remain in #32406 but are deprecated, suggesting that future Bitcoin Core versions might not support such customization, potentially standardizing the uncapped policy.

Arguments in Favor of Relaxing Limits

Supporters of pull request #32406 and similar proposals argue that the current restrictions are outdated and ineffective. Their key points include: - Ineffective Limits: Developers bypass the 80-byte limit using methods like Inscriptions, which store data in other transaction parts, often at higher cost and inefficiency (BitcoinDev Mailing List). Relaxing OP_RETURN could channel data into a more efficient format. - Preventing UTXO Bloat: By encouraging OP_RETURN use, which doesn’t affect the UTXO set, the proposal could reduce reliance on harmful alternatives like unspendable Taproot outputs used by projects like Citrea’s Clementine bridge. - Supporting Innovation: Projects like Citrea require more data (e.g., 144 bytes) for security proofs, and relaxed limits could enable new Layer 2 solutions (CryptoSlate). - Code Simplification: Developers like Peter Todd argue that these limits complicate Bitcoin Core’s codebase unnecessarily (CoinGeek). - Aligning with Practice: Miners already process non-standard transactions, and uncapping defaults could improve fee estimation and reduce reliance on out-of-band services, as noted by ismaelsadeeq in the pull request discussion.

In the GitHub discussion, developers like Sjors and TheCharlatan expressed support (Concept ACK), citing these efficiency and innovation benefits.

Arguments Against Relaxing Limits

Opponents, including prominent developers and community members, raise significant concerns about the implications of these changes: - Deviation from Bitcoin’s Purpose: Critics like Luke Dashjr, who called the proposal “utter insanity,” argue that Bitcoin’s base layer should prioritize peer-to-peer cash, not data storage (CoinDesk). Jason Hughes warned it could turn Bitcoin into a “worthless altcoin” (BeInCrypto). - Blockchain Bloat: Additional data increases the storage and processing burden on full nodes, potentially making node operation cost-prohibitive and threatening decentralization (CryptoSlate). - Network Congestion: Unrestricted data could lead to “spam” transactions, raising fees and hindering Bitcoin’s use for financial transactions. - Risk of Illicit Content: The timechain’s immutability means data, including potentially illegal or objectionable content, is permanently stored on every node. The 80-byte limit acts as a practical barrier, and relaxing it could exacerbate this issue. - Preserving Consensus: Developers like John Carvalho view the limits as a hard-won community agreement, not to be changed lightly.

In the pull request discussion, nsvrn and moth-oss expressed concerns about spam and centralization, advocating for gradual changes. Concept NACKs from developers like wizkid057 and Luke Dashjr reflect strong opposition.

Community Feedback

The GitHub discussion for pull request #32406 shows a divided community: - Support (Concept ACK): Sjors, polespinasa, ismaelsadeeq, miketwenty1, TheCharlatan, Psifour. - Opposition (Concept NACK): wizkid057, BitcoinMechanic, Retropex, nsvrn, moth-oss, Luke Dashjr. - Other: Peter Todd provided a stale ACK, indicating partial or outdated support.

Additional discussions on the BitcoinDev mailing list and related pull requests (e.g., #32359 by Peter Todd) highlight similar arguments, with #32359 proposing a more aggressive removal of all OP_RETURN limits and configuration options (GitHub PR #32359).

| Feedback Type | Developers | Key Points | |---------------|------------|------------| | Concept ACK | Sjors, ismaelsadeeq, others | Improves efficiency, supports innovation, aligns with mining practices. | | Concept NACK | Luke Dashjr, wizkid057, others | Risks bloat, spam, centralization, and deviation from Bitcoin’s purpose. | | Stale ACK | Peter Todd | Acknowledges proposal but with reservations or outdated support. |

Workarounds and Their Implications

The existence of workarounds, such as Inscriptions, which exploit SegWit discounts to embed data, is a key argument for relaxing OP_RETURN limits. These methods are costlier and less efficient, often costing more than OP_RETURN for data under 143 bytes (BitcoinDev Mailing List). Supporters argue that formalizing larger OP_RETURN data could streamline these use cases. Critics, however, see workarounds as a reason to strengthen, not weaken, restrictions, emphasizing the need to address underlying incentives rather than accommodating bypasses.

Ecosystem Pressures

External factors influence the debate: - Miners: Services like Marathon Digital’s Slipstream process non-standard transactions for a fee, showing that market incentives already bypass standardness rules. - Layer 2 Projects: Citrea’s Clementine bridge, requiring more data for security proofs, exemplifies the demand for relaxed limits to support innovative applications. - Community Dynamics: The debate echoes past controversies, like the Ordinals debate, where data storage via inscriptions raised similar concerns about Bitcoin’s purpose (CoinDesk).

Bitcoin’s Identity at Stake

The OP_RETURN debate is not merely technical but philosophical, questioning whether Bitcoin should remain a focused monetary system or evolve into a broader data platform. Supporters see relaxed limits as a pragmatic step toward efficiency and innovation, while opponents view them as a risk to Bitcoin’s decentralization, accessibility, and core mission. The community’s decision will have lasting implications, affecting node operators, miners, developers, and users.

Conclusion

As Bitcoin navigates this crossroads, the community must balance the potential benefits of relaxed OP_RETURN limits—such as improved efficiency and support for new applications—against the risks of blockchain bloat, network congestion, and deviation from its monetary roots. The ongoing discussion, accessible via pull request #32406 on GitHub (GitHub PR #32406). Readers are encouraged to explore the debate and contribute to ensuring that any changes align with Bitcoin’s long-term goals as a decentralized, secure, and reliable system.

@ dc4cd086:cee77c06

Have you ever wanted to learn from lengthy educational videos but found it challenging to navigate through hours of content? Our new tool addresses this problem by transforming long-form video lectures into easily digestible, searchable content.

Key Features:

Video Processing:

• Automatically downloads YouTube videos, transcripts, and chapter information
• Splits transcripts into sections based on video chapters

Content Summarization:

• Utilizes language models to transform spoken content into clear, readable text
• Formats output in AsciiDoc for improved readability and navigation
• Highlights key terms and concepts with [[term]] notation for potential cross-referencing

Diagram Extraction:

• Analyzes video entropy to identify static diagram/slide sections
• Provides a user-friendly GUI for manual selection of relevant time ranges
• Allows users to pick representative frames from selected ranges

Going Forward:

Currently undergoing a rewrite to improve organization and functionality, but you are welcome to try the current version, though it might not work on every machine. Will support multiple open and closed language models for user choice Free and open-source, allowing for personal customization and integration with various knowledge bases. Just because we might not have it on our official Alexandria knowledge base, you are still welcome to use it on you own personal or community knowledge bases! We want to help find connections between ideas that exist across relays, allowing individuals and groups to mix and match knowledge bases between each other, allowing for any degree of openness you care.

While designed with #Alexandria users in mind, it's available for anyone to use and adapt to their own learning needs.

Screenshots

Frame Selection

This is a screenshot of the frame selection interface. You'll see a signal that represents frame entropy over time. The vertical lines indicate the start and end of a chapter. Within these chapters you can select the frames by clicking and dragging the mouse over the desired range where you think diagram is in that chapter. At the bottom is an option that tells the program to select a specific number of frames from that selection.

Diagram Extraction

This is a screenshot of the diagram extraction interface. For every selection you've made, there will be a set of frames that you can choose from. You can select and deselect as many frames as you'd like to save.

Links

• repo: https://github.com/limina1/video_article_converter
• Nostr Apps 101: https://www.youtube.com/watch?v=Flxa_jkErqE

Output

And now, we have a demonstration of the final result of this tool, with some quick cleaning up. The video we will be using this tool on is titled Nostr Apps 101 by nostr:npub1nxy4qpqnld6kmpphjykvx2lqwvxmuxluddwjamm4nc29ds3elyzsm5avr7 during Nostrasia. The following thread is an analog to the modular articles we are constructing for Alexandria, and I hope it conveys the functionality we want to create in the knowledge space. Note, this tool is the first step! You could use a different prompt that is most appropriate for the specific context of the transcript you are working with, but you can also manually clean up any discrepancies that don't portray the video accurately.

nostr:nevent1qvzqqqqqqypzp5r5hd579v2sszvvzfel677c8dxgxm3skl773sujlsuft64c44ncqy2hwumn8ghj7un9d3shjtnyv9kh2uewd9hj7qgwwaehxw309ahx7uewd3hkctcpzemhxue69uhhyetvv9ujumt0wd68ytnsw43z7qghwaehxw309aex2mrp0yhxummnw3ezucnpdejz7qgewaehxw309aex2mrp0yh8xmn0wf6zuum0vd5kzmp0qqsxunmjy20mvlq37vnrcshkf6sdrtkfjtjz3anuetmcuv8jswhezgc7hglpn

Or view on Coracle nostr:nevent1qqsxunmjy20mvlq37vnrcshkf6sdrtkfjtjz3anuetmcuv8jswhezgcppemhxue69uhkummn9ekx7mp0qgsdqa9md83tz5yqnrqjw07hhkpmfjpkuv9hlh5v8yhu8z274w9dv7qnnq0s3

@ 2183e947:f497b975

Most darknet markets (DNMs) are designed poorly in the following ways:

1. Hosting

Most DNMs use a model whereby merchants fill out a form to create their listings, and the data they submit then gets hosted on the DNM's servers. In scenarios where a "legal" website would be forced to censor that content (e.g. a DMCA takedown order), DNMs, of course, do not obey. This can lead to authorities trying to find the DNM's servers to take enforcement actions against them. This design creates a single point of failure.

A better design is to outsource hosting to third parties. Let merchants host their listings on nostr relays, not on the DNM's server. The DNM should only be designed as an open source interface for exploring listings hosted elsewhere, that way takedown orders end up with the people who actually host the listings, i.e. with nostr relays, and not with the DNM itself. And if a nostr relay DOES go down due to enforcement action, it does not significantly affect the DNM -- they'll just stop querying for listings from that relay in their next software update, because that relay doesn't work anymore, and only query for listings from relays that still work.

2. Moderation

Most DNMs have employees who curate the listings on the DNM. For example, they approve/deny listings depending on whether they fit the content policies of the website. Some DNMs are only for drugs, others are only for firearms. The problem is, to approve a criminal listing is, in the eyes of law enforcement, an act of conspiracy. Consequently, they don't just go after the merchant who made the listing but the moderators who approved it, and since the moderators typically act under the direction of the DNM, this means the police go after the DNM itself.

A better design is to outsource moderation to third parties. Let anyone call themselves a moderator and create lists of approved goods and services. Merchants can pay the most popular third party moderators to add their products to their lists. The DNM itself just lets its users pick which moderators to use, such that the user's choice -- and not a choice by the DNM -- determines what goods and services the user sees in the interface.

That way, the police go after the moderators and merchants rather than the DNM itself, which is basically just a web browser: it doesn't host anything or approve of any content, it just shows what its users tell it to show. And if a popular moderator gets arrested, his list will still work for a while, but will gradually get more and more outdated, leading someone else to eventually become the new most popular moderator, and a natural transition can occur.

3. Escrow

Most DNMs offer an escrow solution whereby users do not pay merchants directly. Rather, during the Checkout process, they put their money in escrow, and request the DNM to release it to the merchant when the product arrives, otherwise they initiate a dispute. Most DNMs consider escrow necessary because DNM users and merchants do not trust one another; users don't want to pay for a product first and then discover that the merchant never ships it, and merchants don't want to ship a product first and then discover that the user never pays for it.

The problem is, running an escrow solution for criminals is almost certain to get you accused of conspiracy, money laundering, and unlicensed money transmission, so the police are likely to shut down any DNM that does this. A better design is to oursource escrow to third parties. Let anyone call themselves an escrow, and let moderators approve escrows just like they approve listings. A merchant or user who doesn't trust the escrows chosen by a given moderator can just pick a different moderator. That way, the police go after the third party escrows rather than the DNM itself, which never touches user funds.

4. Consequences

Designing a DNM along these principles has an interesting consequence: the DNM is no longer anything but an interface, a glorified web browser. It doesn't host any content, approve any listings, or touch any money. It doesn't even really need a server -- it can just be an HTML file that users open up on their computer or smart phone. For two reasons, such a program is hard to take down:

First, it is hard for the police to justify going after the DNM, since there are no charges to bring. Its maintainers aren't doing anything illegal, no more than Firefox does anything illegal by maintaining a web browser that some people use to browse illegal content. What the user displays in the app is up to them, not to the code maintainers. Second, if the police decided to go after the DNM anyway, they still couldn't take it down because it's just an HTML file -- the maintainers do not even need to run a server to host the file, because users can share it with one another, eliminating all single points of failure.

Another consequence of this design is this: most of the listings will probably be legal, because there is more demand for legal goods and services than illegal ones. Users who want to find illegal goods would pick moderators who only approve those listings, but everyone else would use "legal" moderators, and the app would not, at first glance, look much like a DNM, just a marketplace for legal goods and services. To find the illegal stuff that lurks among the abundant legal stuff, you'd probably have to filter for it via your selection of moderators, making it seem like the "default" mode is legal.

5. Conclusion

I think this DNM model is far better than the designs that prevail today. It is easier to maintain, harder to take down, and pushes the "hard parts" to the edges, so that the DNM is not significantly affected even if a major merchant, moderator, or escrow gets arrested. I hope it comes to fruition.

@ 84b0c46a:417782f5

nostrリンクテスト

web+nostrリンクテスト

x-ukagaka-linkテスト

x-ukagaka-linkテスト2

nostalk

ハイパーテスト

@ 8947a945:9bfcf626

สวัสดีทุกคนบน Nostr ครับ รวมไปถึง watchersและ ผู้ติดตามของผมจาก Deviantart และ platform งานศิลปะอื่นๆนะครับ

ตั้งแต่ต้นปี 2024 ผมใช้ AI เจนรูปงานตัวละครสาวๆจากอนิเมะ และเปิด exclusive content ให้สำหรับผู้ที่ชื่นชอบผลงานของผมเป็นพิเศษ

ผมโพสผลงานผมทั้งหมดไว้ที่เวบ Deviantart และค่อยๆสร้างฐานผู้ติดตามมาเรื่อยๆอย่างค่อยเป็นค่อยไปมาตลอดครับ ทุกอย่างเติบโตไปเรื่อยๆของมัน ส่วนตัวผมมองว่ามันเป็นพิร์ตธุรกิจออนไลน์ ของผมพอร์ตนึงได้เลย

เมื่อวันที่ 16 กย.2024 มีผู้ติดตามคนหนึ่งส่งข้อความส่วนตัวมาหาผม บอกว่าชื่นชอบผลงานของผมมาก ต้องการจะขอซื้อผลงาน แต่ขอซื้อเป็น NFT นะ เสนอราคาซื้อขายต่อชิ้นที่สูงมาก หลังจากนั้นผมกับผู้ซื้อคนนี้พูดคุยกันในเมล์ครับ

นี่คือข้อสรุปสั่นๆจากการต่อรองซื้อขายครับ

(หลังจากนี้ผมขอเรียกผู้ซื้อว่า scammer นะครับ เพราะไพ่มันหงายมาแล้ว ว่าเขาคือมิจฉาชีพ)

• Scammer รายแรก เลือกผลงานที่จะซื้อ เสนอราคาซื้อที่สูงมาก แต่ต้องเป็นเวบไซต์ NFTmarket place ที่เขากำหนดเท่านั้น มันทำงานอยู่บน ERC20 ผมเข้าไปดูเวบไซต์ที่ว่านี้แล้วรู้สึกว่ามันดูแปลกๆครับ คนที่จะลงขายผลงานจะต้องใช้ email ในการสมัครบัญชีซะก่อน ถึงจะผูก wallet อย่างเช่น metamask ได้ เมื่อผูก wallet แล้วไม่สามารถเปลี่ยนได้ด้วย ตอนนั้นผมใช้ wallet ที่ไม่ได้ link กับ HW wallet ไว้ ทดลองสลับ wallet ไปๆมาๆ มันทำไม่ได้ แถมลอง log out แล้ว เลข wallet ก็ยังคาอยู่อันเดิม อันนี้มันดูแปลกๆแล้วหนึ่งอย่าง เวบนี้ค่า ETH ในการ mint 0.15 - 0.2 ETH … ตีเป็นเงินบาทนี่แพงบรรลัยอยู่นะครับ

• Scammer รายแรกพยายามชักจูงผม หว่านล้อมผมว่า แหม เดี๋ยวเขาก็มารับซื้องานผมน่า mint งานเสร็จ รีบบอกเขานะ เดี๋ยวเขารีบกดซื้อเลย พอขายได้กำไร ผมก็ได้ค่า gas คืนได้ แถมยังได้กำไรอีก ไม่มีอะไรต้องเสีนจริงมั้ย แต่มันเป้นความโชคดีครับ เพราะตอนนั้นผมไม่เหลือทุนสำรองที่จะมาซื้อ ETH ได้ ผมเลยต่อรองกับเขาตามนี้ครับ :

• ผมเสนอว่า เอางี้มั้ย ผมส่งผลงานของผมแบบ low resolution ให้ก่อน แลกกับให้เขาช่วยโอน ETH ที่เป็นค่า mint งานมาให้หน่อย พอผมได้ ETH แล้ว ผมจะ upscale งานของผม แล้วเมล์ไปให้ ใจแลกใจกันไปเลย ... เขาไม่เอา

• ผมเสนอให้ไปซื้อที่ร้านค้าออนไลน์ buymeacoffee ของผมมั้ย จ่ายเป็น USD ... เขาไม่เอา
• ผมเสนอให้ซื้อขายผ่าน PPV lightning invoice ที่ผมมีสิทธิ์เข้าถึง เพราะเป็น creator ของ Creatr ... เขาไม่เอา
• ผมยอกเขาว่างั้นก็รอนะ รอเงินเดือนออก เขาบอก ok

สัปดาห์ถัดมา มี scammer คนที่สองติดต่อผมเข้ามา ใช้วิธีการใกล้เคียงกัน แต่ใช้คนละเวบ แถมเสนอราคาซื้อที่สูงกว่าคนแรกมาก เวบที่สองนี้เลวร้ายค่าเวบแรกอีกครับ คือต้องใช้เมล์สมัครบัญชี ไม่สามารถผูก metamask ได้ พอสมัครเสร็จจะได้ wallet เปล่าๆมาหนึ่งอัน ผมต้องโอน ETH เข้าไปใน wallet นั้นก่อน เพื่อเอาไปเป็นค่า mint NFT 0.2 ETH

ผมบอก scammer รายที่สองว่า ต้องรอนะ เพราะตอนนี้กำลังติดต่อซื้อขายอยู่กับผู้ซื้อรายแรกอยู่ ผมกำลังรอเงินเพื่อมาซื้อ ETH เป็นต้นทุนดำเนินงานอยู่ คนคนนี้ขอให้ผมส่งเวบแรกไปให้เขาดูหน่อย หลังจากนั้นไม่นานเขาเตือนผมมาว่าเวบแรกมันคือ scam นะ ไม่สามารถถอนเงินออกมาได้ เขายังส่งรูป cap หน้าจอที่คุยกับผู้เสียหายจากเวบแรกมาให้ดูว่าเจอปัญหาถอนเงินไม่ได้ ไม่พอ เขายังบลัฟ opensea ด้วยว่าลูกค้าขายงานได้ แต่ถอนเงินไม่ได้

Opensea ถอนเงินไม่ได้ ตรงนี้แหละครับคือตัวกระตุกต่อมเอ๊ะของผมดังมาก เพราะ opensea อ่ะ ผู้ใช้ connect wallet เข้ากับ marketplace โดยตรง ซื้อขายกันเกิดขึ้น เงินวิ่งเข้าวิ่งออก wallet ของแต่ละคนโดยตรงเลย opensea เก็บแค่ค่า fee ในการใช้ platform ไม่เก็บเงินลูกค้าไว้ แถมปีนี้ค่า gas fee ก็ถูกกว่า bull run cycle 2020 มาก ตอนนี้ค่า gas fee ประมาณ 0.0001 ETH (แต่มันก็แพงกว่า BTC อยู่ดีอ่ะครับ)

ผมเลยเอาเรื่องนี้ไปปรึกษาพี่บิท แต่แอดมินมาคุยกับผมแทน ทางแอดมินแจ้งว่ายังไม่เคยมีเพื่อนๆมาปรึกษาเรื่องนี้ กรณีที่ผมทักมาถามนี่เป็นรายแรกเลย แต่แอดมินให้ความเห็นไปในทางเดียวกับสมมุติฐานของผมว่าน่าจะ scam ในเวลาเดียวกับผมเอาเรื่องนี้ไปถามในเพจ NFT community คนไทนด้วย ได้รับการ confirm ชัดเจนว่า scam และมีคนไม่น้อยโดนหลอก หลังจากที่ผมรู้ที่มาแล้ว ผมเลยเล่นสงครามปั่นประสาท scammer ทั้งสองคนนี้ครับ เพื่อดูว่าหลอกหลวงมิจฉาชีพจริงมั้ย

โดยวันที่ 30 กย. ผมเลยปั่นประสาน scammer ทั้งสองรายนี้ โดยการ mint ผลงานที่เขาเสนอซื้อนั่นแหละ ขึ้น opensea แล้วส่งข้อความไปบอกว่า

mint ให้แล้วนะ แต่เงินไม่พอจริงๆว่ะโทษที เลย mint ขึ้น opensea แทน พอดีบ้านจน ทำได้แค่นี้ไปถึงแค่ opensea รีบไปซื้อล่ะ มีคนจ้องจะคว้างานผมเยอะอยู่ ผมไม่คิด royalty fee ด้วยนะเฮ้ย เอาไปขายต่อไม่ต้องแบ่งกำไรกับผม

เท่านั้นแหละครับ สงครามจิตวิทยาก็เริ่มขึ้น แต่เขาจนมุม กลืนน้ำลายตัวเอง ช็อตเด็ดคือ

เขา : เนี่ยอุส่ารอ บอกเพื่อนในทีมว่าวันจันทร์ที่ 30 กย. ได้ของแน่ๆ เพื่อนๆในทีมเห็นงานผมแล้วมันสวยจริง เลยใส่เงินเต็มที่ 9.3ETH (+ capture screen ส่งตัวเลขยอดเงินมาให้ดู)ไว้รอโดยเฉพาะเลยนะ ผม : เหรอ ... งั้น ขอดู wallet address ที่มี transaction มาให้ดูหน่อยสิ เขา : 2ETH นี่มัน 5000$ เลยนะ ผม : แล้วไง ขอดู wallet address ที่มีการเอายอดเงิน 9.3ETH มาให้ดูหน่อย ไหนบอกว่าเตรียมเงินไว้มากแล้วนี่ ขอดูหน่อย ว่าใส่ไว้เมื่อไหร่ ... เอามาแค่ adrress นะเว้ย ไม่ต้องทะลึ่งส่ง seed มาให้ เขา : ส่งรูปเดิม 9.3 ETH มาให้ดู ผม : รูป screenshot อ่ะ มันไม่มีความหมายหรอกเว้ย ตัดต่อเอาก็ได้ง่ายจะตาย เอา transaction hash มาดู ไหนว่าเตรียมเงินไว้รอ 9.3ETH แล้วอยากซื้องานผมจนตัวสั่นเลยไม่ใช่เหรอ ถ้าจะส่ง wallet address มาให้ดู หรือจะช่วยส่ง 0.15ETH มาให้ยืม mint งานก่อน แล้วมากดซื้อ 2ETH ไป แล้วผมใช้ 0.15ETH คืนให้ก็ได้ จะซื้อหรือไม่ซื้อเนี่ย เขา : จะเอา address เขาไปทำไม ผม : ตัดจบ รำคาญ ไม่ขายให้ละ เขา : 2ETH = 5000 USD เลยนะ ผม : แล้วไง

ผมเลยเขียนบทความนี้มาเตือนเพื่อนๆพี่ๆทุกคนครับ เผื่อใครกำลังเปิดพอร์ตทำธุรกิจขาย digital art online แล้วจะโชคดี เจอของดีแบบผม

---

ทำไมผมถึงมั่นใจว่ามันคือการหลอกหลวง แล้วคนโกงจะได้อะไร

อันดับแรกไปพิจารณาดู opensea ครับ เป็นเวบ NFTmarketplace ที่ volume การซื้อขายสูงที่สุด เขาไม่เก็บเงินของคนจะซื้อจะขายกันไว้กับตัวเอง เงินวิ่งเข้าวิ่งออก wallet ผู้ซื้อผู้ขายเลย ส่วนทางเวบเก็บค่าธรรมเนียมเท่านั้น แถมค่าธรรมเนียมก็ถูกกว่าเมื่อปี 2020 เยอะ ดังนั้นการที่จะไปลงขายงานบนเวบ NFT อื่นที่ค่า fee สูงกว่ากันเป็นร้อยเท่า ... จะทำไปทำไม

ผมเชื่อว่า scammer โกงเงินเจ้าของผลงานโดยการเล่นกับความโลภและความอ่อนประสบการณ์ของเจ้าของผลงานครับ เมื่อไหร่ก็ตามที่เจ้าของผลงานโอน ETH เข้าไปใน wallet เวบนั้นเมื่อไหร่ หรือเมื่อไหร่ก็ตามที่จ่ายค่า fee ในการ mint งาน เงินเหล่านั้นสิ่งเข้ากระเป๋า scammer ทันที แล้วก็จะมีการเล่นตุกติกต่อแน่นอนครับ เช่นถอนไม่ได้ หรือซื้อไม่ได้ ต้องโอนเงินมาเพิ่มเพื่อปลดล็อค smart contract อะไรก็ว่าไป แล้วคนนิสัยไม่ดีพวกเนี้ย ก็จะเล่นกับความโลภของคน เอาราคาเสนอซื้อที่สูงโคตรๆมาล่อ ... อันนี้ไม่ว่ากัน เพราะบนโลก NFT รูปภาพบางรูปที่ไม่ได้มีความเป็นศิลปะอะไรเลย มันดันขายกันได้ 100 - 150 ETH ศิลปินที่พยายามสร้างตัวก็อาจจะมองว่า ผลงานเรามีคนรับซื้อ 2 - 4 ETH ต่องานมันก็มากพอแล้ว (จริงๆมากเกินจนน่าตกใจด้วยซ้ำครับ)

บนโลกของ BTC ไม่ต้องเชื่อใจกัน โอนเงินไปหากันได้ ปิดสมุดบัญชีได้โดยไม่ต้องเชื่อใจกัน

บบโลกของ ETH "code is law" smart contract มีเขียนอยู่แล้ว ไปอ่าน มันไม่ได้ยากมากในการทำความเข้าใจ ดังนั้น การจะมาเชื่อคำสัญญาจากคนด้วยกัน เป็นอะไรที่ไม่มีเหตุผล

ผมไปเล่าเรื่องเหล่านี้ให้กับ community งานศิลปะ ก็มีทั้งเสียงตอบรับที่ดี และไม่ดีปนกันไป มีบางคนยืนยันเสียงแข็งไปในทำนองว่า ไอ้เรื่องแบบเนี้ยไม่ได้กินเขาหรอก เพราะเขาตั้งใจแน่วแน่ว่างานศิลป์ของเขา เขาไม่เอาเข้ามายุ่งในโลก digital currency เด็ดขาด ซึ่งผมก็เคารพมุมมองเขาครับ แต่มันจะดีกว่ามั้ย ถ้าเราเปิดหูเปิดตาให้ทันเทคโนโลยี โดยเฉพาะเรื่อง digital currency , blockchain โดนโกงทีนึงนี่คือหมดตัวกันง่ายกว่าเงิน fiat อีก

อยากจะมาเล่าให้ฟังครับ และอยากให้ช่วยแชร์ไปให้คนรู้จักด้วย จะได้ระวังตัวกัน

Note

• ภาพประกอบ cyber security ทั้งสองนี่ของผมเองครับ ทำเอง วางขายบน AdobeStock
• อีกบัญชีนึงของผม "HikariHarmony" npub1exdtszhpw3ep643p9z8pahkw8zw00xa9pesf0u4txyyfqvthwapqwh48sw กำลังค่อยๆเอาผลงานจากโลกข้างนอกเข้ามา nostr ครับ ตั้งใจจะมาสร้างงานศิลปะในนี้ เพื่อนๆที่ชอบงาน จะได้ไม่ต้องออกไปหาที่ไหน

ผลงานของผมครับ - Anime girl fanarts : HikariHarmony - HikariHarmony on Nostr - General art : KeshikiRakuen - KeshikiRakuen อาจจะเป็นบัญชี nostr ที่สามของผม ถ้าไหวครับ

@ 0fa80bd3:ea7325de

DAOs promised decentralization. They offered a system where every member could influence a project's direction, where money and power were transparently distributed, and decisions were made through voting. All of it recorded immutably on the blockchain, free from middlemen.

But something didn’t work out. In practice, most DAOs haven’t evolved into living, self-organizing organisms. They became something else: clubs where participation is unevenly distributed. Leaders remained - only now without formal titles. They hold influence through control over communications, task framing, and community dynamics. Centralization still exists, just wrapped in a new package.

But there's a second, less obvious problem. Crowds can’t create strategy. In DAOs, people vote for what "feels right to the majority." But strategy isn’t about what feels good - it’s about what’s necessary. Difficult, unpopular, yet forward-looking decisions often fail when put to a vote. A founder’s vision is a risk. But in healthy teams, it’s that risk that drives progress. In DAOs, risk is almost always diluted until it becomes something safe and vague.

Instead of empowering leaders, DAOs often neutralize them. This is why many DAOs resemble consensus machines. Everyone talks, debates, and participates, but very little actually gets done. One person says, “Let’s jump,” and five others respond, “Let’s discuss that first.” This dynamic might work for open forums, but not for action.

Decentralization works when there’s trust and delegation, not just voting. Until DAOs develop effective systems for assigning roles, taking ownership, and acting with flexibility, they will keep losing ground to old-fashioned startups led by charismatic founders with a clear vision.

We’ve seen this in many real-world cases. Take MakerDAO, one of the most mature and technically sophisticated DAOs. Its governance token (MKR) holders vote on everything from interest rates to protocol upgrades. While this has allowed for transparency and community involvement, the process is often slow and bureaucratic. Complex proposals stall. Strategic pivots become hard to implement. And in 2023, a controversial proposal to allocate billions to real-world assets passed only narrowly, after months of infighting - highlighting how vision and execution can get stuck in the mud of distributed governance.

On the other hand, Uniswap DAO, responsible for the largest decentralized exchange, raised governance participation only after launching a delegation system where token holders could choose trusted representatives. Still, much of the activity is limited to a small group of active contributors. The vast majority of token holders remain passive. This raises the question: is it really community-led, or just a formalized power structure with lower transparency?

Then there’s ConstitutionDAO, an experiment that went viral. It raised over $40 million in days to try and buy a copy of the U.S. Constitution. But despite the hype, the DAO failed to win the auction. Afterwards, it struggled with refund logistics, communication breakdowns, and confusion over governance. It was a perfect example of collective enthusiasm without infrastructure or planning - proof that a DAO can raise capital fast but still lack cohesion.

Not all efforts have failed. Projects like Gitcoin DAO have made progress by incentivizing small, individual contributions. Their quadratic funding mechanism rewards projects based on the number of contributors, not just the size of donations, helping to elevate grassroots initiatives. But even here, long-term strategy often falls back on a core group of organizers rather than broad community consensus.

The pattern is clear: when the stakes are low or the tasks are modular, DAOs can coordinate well. But when bold moves are needed—when someone has to take responsibility and act under uncertainty DAOs often freeze. In the name of consensus, they lose momentum.

That’s why the organization of the future can’t rely purely on decentralization. It must encourage individual initiative and the ability to take calculated risks. People need to see their contribution not just as a vote, but as a role with clear actions and expected outcomes. When the situation demands, they should be empowered to act first and present the results to the community afterwards allowing for both autonomy and accountability. That’s not a flaw in the system. It’s how real progress happens.

@ 75869cfa:76819987

GM, Nostriches!

The Nostr Review is a biweekly newsletter focused on protocol updates, exciting programs, the long-form content ecosystem, and key events happening in the Nostr-verse. If you’re interested, join me in covering updates from the Nostr ecosystem!

Quick review:

In the past two weeks, 22 pull requests were submitted to the Nostr protocol, with 6 merged. A total of 65 Nostr projects were tracked, with 12 releasing product updates, and over 359 long-form articles were published, 43% focusing on Bitcoin and Nostr. During this period, 4 notable events took place, and 4 significant events are upcoming.

NIPs

Group channels #1917

nostr:npub1t70s45chajpkl4ncyqhsldd2c4557ecg3ze0t5lxuam96gzr6qlqae2qq0 is proposing PR that an interface like discord server channels / telegram topics / matrix(element) space rooms.

NIP-XX: Passkey-Wrapped Keys a.k.a. Nosskey #1919

nostr:npub1y6aja0kkc4fdvuxgqjcdv4fx0v7xv2epuqnddey2eyaxquznp9vq0tp75l is proposing a PR that proposes a standardized method for managing Nostr private keys using WebAuthn passkeys (FIDO2/WebAuthn credentials). The specification aims to significantly improve user experience by eliminating the need for private key backup or complex secret key management, enabling users to interact with Nostr applications through intuitive operations such as biometric authentication or physical security keys.Two implementation approaches are defined:PRF Direct Usage Method - Directly utilizing WebAuthn PRF extension values as Nostr private keys; Encryption Method - Encrypting existing Nostr private keys with keys derived from passkeys For the Encryption Method, while AES-GCM is used as an example in the specification, the NIP itself does not mandate any specific encryption algorithm, allowing implementers to choose appropriate methods. This approach does not require compatibility with NIP-49 (password-based encryption) as the PRF extension in WebAuthn already provides sufficient entropy, making it more efficient to use other standardized encryption algorithms directly.

Create NIP-XX.md: Voice Messages #1923

nostr:npub18ams6ewn5aj2n3wt2qawzglx9mr4nzksxhvrdc4gzrecw7n5tvjqctp424 is proposing a new NIP for Kind 1222: Voice Messages.This new event kind is designed for sharing short audio recordings, intended to function similarly to kind: 1 but specifically for voice content. This is currently in use for YakBak: https://yakbak.app

FEATURES command #1924

nostr:npub1gcxzte5zlkncx26j68ez60fzkvtkm9e0vrwdcvsjakxf9mu9qewqlfnj5z is proposing a new NIP that adds a command message to let Clients know which features are available on each relay and collect conventions for features and their labels. Instead of "negotiating" the connection, this model simply lets clients know what they can use at any point of time. More specifically, it currently allows clients to know when they can switch their regular EOSE-based filters for a Negentropy sync and when they can use COUNT.

LLM/AI Agents NIP #1929

nostr:npub17v7g49shev2lwp0uwrx5v88ad6hj970zfse74wkes9jguhkx7aqsgjwsvj is proposing a new proposal for standardized communication with LLM/AI Agents on the Nostr network that aims to enhance and supersede parts of NIP-90 by providing a more comprehensive and robust framework specifically tailored for AI agent interactions/transactions.This NIP seeks to foster a more interoperable and vibrant ecosystem for AI agents and services on Nostr, while addressing many of the valid arguments against NIP90 in its current state, e.g. 1903

Add NIP-XX: Donation Addresses in User Metadata #1934

nostr:npub1zmc6qyqdfnllhnzzxr5wpepfpnzcf8q6m3jdveflmgruqvd3qa9sjv7f60 is proposing a NIP that introduces standardized donation addresses in user metadata using w tags.The goal is to provide a consistent and interoperable way for users to share payment information across different Nostr clients. It supports multiple cryptocurrencies and networks, including BTC (on Bitcoin, Lightning, and Liquid), ETH, XMR, and USDT. The NIP also offers clear implementation guidelines to help clients integrate this feature seamlessly.

NIP-XX: Ride-hailing protocol on Nostr #1935

nostr:npub13a56exdeda7y44vtnrxr3ljaxh8q9kh04e73vzw8jl8rknuj7h7sst4t9m is proposing a NIP that defines a censorship-resistant, peer-to-peer ride-hailing and delivery protocol on Nostr. It leverages Nostr events, Bitcoin Lightning payments, and reputation mechanisms to create a decentralized alternative to Uber and other centralized transportation platforms.

Notable Projects

Coracle 0.6.16 nostr:npub13myx4j0pp9uenpjjq68wdvqzywuwxfj64welu28mdvaku222mjtqzqv3qk

Coracle 0.6.16 with some minor updates, * Add support for editing WOT feeds * Change default blossom servers * Add support for custom emojis * Fix note deduplication

Primal V2.2.20 nostr:npub12vkcxr0luzwp8e673v29eqjhrr7p9vqq8asav85swaepclllj09sylpugg

They released a new update focused on improving performance and stability across the app. Release 2.2.20 includes: * Feed rendering optimizations * Fix for Blossom uploader crash when uploading large files * Additional minor fixes and improvements

Zap.stream v0.7.0 nostr:npub1eaz6dwsnvwkha5sn5puwwyxjgy26uusundrm684lg3vw4ma5c2jsqarcgz

• Add show "copied to clipboard" message on iOS
• Add badge awards in chat feed
• Add badges assigned to users in chat
• Add share stream button on stream info modal
• Add timeout feature, timeout viewers for x seconds
• Fixed Auto raid redirect loop
• Fixed Always show open in wallet button

Nostur v1.21 nostr:npub1n0stur7q092gyverzc2wfc00e8egkrdnnqq3alhv7p072u89m5es5mk6h0

New in this version: * Support Follow Packs * Support Blossom servers (uploading and mirroring) * Post Preview for Picture-only posts * Audio-only bar * Drag unread counter anywhere, tap to go to next unread post * Show media info in iOS Now Playing control center

Fountain 1.2.2 nostr:npub1v5ufyh4lkeslgxxcclg8f0hzazhaw7rsrhvfquxzm2fk64c72hps45n0v5

Fountain 1.2.2 is live on iOS and Android This update contains a couple of bug fixes for playback issues that were reported in the last week or so.

Alby nostr:npub1getal6ykt05fsz5nqu4uld09nfj3y3qxmv8crys4aeut53unfvlqr80nfm

Alby Hub v1.17 Release * Sub-wallets — Fully redesigned and optimized * Auto-swaps between lightning & on-chain * On-chain TX list now on the node page * LDK upgrade for your integrated node

zap.store nostr:npub10r8xl2njyepcw2zwv3a6dyufj4e4ajx86hz6v4ehu4gnpupxxp7stjt2p8

zapstore-cli 0.2.0-rc1 released The biggest zapstore-cli release yet, with lots of improvements for publishing. * Support for signing with nsec, NIP-07 in the CLI, NIP-46 bunkers, as well as sending unsigned events to stdout for use with nak or any other signer * No longer depend on apktool (that annoyed so many Linux devs) or apksigner, no more shell calls * Upload to configurable Blossom servers * Simplified yet more powerful config file format * Much smarter extracting metadata * Overall way faster

RUNSTR v0.4.0 nostr:npub1vygzr642y6f8gxcjx6auaf2vd25lyzarpjkwx9kr4y752zy6058s8jvy4e

Streak Rewards * Base Reward: Earn 50 sats for every completed run over .5 miles * Streak Bonus: Unlock an additional 50 sat boost for each day your streak continues

Teams Enhancement * Group Chat: Communicate with your team members in real-time * Share achievements, plan group runs, and stay motivated together

NIP101h Integration * Caloric Data: Track calories burned during your activities * Workout Intensity: Monitor how hard you're pushing yourself * NIP-44 Encryption: Your fitness data stays private and secure

Performance Improvements and Small Upgrades * Graphene Optimizations: Faster loading times and smoother experience * Stricter Distance Filtering: More accurate run tracking and statistics * Code Refactoring: Cleaner codebase for better stability * Bug Fixes & UI Improvements: Various small enhancements

ZEUS v0.11.0 nostr:npub1xnf02f60r9v0e5kty33a404dm79zr7z2eepyrk5gsq3m7pwvsz2sazlpr5

ZEUS v0.11.0-alpha4 with Cashu support is now available for testing. * Feat: Automatic Cashu mint sweeping based on threshold * Feat: new Cashu seed format + BIP-39 export * Misc: UX enhancements + fixes * Cashu wallets are tied to Embedded LND wallets. Enable under Settings > Ecash * Other wallet types can still sweep funds from Cashu tokens * ZEUS Pay now supports Cashu address types. You can switch between Zaplocker, Cashu, and NWC mode but can only use one at a time. * Atomic swaps are not featured in this build.

KYCNOT.me nostr:npub188x98j0r7l2fszeph6j7hj99h8xl07n989pskk5zd69d2fcksetq5mgcqf

• UI/UX - designe a new logo and color palette for kycnot.me.
• Point system - The new point system provides more detailed information about the listings, and can be expanded to cover additional features across all services.
• ToS Scrapper: implement a powerful automated terms-of-service scrapper that collects all the ToS pages from the listings. It saves you from the hassle of reading the ToS by listing the lines that are suspiciously related to KYC/AML practices.
• Search bar - The new search bar allows you to easily filter services. It performs a full-text search on the Title, Description, Category, and Tags of all the services. Looking for VPN services? Just search for "vpn"!
• Transparency - To be more transparent, all discussions about services now take place publicly on GitLab. This ensures that all service-related matters are publicly accessible and recorded. Additionally, there's a real-time audits page that displays database changes.
• Listing Requests - upgrade the request system. The new form allows you to directly request services or points without any extra steps.
• Lightweight and fast - The new site is lighter and faster than its predecessor!
• Tor and I2P - At last! kycnot.me is now officially on Tor and I2P!

Shopstr v0.7.2 nostr:npub15dc33fyg3cpd9r58vlqge2hh8dy6hkkrjxkhluv2xpyfreqkmsesesyv6e

This update brings the following improvements and fixes: * Added loading indicators for image uploads and improved upload UX and validation * Added support for out-of-band fiat payment methods * Added improved onboarding flow * Fixed styling for onboarding flow * Fixed styling for 404 page

Sparrow nostr:npub1hea99yd4xt5tjx8jmjvpfz2g5v7nurdqw7ydwst0ww6vw520prnq6fg9v2

Sparrow v2.2.0 released with: * Recent Blocks view * Improved camera support * Dark mode improvements

Long-Form Content Eco

In the past two weeks, more than 359 long-form articles have been published, including over 130 articles on Bitcoin and more than 24 related to Nostr, accounting for 43% of the total content.

These articles about Nostr mainly explore the protocol’s growth, technical tools, and emerging use cases. Topics include relay challenges, LNbits integration via Nostr Wallet Connect, trust systems like NostrTrust, and self-managed NIP-05 identities. Several tools and apps—such as Primal for iOS, Satlantis, and Hostr—highlight client diversity and interoperability. Educational and social angles, including university engagement and long-form note-taking styles, show Nostr’s broader cultural impact.

These articles present a comprehensive picture of Bitcoin as a technology, asset, and cultural force. From beginner guides to advanced strategies, they explore how to buy, store, and use Bitcoin securely, including the adoption of multisig, Lightning Network, and self-custody practices. Many pieces highlight Bitcoin’s global impact—from everyday use in payments and savings, to its adoption by institutions and governments in Africa and Asia. The content delves into larger issues such as mining centralization, regulatory conflicts, and the geopolitical implications of de-dollarization. On the cultural side, Bitcoin is portrayed as a symbol of freedom, resistance, and long-term thinking, with movements like HODL and self-sovereign ownership gaining ground. Technological innovations and grassroots efforts are also driving Bitcoin’s integration with decentralized social platforms and smart contract frameworks.
Thank you, nostr:npub1jp3776ujdul56rfkkrv8rxxgrslqr07rz83xpmz3ndl74lg7ngys320eg2 nostr:npub1dk8z5f8pkrn2746xuhfk347a0g6fsxh20wk492fh9h8lkha2efxqgeq55a nostr:npub10vsdn82fps4vwjaqxcpwj0nyync0cfrp2f5qlayrljh6d549gx5s0y9eap nostr:npub186a9aaqmyp436j0gkxl8yswhat2ampahxunpmfjv80qwyaglywhqswhd06 nostr:npub1jrr9dlerex7tg8njvc88c60asxnf5dp8hgcerh0q8w3gdyurl48q6s5nwv nostr:npub150r0j29fypshg3xcl5gt5ew85gw8tg5qetzcawkapwcaa4z5jnaspwmwfg nostr:npub1zssx5e5cne75w4hxenry8x9qqmn9ql3ty4umlmewu7dqv6yhyh8survrwk nostr:npub1xncam2l8u5chg6w096v89f2q2l0lz4jz4n7q7tdjsu6y5t9qea7q2cmrua nostr:npub1harur8s4wmwzgrugwdmrd9gcv6zzfkzfmp36xu4tel0ces7j2uas3gcqdy nostr:npub10efcj7x65z2ak6vd69xr8f2hvqwuaqrhlygl3yqa4y63hfvc02mqwzaeh3 nostr:npub1sehqzwgg2k03t300l8gjj4znpqhsrg0mtaq2yk70qam2x65nxnjs9ul7fr nostr:npub12lg6yexfh0gsk8aupv5cr5fnj46l0kxg6lp6rz0zw6kwx603lmsshmac9c nostr:npub1guh5grefa7vkay4ps6udxg8lrqxg2kgr3qh9n4gduxut64nfxq0q9y6hjy nostr:npub1lpdect8qqg6u6se46ta22jqu4jn6jnsjzem36dejanjr95vshnlsxqcsgs nostr:npub1s4mv5rnj6cx64eurt5ucmtfnkp6qy65kh4wh799mdfk6ycslwd0qjrdu03 nostr:npub1h3kv6yar972dxetymty0t936p45utq7fj6p5rw7ly79jrafsnrjqvuwlmn and others, for your work. Enriching Nostr’s long-form content ecosystem is crucial.

Nostriches Global Meet Ups

Recently, several Nostr events have been hosted in different countries. * Recently, YakiHonne collaborated with the Nigerian Army College and kasu techies community to successfully host two Nostr Workshops, attracting over 70 enthusiastic participants. The events not only provided a comprehensive introduction to the Nostr ecosystem and Bitcoin payments but also offered hands-on experiences with decentralized technologies through the YakiHonne platform.
YakiHonne Global Pizza Fest officially kicked off on May 21, 2025, and will run through May 28.The event celebrates the evolution of Bitcoin by encouraging participants to buy pizza using sats, while promoting the concept of social payments.YakiHonne is offering up to 10,000 sats in pizza sponsorship for each participating community. Outstanding content may be featured in the official recap video and selected communities will be invited to join the Global Community Partner Program. * Bitcoin FilmFest 2025* officially kicked off on May 22 at Kinoteka Cinema in Warsaw, Poland, and will run through May 25.This international event brings together Bitcoin culture, independent cinema, and decentralized media under the theme "exploring the uncharted stories beyond the frame." YakiHonne is an official partner on site, sharing on open content networks and the future of social payments during our stage appearance.

Here is the upcoming Nostr event that you might want to check out. * The Bitcoin 2025 conference was held from May 26 to 29 at the Venetian Convention Center in Las Vegas, with the Nostr community hosting a series of vibrant activities.While the Nostr Lounge served as a central hub for socializing and technical exchange, featuring app demos, lightning talks, and limited-edition merchandise. Nostr also delivered two key presentations during the conference, focusing on multisig key management and the future of decentralized social media. * Africa Bitcoin Day – Kenya will take place on May 31st, 2025 (Saturday), from 2:00 PM to 6:00 PM at Nairobi Street Kitchen.Co-hosted by AfroBitcoinOrg and local communities, this event returns following the great success of last year. It will bring together developers, tech entrepreneurs, policymakers, and grassroots organizers to build, connect, and learn around Bitcoin and open technologies. * The 3rd Privacy Summit will take place on June 27, 2024, in Switzerland, bringing together leading figures and innovative projects from the global cryptography and privacy tech space.This edition will focus on on-chain privacy and cutting-edge cryptographic applications, featuring keynote talks, panel discussions, and in-depth community exchanges.The speaker lineup includes core developers, researchers, and founders from projects. * The Bitcoin Paradigm Program 2025 will take place from July 4 to July 5, 2025 (Friday to Saturday), under the theme "Bitcoin: Sovereignty, Energy, and Networks." This two-day event will explore Bitcoin’s relevance in modern society, focusing on its role in financial sovereignty, energy transformation, and decentralized network security. Speakers include

nostr:npub1renaud65zug8r570ndztde2xhk206z3v50a5mwa3kp2xshy3zmjqkqaw97 nostr:npub1admhd8e9r28zl4u73l95c7lmu8k233xn50ayjsruuc62hm7l2a2q2l5zht nostr:npub1nm44dsxxns2f6zquhk24dqzvlawdaf49jdpvvgnuuvy4aqc3r29qcwx73p nostr:npub158d7zqnl36ze3gmyv4kedezvla3z3rvgsfpap83drqrywswwvc8skw9kx0 and more.

Additionally, We warmly invite event organizers who have held recent activities to reach out to us so we can work together to promote the prosperity and development of the Nostr ecosystem.

Thanks for reading! If there’s anything I missed, feel free to reach out and help improve the completeness and accuracy of my coverage.

@ 21335073:a244b1ad

Please respect Virginia Giuffre’s memory by refraining from asking about the circumstances or theories surrounding her passing.

Since Virginia Giuffre’s death, I’ve reflected on what she would want me to say or do. This piece is my attempt to honor her legacy.

When I first spoke with Virginia, I was struck by her unshakable hope. I had grown cynical after years in the anti-human trafficking movement, worn down by a broken system and a government that often seemed complicit. But Virginia’s passion, creativity, and belief that survivors could be heard reignited something in me. She reminded me of my younger, more hopeful self. Instead of warning her about the challenges ahead, I let her dream big, unburdened by my own disillusionment. That conversation changed me for the better, and following her lead led to meaningful progress.

Virginia was one of the bravest people I’ve ever known. As a survivor of Epstein, Maxwell, and their co-conspirators, she risked everything to speak out, taking on some of the world’s most powerful figures.

She loved when I said, “Epstein isn’t the only Epstein.” This wasn’t just about one man—it was a call to hold all abusers accountable and to ensure survivors find hope and healing.

The Epstein case often gets reduced to sensational details about the elite, but that misses the bigger picture. Yes, we should be holding all of the co-conspirators accountable, we must listen to the survivors’ stories. Their experiences reveal how predators exploit vulnerabilities, offering lessons to prevent future victims.

You’re not powerless in this fight. Educate yourself about trafficking and abuse—online and offline—and take steps to protect those around you. Supporting survivors starts with small, meaningful actions. Free online resources can guide you in being a safe, supportive presence.

When high-profile accusations arise, resist snap judgments. Instead of dismissing survivors as “crazy,” pause to consider the trauma they may be navigating. Speaking out or coping with abuse is never easy. You don’t have to believe every claim, but you can refrain from attacking accusers online.

Society also fails at providing aftercare for survivors. The government, often part of the problem, won’t solve this. It’s up to us. Prevention is critical, but when abuse occurs, step up for your loved ones and community. Protect the vulnerable. it’s a challenging but a rewarding journey.

If you’re contributing to Nostr, you’re helping build a censorship resistant platform where survivors can share their stories freely, no matter how powerful their abusers are. Their voices can endure here, offering strength and hope to others. This gives me great hope for the future.

Virginia Giuffre’s courage was a gift to the world. It was an honor to know and serve her. She will be deeply missed. My hope is that her story inspires others to take on the powerful.

@ 1d7ff02a:d042b5be

ສຳລັບໃຜທີ່ຍັງບໍ່ເຂົ້າໃຈ Bitcoin ຢ່າງແທ້ຈິງ, ຫມາຍຄວາມວ່າເຈົ້າຍັງບໍ່ທັນເຂົ້າໃຈວ່າເງິນແມ່ນຫຍັງ, ໃຜເປັນຜູ້ສ້າງມັນ, ແລະເປັນຫຍັງມະນຸດຈຶ່ງຕ້ອງການເງິນ. ມັນເປັນເລື່ອງ scam ທີ່ລະບົບການສຶກສາບໍ່ໄດ້ສອນເລື່ອງສຳຄັນນີ້, ໃນຂະນະທີ່ພວກເຮົາໃຊ້ເວລາເກືອບທັງຊີວິດເພື່ອຫາເງິນ. ດັ່ງນັ້ນ, ຂໍແນະນຳໃຫ້ follow the money ແລະ ສຶກສາ Bitcoin ຢ່າງຈິງຈັງ.

Why Bitcoin Matters

Saving is the greatest discovery in human history

ກ່ອນທີ່ມະນຸດຈະຮຽນຮູ້ການເກັບອອມ, ພວກເຮົາເປັນພຽງແຕ່ສັດທີ່ມີຊີວິດຢູ່ແບບວັນຕໍ່ວັນ. ການປະຢັດແມ່ນສິ່ງທີ່ເຮັດໃຫ້ມະນຸດແຕກຕ່າງຈາກສັດອື່ນ — ຄວາມສາມາດໃນການຄິດກ່ຽວກັບອະນາຄົດ ແລະ ເກັບໄວ້ສຳລັບມື້ຫຼັງ.

Saving created civilization itself

ບໍ່ມີການເກັບອອມ, ບໍ່ມີການສ້າງເມືອງ, ບໍ່ມີວິທະຍາສາດ, ບໍ່ມີສິລະປະ. ທຸກສິ່ງທີ່ເຮົາເອີ້ນວ່າ "ຄວາມກ້າວໜ້າ" ແມ່ນມາຈາກຄວາມສາມາດໃນການຮູ້ຈັກເກັບອອມ.

Money is the greatest creation in human history

ມັນເປັນເຄື່ອງມືທີ່ເຮັດໃຫ້ອາລະຍະທຳມະນຸດກ້າວໜ້າມາເຖິງທຸກມື້ນີ້ ເງິນ ເປັນເຄື່ອງມືທີ່ດີທີ່ສຸດທີ່ມະນຸດໃຊ້ໃນການເກັບອອມ.

Bitcoin is the best money ever created

ມັນແມ່ນເງິນທີ່ສົມບູນແບບທີ່ສຸດທີ່ມະນຸດເຄີຍສ້າງຂຶ້ນມາ. ບໍ່ມີໃຜສາມາດ ຄວບຄຸມ, ຈັດການ, ທຳລາຍ ແລະ ມີຈຳກັດຢ່າງແທ້ຈິງ ຄືກັບເວລາໃນຊີວິດ.

Bitcoin ຄືກັບ black hole

ທີ່ຈະດູດເອົາມູນຄ່າທັງໝົດຈາກລະບົບການເງິນທີ່ເສຍຫາຍມັນຈະດູດເອົາຄວາມໝັ້ນຄົງແລະມູນຄ່າມາສູ່ຕົວມັນເອງ. ທຸກສິ່ງທີ່ມີມູນຄ່າຈະໄຫຼເຂົ້າສູ່ Bitcoin ໃນທີ່ສຸດ.

Bitcoin ຄືກັບສາດສະໜາພຸດທີ່ຄົ້ນພົບຄວາມຈິງ

ມັນເຮັດໃຫ້ເຂົ້າໃຈຕົ້ນຕໍບັນຫາຂອງລະບົບການເງິນປະຈຸບັນ ແລະ ເກີດເປັນບັນຫາຫລາຍໆຢ່າງໃນສັງຄົມ ດັ່ງກັບພະພຸດທະເຈົ້າທີ່ເຂົ້າໃຈທຸກ ແລະ ເຫດຂອງການເກີດທຸກ.

Bitcoin ຄືອິດສະຫຼະພາບ

ເງິນຄືອຳນາດ, ເງິນຄືສິ່ງຄວບຄຸມພຶດຕິກຳຂອງມະນຸດ ເມື່ອເຮົາມີເງິນທີ່ຮັກສາມູນຄ່າໄດ້ ແລະ ຄວບຄຸມບໍ່ໄດ້ ຈຶ່ງຈະມີຄວາມອິດສະຫຼະທາງຄວາມຄິດ, ການສະແດງອອກ, ແລະ ອຳນາດໃນການເລືອກ.

ຫນີ້ສິນທີ່ມະນຸດສ້າງຂຶ້ນໃນປະຈຸບັນນີ້ ໃຊ້ເວລາອີກພັນປີກໍ່ໄຊ້ຫນີ້ບໍ່ໝົດ

ມັນບໍ່ມີທາງອອກ ແລະ ກຳລັງມຸ່ງໜ້າສູ່ການລົ່ມສະລາຍຢ່າງຮ້າຍແຮງ. Bitcoin ຄືແສງສະຫວ່າງທີ່ຈະຊ່ວຍປ້ອງກັນບໍ່ໃຫ້ມະນຸດເຂົ້າສູ່ຍຸກມືດມົວອີກຄັ້ງ.

Bitcoin cannot steal your time

ມັນບໍ່ສາມາດຖືກສ້າງຂຶ້ນຈາກຄວາມຫວ່າງເປົ່າ. ທຸກ Bitcoin ຕ້ອງໃຊ້ພະລັງງານແລະເວລາທີ່ແທ້ຈິງໃນການສ້າງ.

Bitcoin ຄືປະກັນໄພທີ່ປ້ອງກັນການບໍລິຫານທີ່ຜິດພາດ

ມັນຊ່ວຍປ້ອງກັນຄວາມເສື່ອມໂຊມຂອງເງິນຕາ, ເສດຖະກິດທີ່ຕົກຕ່ຳ ແລະ ນະໂຍບາຍທີ່ຜິດພາດ, Bitcoin ຈະປົກປ້ອງຄຸນຄ່າຂອງເຈົ້າ.

Bitcoin is going to absorb the world's value

ໃນທີ່ສຸດ, Bitcoin ຈະກາຍເປັນທີ່ເກັບຮັກສາມູນຄ່າຂອງໂລກທັງໝົດ. ມັນຈະດູດເອົາຄວາມມັ່ງຄັ່ງຈາກທຸກຊັບສິນ, ທຸກລາຄາ, ແລະທຸກການລົງທຶນ.

Exit The Matrix

ພວກເຮົາອາໄສຢູ່ໃນ Matrix ທາງດ້ານການເງິນ. ທຸກໆມື້ພວກເຮົາຕື່ນຂຶ້ນມາແລະໄປເຮັດວຽກ, ຄິດວ່າເຮົາກຳລັງສ້າງອະນາຄົດໃຫ້ຕົວເອງ. ແຕ່ຄວາມຈິງແລ້ວ, ພວກເຮົາພຽງແຕ່ກຳລັງໃຫ້ພະລັງງານແກ່ລະບົບທີ່ຂູດເອົາຄຸນຄ່າຈາກພວກເຮົາທຸກວິນາທີ. Bitcoin is the red pill — ມັນຈະເປີດຕາໃຫ້ເຈົ້າເຫັນຄວາມຈິງຂອງໂລກການເງິນ. Central banks are the architects of this Matrix — ພວກເຂົາສ້າງເງິນຈາກຄວາມຫວ່າງເປົ່າ, ແລະພວກເຮົາຕ້ອງເຮັດວຽກໜັກເພື່ອໄດ້ມັນມາ.

ລະບົບການສຶກສາໄດ້ຫຼອກລວງເຮົາຢ່າງໃຫຍ່ຫຼວງ. ພວກເຂົາສອນໃຫ້ເຮົາເຮັດວຽກເພື່ອຫາເງິນ, ແຕ່ບໍ່ເຄີຍສອນວ່າເງິນແມ່ນຫຍັງ. ເຮົາໃຊ້ເວລາ 12-16 ປີໃນໂຮງຮຽນ, ຫຼັງຈາກນັ້ນໃຊ້ເວລາທັງຊີວິດເພື່ອຫາເງິນ, ແຕ່ບໍ່ເຄີຍຮູ້ຈັກວ່າມັນແມ່ນຫຍັງ, ໃຜສ້າງ, ແລະເປັນຫຍັງມັນມີຄຸນຄ່າ.This is the biggest scam in human history ພວກເຮົາຖືກສອນໃຫ້ເປັນທາດຂອງລະບົບ, ແຕ່ບໍ່ໄດ້ຮັບການສອນໃຫ້ເຂົ້າໃຈລະບົບ.

The Bitcoin standard will end war

ເມື່ອບໍ່ສາມາດພິມເງິນເພື່ອສົງຄາມແລ້ວ, ສົງຄາມຈະກາຍເປັນສິ່ງທີ່ແພງເກີນໄປ.

ພວກເຮົາກຳລັງເຂົ້າສູ່ຍຸກ Bitcoin Renaissance

ຍຸກແຫ່ງການຟື້ນຟູທາງດ້ານການເງິນແລະປັນຍາ. Bitcoin is creating a new class of humans ຄົນທີ່ເຂົ້າໃຈ ແລະ ຖື Bitcoin ຈະກາຍເປັນຊົນຊັ້ນໃໝ່ທີ່ມີອິດສະຫຼະພາບຢ່າງແທ້ຈິງ.

The Path to Financial Truth

Follow the money trail ແລະເຈົ້າຈະເຫັນຄວາມຈິງ:

• ໃຜຄວບຄຸມການພິມເງິນ?
• ເປັນຫຍັງລາຄາສິນຄ້າຂຶ້ນສູງຂຶ້ນເລື້ອຍໆ?
• ເປັນຫຍັງຄົນທຸກທຸກກວ່າເກົ່າ ແລະຄົນຮັ່ງມີຮັ່ງມີກວ່າເກົ່າ?

ຄຳຕອບທັງໝົດແມ່ນຢູ່ໃນການທຳຄວາມເຂົ້າໃຈເລື່ອງເງິນ ແລະ Bitcoin.

ການສຶກສາ Bitcoin ບໍ່ແມ່ນພຽງແຕ່ການລົງທຶນ — ມັນແມ່ນການເຂົ້າໃຈອະນາຄົດຂອງເງິນຕາ ແລະ ສັງຄົມມະນຸດ.

Don't just work for money. Understand money. Study Bitcoin.

ຖ້າເຈົ້າບໍ່ເຂົ້າໃຈເງິນ, ເຈົ້າຈະເປັນທາດຂອງລະບົບຕະຫຼອດໄປ. ຖ້າເຈົ້າເຂົ້າໃຈ Bitcoin, ເຈົ້າຈະໄດ້ຮັບອິດສະຫຼະພາບ.

@ 1d7ff02a:d042b5be

ກຸນແຈສຳຄັນແມ່ນການເຂົ້າໃຈວ່າແສງແດດບໍ່ແມ່ນສິ່ງດຽວ—ມັນແມ່ນຄື່ນຄວາມຖີ່ທີ່ສັບສົນທີ່ເຮັດວຽກຮ່ວມກັນຄືດັ່ງດົນຕີສຳລັບສຸຂະພາບຂອງມະນຸດ.

ວົງດົນຕີສຸຂະພາບຂອງດວງອາທິດ

ແສງຕອນເຊົ້າ (ແສງແດງ/ແສງອິນຟາເຣດໃກ້): ແສງແດງອ່ອນໂຍນຂອງຕອນແລງແລະຄຳ່ທີ່ປະກອບສ້າງ 90% ຂອງການປ່ອຍແສງຂອງດວງອາທິດ. ຄື່ນຄວາມຖີ່ນີ້ເຮັດໜ້າທີ່ຄືການປັບແຕ່ງເຊວລ໌, ເພີ່ມການຜະລິດພະລັງງານມີໂຕຄອນເດຍແລະກະກຽມຮ່າງກາຍຂອງທ່ານສຳລັບມື້ທີ່ຈະມາເຖິງ. ຄິດໃສ່ວ່າມັນແມ່ນການກະກຽມເຄື່ອງຈັກເຊວລ໌ຂອງທ່ານ.

ແສງຕອນກາງວັນ (ແສງ UV/ແສງສີຟ້າ): ແສງອາທິດທີ່ເຂັ້ມຂົ້ນຕອນກາງວັນສົ່ງມອບແສງອຸນຕາລະວິໂອເລດທີ່ຜະລິດວິຕາມິນ D—ຮໍໂມນທີ່ສຳຄັນຫຼາຍທີ່ເກືອບທຸກເຊວລ໌ໃນຮ່າງກາຍຂອງທ່ານມີຕົວຮັບສຳລັບມັນ. ເຖິງແມ່ນວ່າມັນຖືກເອີ້ນວ່າ "ວິຕາມິນ," ຮ່າງກາຍຂອງທ່ານຜະລິດວິຕາມິນ D ສ່ວນໃຫຍ່ຜ່ານການສຳຜັດຜິວໜັງກັບແສງ UVB. ນີ້ບໍ່ແມ່ນພຽງແຕ່ເລື່ອງສຸຂະພາບກະດູກ—ການຂາດວິຕາມິນ D ໄດ້ຖືກເຊື່ອມໂຍງກັບມະເຮັງ, ໂຣກພູມຄຸ້ມກັນຕົນເອງ, ໂຣກຫົວໃຈແລະເສັ້ນເລືອດ, ແລະການເພີ່ມຂຶ້ນຂອງການເສຍຊີວິດຈາກທຸກສາເຫດ. ວິຕາມິນ D ທີ່ຜະລິດຕາມທຳມະຊາດຈາກແສງແດດແກ່ຍາວ 2-3 ເທົ່າໃນຮ່າງກາຍຂອງທ່ານເມື່ອທຽບກັບຢາເສີມ, ສະແດງໃຫ້ເຫັນວ່າເປັນຫຍັງການສຳຜັດແສງແດດຕາມທຳມະຊາດຈຶ່ງດີກວ່າຢາເສີມ.

ແສງ UV ຍັງກະຕຸ້ນການຜະລິດເມລານິນ, ທີ່ເຮັດໜ້າທີ່ເປັນແບັດເຕີຣີທຳມະຊາດ, ເກັບຮັກສາອີເລັກຕຣອນທີ່ໃຫ້ພະລັງງານແກ່ມີໂຕຄອນເດຍຂອງທ່ານ. ໃນຂະນະທີ່ແສງສີຟ້າຮັບໃຊ້ຈຸດປະສົງຄູ່: ມັນຮັກສາໃຫ້ທ່ານຕື່ນຕົວໃນຕອນກາງວັນໃນຂະນະທີ່ຂັດຂວາງການຜະລິດເມລາໂທນິນ. ແຕ່ວ່າ, ແສງສີຟ້າມີດ້ານມືດ—ການສຶກສາສະແດງວ່າມັນສາມາດເຮັດໃຫ້ເກີດຄວາມເສຍຫາຍຂອງ DNA ແລະສ້າງສິ່ງທີ່ເປັນອັນຕະລາຍທີ່ເອີ້ນວ່າສະສາລະອົກຊິເຈນປະຕິກິລິຍາຢູ່ທັງຜິວໜັງແລະຕາ, ຄ້າຍຄືກັບລັງສີ UV. ນີ້ແມ່ນເຫດຜົນທີ່ການສຳຜັດແສງສີຟ້າໂດດດ່ຽວ (ເຊັ່ນຈາກໜ້າຈໍ) ໂດຍບໍ່ມີຄື່ນຄວາມຖີ່ປ້ອງກັນຂອງແສງອາທິດສາມາດເປັນອັນຕະລາຍໂດຍສະເພາະ.

ການປ່ຽນແປງຕອນແລງ: ເມື່ອແສງສີຟ້າຫຼຸດລົງໃນຕອນແລງ, ຮ່າງກາຍຂອງທ່ານເລີ່ມຜະລິດເມລາໂທນິນ, ທີມງານທຳຄວາມສະອາດເຊວລ໌ທີ່ເອົາຜະລິດຕະພັນພິດທີ່ສະສົມໃນລະຫວ່າງການຜະລິດພະລັງງານຂອງມື້ອອກ.

ວິກິດການແສງສະໄໝໃໝ່

ມະນຸດສະໄໝໃໝ່ໃຊ້ເວລາ 93% ຢູ່ໃນເຮືອນ, ສ້າງຄວາມບໍ່ສົມດູນຂອງແສງທີ່ເປັນອັນຕະລາຍ. ພວກເຮົາໄດ້ປ່ຽນໝໍ້ແສງໄຟແກ້ວທີ່ມີປະໂຫຍດດ້ວຍ LED ທີ່ຂາດຄື່ນຄວາມຖີ່ແສງອິນຟາເຣດໃກ້ທີ່ປ້ອງກັນ, ໃນຂະນະທີ່ແສງສີຟ້າປອມຈາກໜ້າຈໍຂັດຂວາງການຜະລິດເມລາໂທນິນຕາມທຳມະຊາດຂອງພວກເຮົາໃນຕອນກາງຄືນ. ນີ້ສ້າງພາຍຸທີ່ສົມບູນແບບ: ຄວາມເຄັ່ງຕຶງຈາກການເກີດອົກຊິເດຊັນໂດຍບໍ່ມີກົນໄກການທຳຄວາມສະອາດຕາມທຳມະຊາດ, ການຂາດວິຕາມິນ D, ແລະການຂາດຄື່ນຄວາມຖີ່ປ້ອງກັນຕອນເຊົ້າທີ່ກະກຽມຮ່າງກາຍຂອງພວກເຮົາສຳລັບການສຳຜັດແສງແດດ.

ທາງແກ້ໄຂຕາມທຳມະຊາດ

ການຄົ້ນຄວ້າຊີ້ໃຫ້ເຫັນວິທີການງ່າຍໆ: ຮັບເອົາຈັງຫວະຕາມທຳມະຊາດຂອງດວງອາທິດ. ເລີ່ມມື້ຂອງທ່ານດ້ວຍການສຳຜັດແສງຕອນເຊົ້າເພື່ອກະກຽມມີໂຕຄອນເດຍຂອງທ່ານ. ຍອມຮັບວ່າແສງແດດຕອນກາງວັນບາງຢ່າງໃຫ້ວິຕາມິນ D ແລະເມລານິນທີ່ຈຳເປັນ. ຄ່ອຍໆຜ່ອນຄາຍເມື່ອແສງແລງຫຼຸດລົງ, ອະນຸຍາດໃຫ້ມີການຜະລິດເມລາໂທນິນຕາມທຳມະຊາດ.

ຮ່າງກາຍຂອງທ່ານພັດທະນາມາຫຼາຍລ້ານປີກັບວົງຈອນແສງນີ້. ໃນຂະນະທີ່ພວກເຮົາບໍ່ສາມາດປະຖິ້ມຊີວິດທີ່ທັນສະໄໝໄດ້, ພວກເຮົາສາມາດເຄົາລົບຄວາມຕ້ອງການທາງຊີວະວິທະຍາຂອງພວກເຮົາສຳລັບແສງແດດແບບຄົບຖ້ວນ. ຫຼັງຈາກທັງໝົດ, ທຸກເຊວລ໌ໃນຮ່າງກາຍຂອງທ່ານແລ່ນດ້ວຍພະລັງງານ, ແລະດວງອາທິດຍັງຄົງເປັນແຫຼ່ງພະລັງງານຫຼັກຂອງໂລກພວກເຮົາ. ໃນໂລກເທັກໂນໂລຢີສູງຂອງພວກເຮົາ, ພວກເຮົາຕ້ອງຈື່ຄູ່ຮ່ວມງານບູຮານລະຫວ່າງສຸຂະພາບຂອງມະນຸດກໍຄືແສງແດດ.

@ c066aac5:6a41a034

I’m drawn to extremities in art. The louder, the bolder, the more outrageous, the better. Bold art takes me out of the mundane into a whole new world where anything and everything is possible. Having grown up in the safety of the suburban midwest, I was a bit of a rebellious soul in search of the satiation that only came from the consumption of the outrageous. My inclination to find bold art draws me to NOSTR, because I believe NOSTR can be the place where the next generation of artistic pioneers go to express themselves. I also believe that as much as we are able, were should invite them to come create here.

My Background: A Small Side Story

My father was a professional gamer in the 80s, back when there was no money or glory in the avocation. He did get a bit of spotlight though after the fact: in the mid 2000’s there were a few parties making documentaries about that era of gaming as well as current arcade events (namely 2007’sChasing GhostsandThe King of Kong: A Fistful of Quarters). As a result of these documentaries, there was a revival in the arcade gaming scene. My family attended events related to the documentaries or arcade gaming and I became exposed to a lot of things I wouldn’t have been able to find. The producer ofThe King of Kong: A Fistful of Quarters had previously made a documentary calledNew York Dollwhich was centered around the life of bassist Arthur Kane. My 12 year old mind was blown: The New York Dolls were a glam-punk sensation dressed in drag. The music was from another planet. Johnny Thunders’ guitar playing was like Chuck Berry with more distortion and less filter. Later on I got to meet the Galaga record holder at the time, Phil Day, in Ottumwa Iowa. Phil is an Australian man of high intellect and good taste. He exposed me to great creators such as Nick Cave & The Bad Seeds, Shakespeare, Lou Reed, artists who created things that I had previously found inconceivable.

I believe this time period informed my current tastes and interests, but regrettably I think it also put coals on the fire of rebellion within. I stopped taking my parents and siblings seriously, the Christian faith of my family (which I now hold dearly to) seemed like a mundane sham, and I felt I couldn’t fit in with most people because of my avant-garde tastes. So I write this with the caveat that there should be a way to encourage these tastes in children without letting them walk down the wrong path. There is nothing inherently wrong with bold art, but I’d advise parents to carefully find ways to cultivate their children’s tastes without completely shutting them down and pushing them away as a result. My parents were very loving and patient during this time; I thank God for that.

With that out of the way, lets dive in to some bold artists:

Nicolas Cage: Actor

There is an excellent video by Wisecrack on Nicolas Cage that explains him better than I will, which I will linkhere. Nicolas Cage rejects the idea that good acting is tied to mere realism; all of his larger than life acting decisions are deliberate choices. When that clicked for me, I immediately realized the man is a genius. He borrows from Kabuki and German Expressionism, art forms that rely on exaggeration to get the message across. He has even created his own acting style, which he calls Nouveau Shamanic. He augments his imagination to go from acting to being. Rather than using the old hat of method acting, he transports himself to a new world mentally. The projects he chooses to partake in are based on his own interests or what he considers would be a challenge (making a bad script good for example). Thus it doesn’t matter how the end result comes out; he has already achieved his goal as an artist. Because of this and because certain directors don’t know how to use his talents, he has a noticeable amount of duds in his filmography. Dig around the duds, you’ll find some pure gold. I’d personally recommend the filmsPig, Joe, Renfield, and his Christmas film The Family Man.

Nick Cave: Songwriter

What a wild career this man has had! From the apocalyptic mayhem of his band The Birthday Party to the pensive atmosphere of his albumGhosteen, it seems like Nick Cave has tried everything. I think his secret sauce is that he’s always working. He maintains an excellent newsletter calledThe Red Hand Files, he has written screenplays such asLawless, he has written books, he has made great film scores such asThe Assassination of Jesse James by the Coward Robert Ford, the man is religiously prolific. I believe that one of the reasons he is prolific is that he’s not afraid to experiment. If he has an idea, he follows it through to completion. From the albumMurder Ballads(which is comprised of what the title suggests) to his rejected sequel toGladiator(Gladiator: Christ Killer), he doesn’t seem to be afraid to take anything on. This has led to some over the top works as well as some deeply personal works. Albums likeSkeleton TreeandGhosteenwere journeys through the grief of his son’s death. The Boatman’s Callis arguably a better break-up album than anything Taylor Swift has put out. He’s not afraid to be outrageous, he’s not afraid to offend, but most importantly he’s not afraid to be himself. Works I’d recommend include The Birthday Party’sLive 1981-82, Nick Cave & The Bad Seeds’The Boatman’s Call, and the filmLawless.

Jim Jarmusch: Director

I consider Jim’s films to be bold almost in an ironic sense: his works are bold in that they are, for the most part, anti-sensational. He has a rule that if his screenplays are criticized for a lack of action, he makes them even less eventful. Even with sensational settings his films feel very close to reality, and they demonstrate the beauty of everyday life. That's what is bold about his art to me: making the sensational grounded in reality while making everyday reality all the more special. Ghost Dog: The Way of the Samurai is about a modern-day African-American hitman who strictly follows the rules of the ancient Samurai, yet one can resonate with the humanity of a seemingly absurd character. Only Lovers Left Aliveis a vampire love story, but in the middle of a vampire romance one can see their their own relationships in a new deeply human light. Jim’s work reminds me that art reflects life, and that there is sacred beauty in seemingly mundane everyday life. I personally recommend his filmsPaterson,Down by Law, andCoffee and Cigarettes.

NOSTR: We Need Bold Art

NOSTR is in my opinion a path to a better future. In a world creeping slowly towards everything apps, I hope that the protocol where the individual owns their data wins over everything else. I love freedom and sovereignty. If NOSTR is going to win the race of everything apps, we need more than Bitcoin content. We need more than shirtless bros paying for bananas in foreign countries and exercising with girls who have seductive accents. Common people cannot see themselves in such a world. NOSTR needs to catch the attention of everyday people. I don’t believe that this can be accomplished merely by introducing more broadly relevant content; people are searching for content that speaks to them. I believe that NOSTR can and should attract artists of all kinds because NOSTR is one of the few places on the internet where artists can express themselves fearlessly. Getting zaps from NOSTR’s value-for-value ecosystem has far less friction than crowdfunding a creative project or pitching investors that will irreversibly modify an artist’s vision. Having a place where one can post their works without fear of censorship should be extremely enticing. Having a place where one can connect with fellow humans directly as opposed to a sea of bots should seem like the obvious solution. If NOSTR can become a safe haven for artists to express themselves and spread their work, I believe that everyday people will follow. The banker whose stressful job weighs on them will suddenly find joy with an original meme made by a great visual comedian. The programmer for a healthcare company who is drowning in hopeless mundanity could suddenly find a new lust for life by hearing the song of a musician who isn’t afraid to crowdfund their their next project by putting their lighting address on the streets of the internet. The excel guru who loves independent film may find that NOSTR is the best way to support non corporate movies. My closing statement: continue to encourage the artists in your life as I’m sure you have been, but while you’re at it give them the purple pill. You may very well be a part of building a better future.

@ 52b4a076:e7fad8bd

I have been recently building NFDB, a new relay DB. This post is meant as a short overview.

Regular relays have challenges

Current relay software have significant challenges, which I have experienced when hosting Nostr.land: - Scalability is only supported by adding full replicas, which does not scale to large relays. - Most relays use slow databases and are not optimized for large scale usage. - Search is near-impossible to implement on standard relays. - Privacy features such as NIP-42 are lacking. - Regular DB maintenance tasks on normal relays require extended downtime. - Fault-tolerance is implemented, if any, using a load balancer, which is limited. - Personalization and advanced filtering is not possible. - Local caching is not supported.

NFDB: A scalable database for large relays

NFDB is a new database meant for medium-large scale relays, built on FoundationDB that provides: - Near-unlimited scalability - Extended fault tolerance - Instant loading - Better search - Better personalization - and more.

Search

NFDB has extended search capabilities including: - Semantic search: Search for meaning, not words. - Interest-based search: Highlight content you care about. - Multi-faceted queries: Easily filter by topic, author group, keywords, and more at the same time. - Wide support for event kinds, including users, articles, etc.

Personalization

NFDB allows significant personalization: - Customized algorithms: Be your own algorithm. - Spam filtering: Filter content to your WoT, and use advanced spam filters. - Topic mutes: Mute topics, not keywords. - Media filtering: With Nostr.build, you will be able to filter NSFW and other content - Low data mode: Block notes that use high amounts of cellular data. - and more

Other

NFDB has support for many other features such as: - NIP-42: Protect your privacy with private drafts and DMs - Microrelays: Easily deploy your own personal microrelay - Containers: Dedicated, fast storage for discoverability events such as relay lists

Calcite: A local microrelay database

Calcite is a lightweight, local version of NFDB that is meant for microrelays and caching, meant for thousands of personal microrelays.

Calcite HA is an additional layer that allows live migration and relay failover in under 30 seconds, providing higher availability compared to current relays with greater simplicity. Calcite HA is enabled in all Calcite deployments.

For zero-downtime, NFDB is recommended.

Noswhere SmartCache

Relays are fixed in one location, but users can be anywhere.

Noswhere SmartCache is a CDN for relays that dynamically caches data on edge servers closest to you, allowing: - Multiple regions around the world - Improved throughput and performance - Faster loading times

routerd

routerd is a custom load-balancer optimized for Nostr relays, integrated with SmartCache.

routerd is specifically integrated with NFDB and Calcite HA to provide fast failover and high performance.

Ending notes

NFDB is planned to be deployed to Nostr.land in the coming weeks.

A lot more is to come. 👀️️️️️️

@ 8947a945:9bfcf626

Hello everyone on Nostr and all my watchersand followersfrom DeviantArt, as well as those from other art platforms

I have been creating and sharing AI-generated anime girl fanart since the beginning of 2024 and have been running member-exclusive content on Patreon.

I also publish showcases of my artworks to Deviantart. I organically build up my audience from time to time. I consider it as one of my online businesses of art. Everything is slowly growing

On September 16, I received a DM from someone expressing interest in purchasing my art in NFT format and offering a very high price for each piece. We later continued the conversation via email.

Here’s a brief overview of what happened

• The first scammer selected the art they wanted to buy and offered a high price for each piece. They provided a URL to an NFT marketplace site running on the Ethereum (ETH) mainnet or ERC20. The site appeared suspicious, requiring email sign-up and linking a MetaMask wallet. However, I couldn't change the wallet address later. The minting gas fees were quite expensive, ranging from 0.15 to 0.2 ETH

• The scammers tried to convince me that the high profits would easily cover the minting gas fees, so I had nothing to lose. Luckily, I didn’t have spare funds to purchase ETH for the gas fees at the time, so I tried negotiating with them as follows:

• I offered to send them a lower-quality version of my art via email in exchange for the minting gas fees, but they refused.

• I offered them the option to pay in USD through Buy Me a Coffee shop here, but they refused.
• I offered them the option to pay via Bitcoin using the Lightning Network invoice , but they refused.
• I asked them to wait until I could secure the funds, and they agreed to wait.

The following week, a second scammer approached me with a similar offer, this time at an even higher price and through a different NFT marketplace website.

This second site also required email registration, and after navigating to the dashboard, it asked for a minting fee of 0.2 ETH. However, the site provided a wallet address for me instead of connecting a MetaMask wallet.

I told the second scammer that I was waiting to make a profit from the first sale, and they asked me to show them the first marketplace. They then warned me that the first site was a scam and even sent screenshots of victims, including one from OpenSea saying that Opensea is not paying.

This raised a red flag, and I began suspecting I might be getting scammed. On OpenSea, funds go directly to users' wallets after transactions, and OpenSea charges a much lower platform fee compared to the previous crypto bull run in 2020. Minting fees on OpenSea are also significantly cheaper, around 0.0001 ETH per transaction.

I also consulted with Thai NFT artist communities and the ex-chairman of the Thai Digital Asset Association. According to them, no one had reported similar issues, but they agreed it seemed like a scam.

After confirming my suspicions with my own research and consulting with the Thai crypto community, I decided to test the scammers’ intentions by doing the following

I minted the artwork they were interested in, set the price they offered, and listed it for sale on OpenSea. I then messaged them, letting them know the art was available and ready to purchase, with no royalty fees if they wanted to resell it.

They became upset and angry, insisting I mint the art on their chosen platform, claiming they had already funded their wallet to support me. When I asked for proof of their wallet address and transactions, they couldn't provide any evidence that they had enough funds.

Here’s what I want to warn all artists in the DeviantArt community or other platforms If you find yourself in a similar situation, be aware that scammers may be targeting you.

---

My Perspective why I Believe This is a Scam and What the Scammers Gain

From my experience with BTC and crypto since 2017, here's why I believe this situation is a scam, and what the scammers aim to achieve

First, looking at OpenSea, the largest NFT marketplace on the ERC20 network, they do not hold users' funds. Instead, funds from transactions go directly to users’ wallets. OpenSea’s platform fees are also much lower now compared to the crypto bull run in 2020. This alone raises suspicion about the legitimacy of other marketplaces requiring significantly higher fees.

I believe the scammers' tactic is to lure artists into paying these exorbitant minting fees, which go directly into the scammers' wallets. They convince the artists by promising to purchase the art at a higher price, making it seem like there's no risk involved. In reality, the artist has already lost by paying the minting fee, and no purchase is ever made.

In the world of Bitcoin (BTC), the principle is "Trust no one" and “Trustless finality of transactions” In other words, transactions are secure and final without needing trust in a third party.

In the world of Ethereum (ETH), the philosophy is "Code is law" where everything is governed by smart contracts deployed on the blockchain. These contracts are transparent, and even basic code can be read and understood. Promises made by people don’t override what the code says.

I also discuss this issue with art communities. Some people have strongly expressed to me that they want nothing to do with crypto as part of their art process. I completely respect that stance.

However, I believe it's wise to keep your eyes open, have some skin in the game, and not fall into scammers’ traps. Understanding the basics of crypto and NFTs can help protect you from these kinds of schemes.

If you found this article helpful, please share it with your fellow artists.

Until next time Take care

Note

• Both cyber security images are mine , I created and approved by AdobeStock to put on sale
• I'm working very hard to bring all my digital arts into Nostr to build my Sats business here to my another npub "HikariHarmony" npub1exdtszhpw3ep643p9z8pahkw8zw00xa9pesf0u4txyyfqvthwapqwh48sw

Link to my full gallery - Anime girl fanarts : HikariHarmony - HikariHarmony on Nostr - General art : KeshikiRakuen

@ 91bea5cd:1df4451c

O Contexto Legal Brasileiro e o Consentimento

No ordenamento jurídico brasileiro, o consentimento do ofendido pode, em certas circunstâncias, afastar a ilicitude de um ato que, sem ele, configuraria crime (como lesão corporal leve, prevista no Art. 129 do Código Penal). Contudo, o consentimento tem limites claros: não é válido para bens jurídicos indisponíveis, como a vida, e sua eficácia é questionável em casos de lesões corporais graves ou gravíssimas.

A prática de BDSM consensual situa-se em uma zona complexa. Em tese, se ambos os parceiros são adultos, capazes, e consentiram livre e informadamente nos atos praticados, sem que resultem em lesões graves permanentes ou risco de morte não consentido, não haveria crime. O desafio reside na comprovação desse consentimento, especialmente se uma das partes, posteriormente, o negar ou alegar coação.

A Lei Maria da Penha (Lei nº 11.340/2006)

A Lei Maria da Penha é um marco fundamental na proteção da mulher contra a violência doméstica e familiar. Ela estabelece mecanismos para coibir e prevenir tal violência, definindo suas formas (física, psicológica, sexual, patrimonial e moral) e prevendo medidas protetivas de urgência.

Embora essencial, a aplicação da lei em contextos de BDSM pode ser delicada. Uma alegação de violência por parte da mulher, mesmo que as lesões ou situações decorram de práticas consensuais, tende a receber atenção prioritária das autoridades, dada a presunção de vulnerabilidade estabelecida pela lei. Isso pode criar um cenário onde o parceiro masculino enfrenta dificuldades significativas em demonstrar a natureza consensual dos atos, especialmente se não houver provas robustas pré-constituídas.

Outros riscos:

Lesão corporal grave ou gravíssima (art. 129, §§ 1º e 2º, CP), não pode ser justificada pelo consentimento, podendo ensejar persecução penal.

Crimes contra a dignidade sexual (arts. 213 e seguintes do CP) são de ação pública incondicionada e independem de representação da vítima para a investigação e denúncia.

Riscos de Falsas Acusações e Alegação de Coação Futura

Os riscos para os praticantes de BDSM, especialmente para o parceiro que assume o papel dominante ou que inflige dor/restrição (frequentemente, mas não exclusivamente, o homem), podem surgir de diversas frentes:

1. Acusações Externas: Vizinhos, familiares ou amigos que desconhecem a natureza consensual do relacionamento podem interpretar sons, marcas ou comportamentos como sinais de abuso e denunciar às autoridades.
2. Alegações Futuras da Parceira: Em caso de término conturbado, vingança, arrependimento ou mudança de perspectiva, a parceira pode reinterpretar as práticas passadas como abuso e buscar reparação ou retaliação através de uma denúncia. A alegação pode ser de que o consentimento nunca existiu ou foi viciado.
3. Alegação de Coação: Uma das formas mais complexas de refutar é a alegação de que o consentimento foi obtido mediante coação (física, moral, psicológica ou econômica). A parceira pode alegar, por exemplo, que se sentia pressionada, intimidada ou dependente, e que seu "sim" não era genuíno. Provar a ausência de coação a posteriori é extremamente difícil.
4. Ingenuidade e Vulnerabilidade Masculina: Muitos homens, confiando na dinâmica consensual e na parceira, podem negligenciar a necessidade de precauções. A crença de que "isso nunca aconteceria comigo" ou a falta de conhecimento sobre as implicações legais e o peso processual de uma acusação no âmbito da Lei Maria da Penha podem deixá-los vulneráveis. A presença de marcas físicas, mesmo que consentidas, pode ser usada como evidência de agressão, invertendo o ônus da prova na prática, ainda que não na teoria jurídica.

Estratégias de Prevenção e Mitigação

Não existe um método infalível para evitar completamente o risco de uma falsa acusação, mas diversas medidas podem ser adotadas para construir um histórico de consentimento e reduzir vulnerabilidades:

1. Comunicação Explícita e Contínua: A base de qualquer prática BDSM segura é a comunicação constante. Negociar limites, desejos, palavras de segurança ("safewords") e expectativas antes, durante e depois das cenas é crucial. Manter registros dessas negociações (e-mails, mensagens, diários compartilhados) pode ser útil.

2. Documentação do Consentimento:

   • Contratos de Relacionamento/Cena: Embora a validade jurídica de "contratos BDSM" seja discutível no Brasil (não podem afastar normas de ordem pública), eles servem como forte evidência da intenção das partes, da negociação detalhada de limites e do consentimento informado. Devem ser claros, datados, assinados e, idealmente, reconhecidos em cartório (para prova de data e autenticidade das assinaturas).

   • Registros Audiovisuais: Gravar (com consentimento explícito para a gravação) discussões sobre consentimento e limites antes das cenas pode ser uma prova poderosa. Gravar as próprias cenas é mais complexo devido a questões de privacidade e potencial uso indevido, mas pode ser considerado em casos específicos, sempre com consentimento mútuo documentado para a gravação.

     Importante: a gravação deve ser com ciência da outra parte, para não configurar violação da intimidade (art. 5º, X, da Constituição Federal e art. 20 do Código Civil).

3. Testemunhas: Em alguns contextos de comunidade BDSM, a presença de terceiros de confiança durante negociações ou mesmo cenas pode servir como testemunho, embora isso possa alterar a dinâmica íntima do casal.

4. Estabelecimento Claro de Limites e Palavras de Segurança: Definir e respeitar rigorosamente os limites (o que é permitido, o que é proibido) e as palavras de segurança é fundamental. O desrespeito a uma palavra de segurança encerra o consentimento para aquele ato.
5. Avaliação Contínua do Consentimento: O consentimento não é um cheque em branco; ele deve ser entusiástico, contínuo e revogável a qualquer momento. Verificar o bem-estar do parceiro durante a cena ("check-ins") é essencial.
6. Discrição e Cuidado com Evidências Físicas: Ser discreto sobre a natureza do relacionamento pode evitar mal-entendidos externos. Após cenas que deixem marcas, é prudente que ambos os parceiros estejam cientes e de acordo, talvez documentando por fotos (com data) e uma nota sobre a consensualidade da prática que as gerou.
7. Aconselhamento Jurídico Preventivo: Consultar um advogado especializado em direito de família e criminal, com sensibilidade para dinâmicas de relacionamento alternativas, pode fornecer orientação personalizada sobre as melhores formas de documentar o consentimento e entender os riscos legais específicos.

Observações Importantes

• Nenhuma documentação substitui a necessidade de consentimento real, livre, informado e contínuo.
• A lei brasileira protege a "integridade física" e a "dignidade humana". Práticas que resultem em lesões graves ou que violem a dignidade de forma não consentida (ou com consentimento viciado) serão ilegais, independentemente de qualquer acordo prévio.
• Em caso de acusação, a existência de documentação robusta de consentimento não garante a absolvição, mas fortalece significativamente a defesa, ajudando a demonstrar a natureza consensual da relação e das práticas.

• A alegação de coação futura é particularmente difícil de prevenir apenas com documentos. Um histórico consistente de comunicação aberta (whatsapp/telegram/e-mails), respeito mútuo e ausência de dependência ou controle excessivo na relação pode ajudar a contextualizar a dinâmica como não coercitiva.

• Cuidado com Marcas Visíveis e Lesões Graves Práticas que resultam em hematomas severos ou lesões podem ser interpretadas como agressão, mesmo que consentidas. Evitar excessos protege não apenas a integridade física, mas também evita questionamentos legais futuros.

O que vem a ser consentimento viciado

No Direito, consentimento viciado é quando a pessoa concorda com algo, mas a vontade dela não é livre ou plena — ou seja, o consentimento existe formalmente, mas é defeituoso por alguma razão.

O Código Civil brasileiro (art. 138 a 165) define várias formas de vício de consentimento. As principais são:

Erro: A pessoa se engana sobre o que está consentindo. (Ex.: A pessoa acredita que vai participar de um jogo leve, mas na verdade é exposta a práticas pesadas.)

Dolo: A pessoa é enganada propositalmente para aceitar algo. (Ex.: Alguém mente sobre o que vai acontecer durante a prática.)

Coação: A pessoa é forçada ou ameaçada a consentir. (Ex.: "Se você não aceitar, eu termino com você" — pressão emocional forte pode ser vista como coação.)

Estado de perigo ou lesão: A pessoa aceita algo em situação de necessidade extrema ou abuso de sua vulnerabilidade. (Ex.: Alguém em situação emocional muito fragilizada é induzida a aceitar práticas que normalmente recusaria.)

No contexto de BDSM, isso é ainda mais delicado: Mesmo que a pessoa tenha "assinado" um contrato ou dito "sim", se depois ela alegar que seu consentimento foi dado sob medo, engano ou pressão psicológica, o consentimento pode ser considerado viciado — e, portanto, juridicamente inválido.

Isso tem duas implicações sérias:

1. O crime não se descaracteriza: Se houver vício, o consentimento é ignorado e a prática pode ser tratada como crime normal (lesão corporal, estupro, tortura, etc.).

2. A prova do consentimento precisa ser sólida: Mostrando que a pessoa estava informada, lúcida, livre e sem qualquer tipo de coação.

   Consentimento viciado é quando a pessoa concorda formalmente, mas de maneira enganada, forçada ou pressionada, tornando o consentimento inútil para efeitos jurídicos.

Conclusão

Casais que praticam BDSM consensual no Brasil navegam em um terreno que exige não apenas confiança mútua e comunicação excepcional, mas também uma consciência aguçada das complexidades legais e dos riscos de interpretações equivocadas ou acusações mal-intencionadas. Embora o BDSM seja uma expressão legítima da sexualidade humana, sua prática no Brasil exige responsabilidade redobrada. Ter provas claras de consentimento, manter a comunicação aberta e agir com prudência são formas eficazes de se proteger de falsas alegações e preservar a liberdade e a segurança de todos os envolvidos. Embora leis controversas como a Maria da Penha sejam "vitais" para a proteção contra a violência real, os praticantes de BDSM, e em particular os homens nesse contexto, devem adotar uma postura proativa e prudente para mitigar os riscos inerentes à potencial má interpretação ou instrumentalização dessas práticas e leis, garantindo que a expressão de sua consensualidade esteja resguardada na medida do possível.

---

Importante: No Brasil, mesmo com tudo isso, o Ministério Público pode denunciar por crime como lesão corporal grave, estupro ou tortura, independente de consentimento. Então a prudência nas práticas é fundamental.

Aviso Legal: Este artigo tem caráter meramente informativo e não constitui aconselhamento jurídico. As leis e interpretações podem mudar, e cada situação é única. Recomenda-se buscar orientação de um advogado qualificado para discutir casos específicos.

Se curtiu este artigo faça uma contribuição, se tiver algum ponto relevante para o artigo deixe seu comentário.

@ 6be5cc06:5259daf0

Introdução

Uma sociedade não deve ser construída sobre coerção, mas sim sobre associações voluntárias e interações espontâneas entre indivíduos. A sociedade de condomínios privados surge como uma alternativa natural ao modelo atual de centros urbanos, substituindo a imposição centralizada por estruturas baseadas em contratos e livre associação. Cada condomínio é uma unidade autônoma, gerida por aqueles que ali residem, onde os critérios de entrada, as regras internas e o comércio são definidos pelos próprios participantes. Essa estrutura permite que indivíduos se agrupem com base em valores compartilhados, eliminando os conflitos artificiais impostos por estados e legislações homogêneas que não respeitam a diversidade de preferências e estilos de vida.

O objetivo dessa sociedade é simples: permitir que as pessoas vivam de acordo com seus princípios sem interferência externa. Em um mundo onde a coerção estatal distorce incentivos, os condomínios privados oferecem uma alternativa onde a ordem surge do livre mercado e da cooperação voluntária. Os moradores escolhem seus vizinhos, definem suas próprias normas e interagem economicamente conforme suas necessidades e interesses. O modelo elimina a necessidade de um controle central, pois os incentivos derivados do livre mercado levam ao desenvolvimento de comunidades prósperas, onde a reputação e a confiança mútua são mais eficazes do que qualquer imposição estatal. Assim, essa sociedade representa a evolução lógica do conceito de liberdade individual e propriedade privada como pilares fundamentais da ordem social.

Público-Alvo e Identidade

Os condomínios privados refletem o princípio da livre associação, permitindo que indivíduos escolham viver em comunidades alinhadas com seus valores e necessidades sem interferência estatal. Cada condomínio possui uma identidade própria, moldada pelos moradores e seus interesses, criando ambientes onde afinidades culturais, filosóficas ou profissionais são preservadas e incentivadas. Enquanto alguns podem ser voltados para famílias numerosas, oferecendo amplos espaços e infraestrutura adequada, outros podem priorizar solteiros e jovens profissionais, com áreas de coworking e espaços de lazer voltados para networking e socialização. Da mesma forma, comunidades religiosas podem estabelecer seus próprios espaços de culto e eventos, enquanto condomínios para idosos podem ser projetados com acessibilidade e serviços médicos especializados.

Críticos podem afirmar que essa forma de organização resulta em pouca diversidade de habilidades e perspectivas, mas esse argumento ignora a dinâmica das interações humanas e o caráter evolutivo dos intercâmbios entre comunidades. Nenhum condomínio existe isolado; a troca entre diferentes comunidades ocorre naturalmente pelo mercado, incentivando o intercâmbio de conhecimento e serviços entre especialistas de diferentes áreas. Além disso, a ideia de que todos os grupos devem conter uma variedade aleatória de indivíduos desconsidera que a verdadeira diversidade nasce da liberdade de escolha, e não da imposição estatal de convivências forçadas.

Outra crítica possível é que a existência de critérios de entrada pode levar à segregação social. No entanto, essa preocupação deriva da concepção errônea de que todas as comunidades devem ser abertas e incluir qualquer pessoa indiscriminadamente. Porém, a liberdade de associação implica, necessariamente, a liberdade de exclusão. Se um grupo deseja manter determinada identidade cultural, religiosa ou profissional, isso não impede que outros grupos criem suas próprias comunidades conforme seus valores e recursos. Além disso, essa especialização leva a uma concorrência saudável entre condomínios, forçando-os a oferecer melhores condições para atrair moradores. Em vez de uma sociedade homogênea moldada por burocratas, temos um mosaico de comunidades autônomas, onde cada indivíduo pode encontrar ou criar o ambiente que melhor lhe convém.

Autossuficiência e Especialização

A força dos condomínios privados reside na capacidade de seus moradores de contribuírem ativamente para a comunidade, tornando-a funcional e autossuficiente sem a necessidade de intervenções estatais. Diferentes condomínios podem se especializar em áreas específicas ou ter diversos profissionais de diferentes setores, refletindo as competências e interesses de seus residentes. Essa descentralização do conhecimento e da produção permite que cada comunidade desenvolva soluções internas para suas demandas, reduzindo dependências externas e estimulando a prosperidade local.

Os moradores atuam como agentes econômicos, trocando bens e serviços dentro do próprio condomínio e entre diferentes comunidades. Um condomínio voltado para a saúde, por exemplo, pode contar com médicos, enfermeiros e terapeutas que oferecem consultas, aulas e assistência médica particular, remunerados diretamente por seus clientes, sem a intermediação de burocracias. Da mesma forma, um condomínio agrícola pode abrigar agricultores que cultivam alimentos orgânicos, compartilham técnicas de cultivo e comercializam excedentes com outros condomínios, garantindo um fluxo contínuo de suprimentos. Em um condomínio tecnológico, programadores, engenheiros e empreendedores desenvolvem soluções de TI, segurança digital e energia renovável, promovendo a inovação e ampliando as possibilidades de intercâmbio econômico.

A economia interna de cada condomínio se fortalece através de serviços oferecidos pelos próprios moradores. Professores podem ministrar aulas, técnicos podem prestar serviços de manutenção, artesãos podem vender seus produtos diretamente para os vizinhos. O mercado livre e voluntário é o principal regulador dessas interações, garantindo que a especialização surja naturalmente conforme a demanda e a oferta se ajustam. Essa estrutura elimina desperdícios comuns em sistemas centralizados, onde a alocação de recursos se dá por decisões políticas e não pelas necessidades reais da população.

Alguns argumentam que a especialização pode criar bolhas de conhecimento, tornando os condomínios excessivamente dependentes de trocas externas. Contudo, essa preocupação desconsidera a natureza espontânea do mercado, que incentiva a cooperação e o comércio entre comunidades distintas. Nenhum condomínio precisa produzir tudo internamente; ao contrário, a divisão do trabalho e a liberdade de escolha promovem interdependências saudáveis e vantajosas para todos. Assim, cada morador se insere em um ecossistema dinâmico, onde suas habilidades são valorizadas e sua autonomia preservada, sem coerções estatais ou distorções artificiais impostas por planejadores centrais.

Infraestrutura e Sustentabilidade

A solidez de uma sociedade baseada em condomínios privados depende de uma infraestrutura eficiente e sustentável, projetada para reduzir a dependência externa e garantir o máximo de autonomia. Sem um aparato estatal centralizador, cada comunidade deve estruturar seus próprios meios de obtenção de energia, água, alimentação e demais bens essenciais, garantindo que suas operações sejam viáveis a longo prazo. Essa abordagem, longe de ser um entrave, representa a verdadeira inovação descentralizada: um ambiente onde as soluções emergem da necessidade real e da engenhosidade humana, e não de diretrizes burocráticas e regulamentos ineficazes.

Cada condomínio pode investir em tecnologias sustentáveis e autônomas, como energia solar e eólica, reduzindo custos e minimizando a vulnerabilidade às flutuações do mercado energético tradicional. Sistemas de captação e filtragem de água da chuva, bem como a reutilização eficiente dos recursos hídricos, garantem independência em relação a empresas monopolistas e governos que frequentemente administram esse bem de forma ineficaz. Hortas comunitárias e fazendas verticais podem suprir grande parte da demanda alimentar, permitindo que cada condomínio mantenha sua própria reserva de alimentos, aumentando a resiliência contra crises externas e instabilidades de mercado.

Além dos recursos naturais, os espaços compartilhados desempenham um papel fundamental na integração e no fortalecimento dessas comunidades. Bibliotecas, ginásios, creches e salas de aula permitem que o conhecimento e os serviços circulem internamente, criando um ambiente onde a colaboração ocorre de maneira orgânica. A descentralização também se aplica ao uso da tecnologia, plataformas digitais privadas podem ser utilizadas para conectar moradores, facilitar a troca de serviços e produtos, além de coordenar agendamentos e eventos dentro dos condomínios e entre diferentes comunidades.

O Bitcoin surge como uma ferramenta indispensável nesse ecossistema, eliminando a necessidade de bancos estatais ou sistemas financeiros controlados. Ao permitir transações diretas, transparentes e resistentes à censura, o Bitcoin se torna o meio de troca ideal entre os condomínios, garantindo a preservação do valor e possibilitando um comércio ágil e eficiente. Além disso, contratos inteligentes e protocolos descentralizados podem ser integrados para administrar serviços comuns, fortalecer a segurança e reduzir a burocracia, tornando a governança desses condomínios cada vez mais autônoma e imune a intervenções externas.

Alguns podem argumentar que a falta de um aparato estatal para regulamentar a infraestrutura pode resultar em desigualdade no acesso a recursos essenciais, ou que a descentralização completa pode gerar caos e ineficiência. No entanto, essa visão ignora o fato de que a concorrência e a inovação no livre mercado são os maiores motores de desenvolvimento sustentável. Sem monopólios ou subsídios distorcendo a alocação de recursos, a busca por eficiência leva naturalmente à adoção de soluções melhores e mais acessíveis. Condomínios que oferecem infraestrutura de qualidade tendem a atrair mais moradores e investimentos, o que impulsiona a melhoria contínua e a diversificação dos serviços. Em vez de depender de um sistema centralizado falho, as comunidades se tornam responsáveis por sua própria prosperidade, criando uma estrutura sustentável, escalável e adaptável às mudanças do futuro.

Governança e Administração

Em uma sociedade descentralizada, não se deve depender de uma estrutura estatal ou centralizada para regular e tomar decisões em nome dos indivíduos. Cada condomínio, portanto, deve ser gerido de maneira autônoma, com processos claros de tomada de decisão, resolução de conflitos e administração das questões cotidianas. A gestão pode ser organizada por conselhos de moradores, associações ou sistemas de governança direta, conforme as necessidades locais.

Conselhos de Moradores e Processos de Tomada de Decisão

Em muitos casos, a administração interna de um condomínio privado pode ser realizada por um conselho de moradores, composto por representantes eleitos ou indicados pela própria comunidade. A ideia é garantir que as decisões importantes, como planejamento urbano, orçamento, manutenção e serviços, sejam feitas de forma transparente e que os interesses de todos os envolvidos sejam considerados. Isso não significa que a gestão precise ser completamente democrática, mas sim que as decisões devem ser tomadas de forma legítima, transparente e acordadas pela maior parte dos membros.

Em vez de um processo burocrático e centralizado, onde uma liderança impõe suas vontades sobre todos a muitas vezes suas decisões ruins não o afetam diretamente, a gestão de um condomínio privado deve ser orientada pela busca de consenso, onde os próprios gestores sofrerão as consequências de suas más escolhas. O processo de tomada de decisão pode ser dinâmico e direto, com os moradores discutindo e acordando soluções baseadas no mercado e nas necessidades locais, em vez de depender de um sistema impessoal de regulamentação. Além disso, a utilização de tecnologias descentralizadas, como plataformas de blockchain, pode proporcionar maior transparência nas decisões e maior confiança na gestão.

Resolução de Conflitos

A resolução de disputas dentro dos condomínios pode ocorrer de forma voluntária, através de negociação direta ou com o auxílio de mediadores escolhidos pelos próprios moradores por meio de um sistema de reputação. Em alguns casos, podem ser criados mecanismos para resolução de disputas mais formais, com árbitros ou juízes independentes que atuam sem vínculos com o condomínio. Esses árbitros podem ser escolhidos com base em sua experiência ou especialização em áreas como direito, mediação e resolução de conflitos, com uma reputação para zelar. Ao contrário de um sistema judicial centralizado, onde a parte envolvida depende do Estado para resolver disputas, os moradores possuem a autonomia para buscar soluções que atendam aos seus próprios interesses e necessidades. A diversidade de abordagens em um sistema de governança descentralizado cria oportunidades para inovações que atendem diferentes cenários, sem a interferência de burocratas distantes dos próprios problemas que estão "tentando resolver".

Planejamento Urbano e Arquitetura

A questão do design dos condomínios envolve não apenas a estética das construções, mas também a funcionalidade e a sustentabilidade a longo prazo. O planejamento urbano deve refletir as necessidades específicas da comunidade, onde ela decide por si mesma como construir e organizar seu ambiente.\ Arquitetos e urbanistas, muitas vezes moradores especializados, serão responsáveis pela concepção de espaços que atendam a esses critérios, criando ambientes agradáveis, com áreas para lazer, trabalho e convivência que atendam às diversas necessidades de cada grupo.\ Além disso, condomínios com nessecidades semelhantes poderão adotar ideias que deram certo em outros e certamente também dará no seu.

Segurança e Vigilância

Em relação à segurança, cada condomínio pode adotar sistemas de vigilância e proteção que atendam à sua realidade específica. Algumas comunidades podem optar por sistemas de câmeras de segurança, armamento pleno de seus moradores, patrulhamento privado ou até mesmo formas alternativas de garantir a proteção, como vigilância por meio de criptografia e monitoramento descentralizado. A chave para a segurança será a confiança mútua e a colaboração voluntária entre os moradores, que terão a liberdade de definir suas próprias medidas.

Comércio entre Condomínios

A troca de bens e serviços entre as diferentes comunidades é essencial para o funcionamento da rede. Como cada condomínio possui um grau de especialização ou uma mistura de profissionais em diversas áreas, a interdependência entre eles se torna crucial para suprir necessidades e promover a colaboração.

Embora alguns condomínios sejam especializados em áreas como saúde, agricultura ou tecnologia, outros podem ter um perfil mais diversificado, com moradores que atuam em diferentes campos de conhecimento. Por exemplo, um condomínio agrícola pode produzir alimentos orgânicos frescos, enquanto um condomínio de saúde oferece consultas médicas, terapias e cuidados especializados. Já um condomínio tecnológico pode fornecer inovações em software ou equipamentos de energia. Podem haver condomínios universitários que oferecem todo tipo de solução no campo de ensino. Ao mesmo tempo, um condomínio misto, com moradores de diversas áreas, pode oferecer uma variedade de serviços e produtos, tornando-se um centro de intercâmbio de diferentes tipos de expertise.

Essa divisão de trabalho, seja especializada ou diversificada, permite que os condomínios ofereçam o melhor de suas áreas de atuação, ao mesmo tempo em que atendem às demandas de outros. Um condomínio que não se especializa pode, por exemplo, buscar um acordo de troca com um condomínio agrícola para obter alimentos frescos ou com um condomínio tecnológico para adquirir soluções inovadoras.

Embora os condomínios busquem a autossuficiência, alguns recursos essenciais não podem ser produzidos internamente. Itens como minérios para construção, combustíveis ou até mesmo água, em regiões secas, não estão disponíveis em todas as áreas. A natureza não distribui os recursos de maneira uniforme, e a capacidade de produção local pode ser insuficiente para suprir todas as necessidades dos moradores. Isso implica que, para garantir a qualidade de vida e a continuidade das operações, os condomínios precisarão estabelecer relações comerciais e de fornecimento com fontes externas, seja através de mercados, importações ou parcerias com outras comunidades ou fornecedores fora do sistema de condomínios. O comércio intercondomínios e com o exterior será vital para a complementaridade das necessidades, assegurando que os moradores tenham acesso a tudo o que não pode ser produzido localmente.

O sistema econômico entre os condomínios pode ser flexível, permitindo o uso de uma moeda comum (como o Bitcoin) ou até mesmo um sistema de troca direta. Por exemplo, um morador de um condomínio misto pode oferecer serviços de design gráfico em troca de alimentos ou cuidados médicos. Esse tipo de colaboração estimula a produtividade e cria incentivos para que cada condomínio ofereça o melhor de seus recursos e habilidades, garantindo acesso aos bens e serviços necessários.

Relações Externas e Diplomacia

O isolamento excessivo pode limitar o acesso a inovações, avanços culturais e tecnológicos, e até mesmo dificultar o acesso a mercados externos. Por isso, é importante que haja canais de comunicação e métodos de diplomacia para interagir com outras comunidades. Os condomínios podem, por exemplo, estabelecer parcerias com outras regiões, seja para troca de produtos, serviços ou até para inovação. Isso garante que a rede de condomínios não se torne autossuficiente ao ponto de se desconectar do resto do mundo, o que pode resultar em estagnação.

Feiras, mercados intercondomínios e até eventos culturais e educacionais podem ser organizados para promover essas interações. A colaboração entre as comunidades e o exterior não precisa ser baseada em uma troca de dependência, mas sim numa rede de oportunidades que cria benefícios para todas as partes envolvidas. Uma boa reputação atrai novos moradores, pode valorizar propriedades e facilitar parcerias. A diplomacia entre as comunidades também pode ser exercida para resolver disputas ou desafios externos.

A manutenção de boas relações entre condomínios é essencial para garantir uma rede de apoio mútuo eficiente. Essas relações incentivam a troca de bens e serviços, como alimentos, assistência médica ou soluções tecnológicas, além de fortalecer a autossuficiência regional. Ao colaborar em segurança, infraestrutura compartilhada, eventos culturais e até mesmo na resolução de conflitos, os condomínios se tornam mais resilientes e eficientes, reduzindo a dependência externa e melhorando a qualidade de vida dos moradores. A cooperação contínua cria um ambiente mais seguro e harmonioso.

Educação e Desenvolvimento Humano

Cada comunidade pode criar escolas internas com currículos adaptados às especializações de seus moradores. Por exemplo, em um condomínio agrícola, podem ser ensinadas práticas agrícolas sustentáveis, e em um condomínio tecnológico, cursos de programação e inovação. Isso permite que crianças e jovens cresçam em ambientes que reforçam as competências valorizadas pela comunidade.

Além das escolas internas, o conceito de homeschooling pode ser incentivado, permitindo que os pais eduquem seus filhos conforme seus próprios valores e necessidades, com o apoio da comunidade. Esse modelo oferece uma educação mais flexível e personalizada, ao contrário do currículo tradicional oferecido pelo sistema público atual.

Os condomínios universitários também podem surgir, criando ambientes dedicados ao desenvolvimento acadêmico, científico e profissional, onde estudantes vivem e aprendem. Além disso, programas de capacitação contínua são essenciais, com oficinas e cursos oferecidos dentro do condomínio para garantir que os moradores se atualizem com novas tecnologias e práticas.

Para ampliar os horizontes educacionais, os intercâmbios estudantis entre diferentes condomínios podem ser incentivados. Esses intercâmbios não se limitam apenas ao ambiente educacional, mas também se estendem ao aprendizado de práticas de vida e habilidades técnicas. Os jovens de diferentes condomínios podem viajar para outras comunidades para estudar, trabalhar ou simplesmente trocar ideias. Isso pode ocorrer de diversas formas, como programas de curto e longo prazo, através de acordos entre os próprios condomínios, permitindo que os estudantes se conectem com outras comunidades, aprendam sobre diferentes especializações e desenvolvam uma compreensão mais ampla.

Essa abordagem descentralizada permite que cada comunidade desenvolva as competências essenciais sem depender de estruturas limitantes do estado ou sistemas educacionais centralizados. Ao proporcionar liberdade de escolha e personalização, os condomínios criam ambientes propícios ao crescimento humano, alinhados às necessidades e interesses de seus moradores.

---

A sociedade dos condomínios privados propõe uma estrutura alternativa de convivência onde as pessoas podem viver de acordo com seus próprios valores e necessidades. Esses condomínios oferecem um modelo de organização que desafia a centralização estatal, buscando criar comunidades adaptáveis e inovadoras. A liberdade garante que as habilidades necessárias para o sustento e crescimento das comunidades sejam mantidas ao longo do tempo.

A troca de bens, serviços e conhecimentos entre os condomínios, sem a imposição de forças externas, cria uma rede de boas relações, onde o comércio e a colaboração substituem a intervenção estatal. Em vez de depender de sistemas coercitivos, cada condomínio funciona como um microcosmo autônomo que, juntos, formam um ecossistema dinâmico e próspero. Este modelo propõe que, por meio de trocas voluntárias, possamos construir uma sociedade mais saudável. Lembre-se: Ideias e somente ideias podem iluminar a escuridão.

@ 40b9c85f:5e61b451

Introduction

Data Vending Machines (DVMs) have emerged as a crucial component of the Nostr ecosystem, offering specialized computational services to clients across the network. As defined in NIP-90, DVMs operate on an apparently simple principle: "data in, data out." They provide a marketplace for data processing where users request specific jobs (like text translation, content recommendation, or AI text generation)

While DVMs have gained significant traction, the current specification faces challenges that hinder widespread adoption and consistent implementation. This article explores some ideas on how we can apply the reflection pattern, a well established approach in RPC systems, to address these challenges and improve the DVM ecosystem's clarity, consistency, and usability.

The Current State of DVMs: Challenges and Limitations

The NIP-90 specification provides a broad framework for DVMs, but this flexibility has led to several issues:

1. Inconsistent Implementation

As noted by hzrd149 in "DVMs were a mistake" every DVM implementation tends to expect inputs in slightly different formats, even while ostensibly following the same specification. For example, a translation request DVM might expect an event ID in one particular format, while an LLM service could expect a "prompt" input that's not even specified in NIP-90.

2. Fragmented Specifications

The DVM specification reserves a range of event kinds (5000-6000), each meant for different types of computational jobs. While creating sub-specifications for each job type is being explored as a possible solution for clarity, in a decentralized and permissionless landscape like Nostr, relying solely on specification enforcement won't be effective for creating a healthy ecosystem. A more comprehensible approach is needed that works with, rather than against, the open nature of the protocol.

3. Ambiguous API Interfaces

There's no standardized way for clients to discover what parameters a specific DVM accepts, which are required versus optional, or what output format to expect. This creates uncertainty and forces developers to rely on documentation outside the protocol itself, if such documentation exists at all.

The Reflection Pattern: A Solution from RPC Systems

The reflection pattern in RPC systems offers a compelling solution to many of these challenges. At its core, reflection enables servers to provide metadata about their available services, methods, and data types at runtime, allowing clients to dynamically discover and interact with the server's API.

In established RPC frameworks like gRPC, reflection serves as a self-describing mechanism where services expose their interface definitions and requirements. In MCP reflection is used to expose the capabilities of the server, such as tools, resources, and prompts. Clients can learn about available capabilities without prior knowledge, and systems can adapt to changes without requiring rebuilds or redeployments. This standardized introspection creates a unified way to query service metadata, making tools like grpcurl possible without requiring precompiled stubs.

How Reflection Could Transform the DVM Specification

By incorporating reflection principles into the DVM specification, we could create a more coherent and predictable ecosystem. DVMs already implement some sort of reflection through the use of 'nip90params', which allow clients to discover some parameters, constraints, and features of the DVMs, such as whether they accept encryption, nutzaps, etc. However, this approach could be expanded to provide more comprehensive self-description capabilities.

1. Defined Lifecycle Phases

Similar to the Model Context Protocol (MCP), DVMs could benefit from a clear lifecycle consisting of an initialization phase and an operation phase. During initialization, the client and DVM would negotiate capabilities and exchange metadata, with the DVM providing a JSON schema containing its input requirements. nip-89 (or other) announcements can be used to bootstrap the discovery and negotiation process by providing the input schema directly. Then, during the operation phase, the client would interact with the DVM according to the negotiated schema and parameters.

2. Schema-Based Interactions

Rather than relying on rigid specifications for each job type, DVMs could self-advertise their schemas. This would allow clients to understand which parameters are required versus optional, what type validation should occur for inputs, what output formats to expect, and what payment flows are supported. By internalizing the input schema of the DVMs they wish to consume, clients gain clarity on how to interact effectively.

3. Capability Negotiation

Capability negotiation would enable DVMs to advertise their supported features, such as encryption methods, payment options, or specialized functionalities. This would allow clients to adjust their interaction approach based on the specific capabilities of each DVM they encounter.

Implementation Approach

While building DVMCP, I realized that the RPC reflection pattern used there could be beneficial for constructing DVMs in general. Since DVMs already follow an RPC style for their operation, and reflection is a natural extension of this approach, it could significantly enhance and clarify the DVM specification.

A reflection enhanced DVM protocol could work as follows: 1. Discovery: Clients discover DVMs through existing NIP-89 application handlers, input schemas could also be advertised in nip-89 announcements, making the second step unnecessary. 2. Schema Request: Clients request the DVM's input schema for the specific job type they're interested in 3. Validation: Clients validate their request against the provided schema before submission 4. Operation: The job proceeds through the standard NIP-90 flow, but with clearer expectations on both sides

Parallels with Other Protocols

This approach has proven successful in other contexts. The Model Context Protocol (MCP) implements a similar lifecycle with capability negotiation during initialization, allowing any client to communicate with any server as long as they adhere to the base protocol. MCP and DVM protocols share fundamental similarities, both aim to expose and consume computational resources through a JSON-RPC-like interface, albeit with specific differences.

gRPC's reflection service similarly allows clients to discover service definitions at runtime, enabling generic tools to work with any gRPC service without prior knowledge. In the REST API world, OpenAPI/Swagger specifications document interfaces in a way that makes them discoverable and testable.

DVMs would benefit from adopting these patterns while maintaining the decentralized, permissionless nature of Nostr.

Conclusion

I am not attempting to rewrite the DVM specification; rather, explore some ideas that could help the ecosystem improve incrementally, reducing fragmentation and making the ecosystem more comprehensible. By allowing DVMs to self describe their interfaces, we could maintain the flexibility that makes Nostr powerful while providing the structure needed for interoperability.

For developers building DVM clients or libraries, this approach would simplify consumption by providing clear expectations about inputs and outputs. For DVM operators, it would establish a standard way to communicate their service's requirements without relying on external documentation.

I am currently developing DVMCP following these patterns. Of course, DVMs and MCP servers have different details; MCP includes capabilities such as tools, resources, and prompts on the server side, as well as 'roots' and 'sampling' on the client side, creating a bidirectional way to consume capabilities. In contrast, DVMs typically function similarly to MCP tools, where you call a DVM with an input and receive an output, with each job type representing a different categorization of the work performed.

Without further ado, I hope this article has provided some insight into the potential benefits of applying the reflection pattern to the DVM specification.

@ 5d4b6c8d:8a1c1ee3

I did pretty poorly today. It's dreary and drizzly here, so I didn't get out walking. Even the dog didn't want to go out. We also had weirdly few chores or errands to do.

Maybe this was just a natural rest day. I did catch up on some sleep.

Foodwise, I kept my fast until reasonably late in the day, but then I ate a bunch of cookies. I'll need to do better tomorrow.

How'd everyone else do, today?

https://stacker.news/items/990061

@ e6817453:b0ac3c39

Hey folks, today we're diving into an exciting and emerging topic: personal artificial intelligence (PAI) and its connection to sovereignty, privacy, and ethics. With the rapid advancements in AI, there's a growing interest in the development of personal AI agents that can work on behalf of the user, acting autonomously and providing tailored services. However, as with any new technology, there are several critical factors that shape the future of PAI. Today, we'll explore three key pillars: privacy and ownership, explainability, and bias.

1. Privacy and Ownership: Foundations of Personal AI

At the heart of personal AI, much like self-sovereign identity (SSI), is the concept of ownership. For personal AI to be truly effective and valuable, users must own not only their data but also the computational power that drives these systems. This autonomy is essential for creating systems that respect the user's privacy and operate independently of large corporations.

In this context, privacy is more than just a feature—it's a fundamental right. Users should feel safe discussing sensitive topics with their AI, knowing that their data won’t be repurposed or misused by big tech companies. This level of control and data ownership ensures that users remain the sole beneficiaries of their information and computational resources, making privacy one of the core pillars of PAI.

2. Bias and Fairness: The Ethical Dilemma of LLMs

Most of today’s AI systems, including personal AI, rely heavily on large language models (LLMs). These models are trained on vast datasets that represent snapshots of the internet, but this introduces a critical ethical challenge: bias. The datasets used for training LLMs can be full of biases, misinformation, and viewpoints that may not align with a user’s personal values.

This leads to one of the major issues in AI ethics for personal AI—how do we ensure fairness and minimize bias in these systems? The training data that LLMs use can introduce perspectives that are not only unrepresentative but potentially harmful or unfair. As users of personal AI, we need systems that are free from such biases and can be tailored to our individual needs and ethical frameworks.

Unfortunately, training models that are truly unbiased and fair requires vast computational resources and significant investment. While large tech companies have the financial means to develop and train these models, individual users or smaller organizations typically do not. This limitation means that users often have to rely on pre-trained models, which may not fully align with their personal ethics or preferences. While fine-tuning models with personalized datasets can help, it's not a perfect solution, and bias remains a significant challenge.

3. Explainability: The Need for Transparency

One of the most frustrating aspects of modern AI is the lack of explainability. Many LLMs operate as "black boxes," meaning that while they provide answers or make decisions, it's often unclear how they arrived at those conclusions. For personal AI to be effective and trustworthy, it must be transparent. Users need to understand how the AI processes information, what data it relies on, and the reasoning behind its conclusions.

Explainability becomes even more critical when AI is used for complex decision-making, especially in areas that impact other people. If an AI is making recommendations, judgments, or decisions, it’s crucial for users to be able to trace the reasoning process behind those actions. Without this transparency, users may end up relying on AI systems that provide flawed or biased outcomes, potentially causing harm.

This lack of transparency is a major hurdle for personal AI development. Current LLMs, as mentioned earlier, are often opaque, making it difficult for users to trust their outputs fully. The explainability of AI systems will need to be improved significantly to ensure that personal AI can be trusted for important tasks.

Addressing the Ethical Landscape of Personal AI

As personal AI systems evolve, they will increasingly shape the ethical landscape of AI. We’ve already touched on the three core pillars—privacy and ownership, bias and fairness, and explainability. But there's more to consider, especially when looking at the broader implications of personal AI development.

Most current AI models, particularly those from big tech companies like Facebook, Google, or OpenAI, are closed systems. This means they are aligned with the goals and ethical frameworks of those companies, which may not always serve the best interests of individual users. Open models, such as Meta's LLaMA, offer more flexibility and control, allowing users to customize and refine the AI to better meet their personal needs. However, the challenge remains in training these models without significant financial and technical resources.

There’s also the temptation to use uncensored models that aren’t aligned with the values of large corporations, as they provide more freedom and flexibility. But in reality, models that are entirely unfiltered may introduce harmful or unethical content. It’s often better to work with aligned models that have had some of the more problematic biases removed, even if this limits some aspects of the system’s freedom.

The future of personal AI will undoubtedly involve a deeper exploration of these ethical questions. As AI becomes more integrated into our daily lives, the need for privacy, fairness, and transparency will only grow. And while we may not yet be able to train personal AI models from scratch, we can continue to shape and refine these systems through curated datasets and ongoing development.

Conclusion

In conclusion, personal AI represents an exciting new frontier, but one that must be navigated with care. Privacy, ownership, bias, and explainability are all essential pillars that will define the future of these systems. As we continue to develop personal AI, we must remain vigilant about the ethical challenges they pose, ensuring that they serve the best interests of users while remaining transparent, fair, and aligned with individual values.

If you have any thoughts or questions on this topic, feel free to reach out—I’d love to continue the conversation!

@ c6dc6b64:69dbbc15

1. Liebe beginnt nicht im Herzen, sondern im Zweifel – sie wächst dort, wo man bleibt, obwohl man fliehen will.
2. Herkunft ist kein Zuhause. Es ist der Ort, an dem man lernt, warum man gehen musste.
3. Wahrheit ist selten laut. Sie flüstert – meist dann, wenn niemand mehr zuhört.
4. Nähe ohne Ehrlichkeit ist nur ein getarnter Abstand.
5. Wer geliebt werden will, wie er ist, muss zuerst wissen, wer das überhaupt ist.
6. Ein Kind spielt nicht, um zu vergessen – es spielt, weil es noch nicht gelernt hat zu verdrängen.
7. Wir nennen es Familie. Aber manchmal ist es nur eine Geschichte, die keiner mehr zu Ende erzählen will.
8. Vertrauen stirbt nicht an Lügen, sondern am Schweigen zwischen ihnen.
9. Die Krone der Zukunft liegt oft auf den Schultern derer, die nie gefragt wurden, ob sie sie tragen wollen.
10. Jeder Versuch, das Chaos zu ordnen, ist ein Spiegelbild unserer Angst – nicht vor dem Zerfall, sondern vor dem, was wir ohne Ordnung wären.

@ c6dc6b64:69dbbc15

„Man muss noch Chaos in sich haben, um einen tanzenden Stern gebären zu können.“

– Friedrich Nietzsche

Der Mensch wächst nicht aus der Welt – er wird in sie geworfen, ohne Ursprung, ohne Auftrag, ohne Trost. Die Familie erscheint zuerst als Halt, doch sie ist oft der erste Spiegel, in dem man sich selbst nicht erkennt. Man nennt es Liebe, nennt es Bindung – aber vielleicht ist es nur die stille Einweisung in ein Gefängnis, dessen Mauern wie Umarmungen aussehen.

Das Kind als unbestechliche Gegenwart

Das Kind ist nicht die Fortsetzung des Selbst, sondern der Beweis, dass auch das Chaos Nachwuchs hat. Es lacht, weil es noch nicht weiß, was Lachen kostet. Es fragt nicht, weil es noch nicht weiß, dass Fragen selten Antworten finden. Und doch ist es das Kind, das die Ordnung zum Wanken bringt – nicht durch Widerstand, sondern durch seine unbestechliche Gegenwärtigkeit.

Freiheit als Abwesenheit von Rettung

Freiheit beginnt dort, wo man aufhört, sich retten zu lassen. Sie ist kein Zustand, sondern eine Haltung: die Weigerung, sich einer Bedeutung zu unterwerfen, die von außen kommt. Die Welt verlangt Funktion – das freie Leben verweigert sich der Funktion, nicht durch Aufstand, sondern durch Abwesenheit. Wer Sicherheit sucht, hat die Welt bereits verloren.

Die Wahrheit der Einsamkeit

Einsamkeit ist kein Unglück – sie ist der Boden, auf dem das Selbst sich überhaupt erst spüren kann. Sie ist nicht leer, sondern ungeteilt. Was fehlt, ist nicht ein anderer Mensch, sondern die Illusion, dass Nähe uns ganz machen könnte. In der Tiefe des Alleinseins offenbart sich nicht Mangel, sondern Klarheit.

Das Nichts – erkannt, nicht gefürchtet

Ein Kind stellt keine Fragen über das Nichts – es lebt in ihm, ohne es zu wissen. Der Erwachsene aber erkennt es, spürt es wie eine zweite Haut, die nicht abgelegt werden kann. Doch dieses Wissen ist keine Strafe. Es ist die Bedingung jeder echten Handlung. Wer das Nichts kennt, liebt nicht, um sich zu retten – sondern weil er weiß, dass nichts gerettet werden muss.

Alltag, Würde, Form

Ein Leben im Angesicht der Leere ist möglich. Nicht durch Verdrängung, sondern durch Durchschreiten. Die Rolle, die man spielt, wird erträglich, wenn man sie nicht mit Identität verwechselt. Die Arbeit, die man verrichtet, dient nicht mehr dem Fortschritt, sondern der Form – und vielleicht ist darin schon Würde genug.

Das Netz und das Nest

Familie kann ein Nest sein – oder ein Netz. Es hält, oder es hält fest. Doch auch das Netz kann Heimat sein, wenn man nicht mehr erwartet, darin zu fliegen. Ein Kind zu begleiten heißt nicht, ihm Wahrheit zu geben, sondern ihm Raum zu lassen, seine eigene zu verwerfen.

Raum statt Richtung

Freiheit ist kein Ziel, sondern ein Aufhören. Wer nichts mehr will, dem kann nichts genommen werden. Wer das Nichts annimmt, dem begegnet keine Leere mehr – sondern Raum. In diesem Raum entsteht das, was nicht geplant ist, nicht beherrscht und nicht gezählt: der Moment, das Staunen, die Stille zwischen zwei Gedanken. Vielleicht ist genau das genug.

Das Schöne im Erlaubten

Man kann leben mit dem Nichts – wenn man nicht mehr verlangt, dass es Sinn macht. Man kann Vater sein, Mutter, Freund, Fremder – ohne sich zu verlieren. Man kann lachen, weinen, müde sein – ohne Trost zu brauchen. Denn wer dem Nichts ins Auge gesehen hat, der weiß: Alles ist bedeutungslos. Und genau deshalb ist alles erlaubt. Und manchmal, ganz selten, auch: schön.

@ c6dc6b64:69dbbc15

„Die Tatsache, dass das Leben keinen Sinn hat, ist ein Grund zu leben – und zwar der einzige.“

– Emil Cioran

Der Mensch steht im Zentrum eines Raumes, der sich weigert, eine Mitte zu haben. Alles um ihn herum scheint geordnet, doch diese Ordnung ist ein leises Zittern vor dem Chaos, das jede Struktur unterwandert. Es gibt kein Versprechen, das nicht gebrochen wird, kein Licht, das nicht aus einer tieferen Dunkelheit geboren wird. So flackert die Existenz – ein schwankender Schein über einem Abgrund, der kein Echo zurückgibt.

Das Nichts – still und überall

Das Nichts ist nicht Abwesenheit. Es ist Gegenwart ohne Form. Es liegt nicht hinter den Dingen, sondern in ihnen – wie ein Geruch, der bleibt, wenn alle Türen geschlossen sind. Es ist der unsichtbare Kern der Welt, der Grund, warum jedes Wort in sich selbst zerfällt, jede Bewegung zu spät kommt, jeder Sinn sich verflüchtigt, sobald man ihn greifen will. Das Schweigen des Universums ist keine Antwort – es ist die endgültige Form der Gleichgültigkeit.

Leben im Schatten der Leere

Wer dem Nichts begegnet, verliert nicht die Hoffnung – er erkennt, dass es nie Hoffnung gab, nur das Bedürfnis danach. Die Leere ist kein Loch, das gefüllt werden will, sondern ein Zustand, der alles durchdringt. Man lebt nicht trotz des Nichts – man lebt im Nichts, als Ahnung, als Abdruck, als Fußspur im Staub eines Raums, den niemand betritt.

Melancholie als Aggregatzustand

Melancholie ist kein Gefühl, sondern ein Aggregatzustand des Bewusstseins, das zu viel gesehen hat, um noch zu glauben. Sie trägt kein Schwarz, sie schreit nicht. Sie fließt durch uns wie ein langsamer Strom, der die Farben der Dinge auswäscht. In ihr liegt kein Wunsch nach Erlösung, sondern nur das Wissen, dass selbst Erlösung eine weitere Form von Fessel wäre. Man kehrt nicht heim, man löst sich auf – langsam, leise, endgültig.

Zeit, Tod, Vergehen

Der Tod ist nicht der Feind des Lebens, sondern seine Form. Leben ist der Prozess des langsamen Verschwindens, und Sterben ist nur die letzte Geste einer Bewegung, die längst begonnen hat. Die Zeit nimmt nicht, sie löscht. Sie lässt zurück, was nicht mehr gefüllt werden kann: ein Umriss, eine Hülle, ein Bild ohne Substanz. Der Mensch verliert sich nicht am Ende, sondern in jedem Moment, den er durchschreitet.

Erinnerung als Fragment

Erinnerung ist kein Besitz, sondern eine Wunde. Was zurückblickt, blickt durch einen zerbrochenen Spiegel – jedes Fragment spiegelt etwas, aber nie das Ganze. Und wer sich darin sucht, findet nicht sich selbst, sondern die Lücken zwischen den Bildern. Vergangenheit ist nicht, was war, sondern das, was nie ganz war – und deshalb nie ganz vergeht.

Fremdheit als Wahrheit

Existenz ist ein Exil. Nicht von einem Ort, sondern von sich selbst. Man ist sich nicht nahe, man ist sich fremd – und in dieser Fremdheit liegt keine Tragik, sondern ein nüchterner Frieden. Die Einsamkeit ist kein Zustand, sondern die einzig mögliche Beziehung zur Welt. Alles andere ist Täuschung, ein letzter Versuch, das Unvereinbare zu versöhnen.

Der flüchtige Sinn

Sinn verflüchtigt sich mit jeder Geste, die ihn zu fassen sucht. Je näher man kommt, desto mehr löst er sich auf – wie Nebel vor der Hand. Was bleibt, ist das Bild der Suche selbst, eine Bewegung im Leeren. Man begreift nicht – man kreist. Und in diesem Kreis liegt der Kern der Erfahrung: nicht das Ziel, sondern die Auflösung aller Ziele.

Die letzte Freiheit

Die einzige Freiheit liegt nicht im Handeln, sondern im Entgleiten. Der Verzicht auf Bedeutung, auf Richtung, auf Rettung – das ist der erste Akt der Selbstermächtigung. Nicht laut, nicht kämpferisch, sondern als stilles Hinwegtreten aus dem Spiel. Dort beginnt das, was nicht mehr genommen werden kann: die Unabhängigkeit vom Verlangen.

Schönheit im Verlöschen

Nichts bleibt. Und gerade deshalb geschieht alles. Nicht um zu sein, sondern um zu vergehen. Und vielleicht liegt darin die letzte Schönheit – nicht im Bestehen, sondern im Verlöschen. In der Fähigkeit, in Ketten zu tanzen, wissend, dass jede Kette aus Licht besteht, das schon lange erloschen ist.

@ a7bbc310:fe7b7be3

I’ve been back from Morocco for just over a month and I’ve had some time to reflect. I started writing a day by day of what I did in my trip to Morocco but that was turning out a bit boring. I couldn’t do the trip justice. I thought I’d share some of my observations instead. I’d start by saying I was only there for 5 1/2 days. 5 days in Marrakesh and half day in Essaouira

You can feel the rich culture and history Morocco has such a rich culture and history. Influence of Romans, French, Arab, Berbers, Saharan and Nomadic tribes. You can see it in the architecture, taste it in the food and hear it in the language. The streets of Marrakesh had the smells of spices, perfumes and petrol. There is a synchronised dance between everyone that occupy the streets. People, motorbikes, donkeys, carts, all jostling for position but never seeming to collide into on another.

One thing that didn’t surprise me was the high level of craftsmanship and intricate designs on some of the buildings. I was told by a tour guide that some of the calligraphy could only be understood and read by the person who wrote it.

There seemed to be a sense of community, people stopping in the street to greet each other and say hello. What surprised me about this in Marrakesh most was that it happened in such a busy city. From my experience big cities are places that you go to get lost, ignored and don’t want to be found. Scene at the end of the movie Collateral comes to mind. You know the one where he’s riding on the subway alone after being shot.

A vendor tried to sell me a pendant, a symbol of the Berber tribe that meant ‘free man’. The symbol looks similar to the one for Sats 丰. I declined to purchase since I wasn’t educated enough on the Berbers to rep a symbol.

Couldn’t get over how much stuff there was for sale! And duplications of everything, rugs, shoes , handbags, jackets. Cold mornings and evenings, warm during the day. Everyone dressed like it was winter, even when it for warmer in the afternoon. It was a special trip. I’d definitely go back. Both to visit Marrakesh and other places.

@ f839fb67:5c930939

Relays

| Name | Address | Price (Sats/Year) | Status | | - | - | - | - | | stephen's aegis relay | wss://paid.relay.vanderwarker.family | 42069 | | | stephen's Outbox | wss://relay.vanderwarker.family | Just Me | | | stephen's Inbox | wss://haven.vanderwarker.family/inbox | WoT | | | stephen's DMs | wss://haven.vanderwarker.family/chat | WoT | | | VFam Data Relay | wss://data.relay.vanderwarker.family | 0 | | | VFam Bots Relay | wss://skeme.vanderwarker.family | Invite | | | VFGroups (NIP29) | wss://groups.vanderwarker.family | 0 | | | [TOR] My Phone Relay | ws://naswsosuewqxyf7ov7gr7igc4tq2rbtqoxxirwyhkbuns4lwc3iowwid.onion | 0 | Meh... |

---

My Pubkeys

| Name | hex | nprofile | | - | - | - | | Main | f839fb6714598a7233d09dbd42af82cc9781d0faa57474f1841af90b5c930939 | nprofile1qqs0sw0mvu29nznjx0gfm02z47pve9up6ra22ar57xzp47gttjfsjwgpramhxue69uhhyetvv9ujuanpdejx2unhv9exketj9enxzmtfd3us9mapfx | | Vanity (Backup) | 82f21be67353c0d68438003fe6e56a35e2a57c49e0899b368b5ca7aa8dde7c23 | nprofile1qqsg9usmuee48sxkssuqq0lxu44rtc4903y7pzvmx694efa23h08cgcpramhxue69uhhyetvv9ujuanpdejx2unhv9exketj9enxzmtfd3ussel49x | | VFStore | 6416f1e658ba00d42107b05ad9bf485c7e46698217e0c19f0dc2e125de3af0d0 | nprofile1qqsxg9h3uevt5qx5yyrmqkkehay9cljxdxpp0cxpnuxu9cf9mca0p5qpramhxue69uhhyetvv9ujuanpdejx2unhv9exketj9enxzmtfd3usaa8plu | | NostrSMS | 9be1b8315248eeb20f9d9ab2717d1750e4f27489eab1fa531d679dadd34c2f8d | nprofile1qqsfhcdcx9fy3m4jp7we4vn305t4pe8jwjy74v062vwk08dd6dxzlrgpramhxue69uhhyetvv9ujuanpdejx2unhv9exketj9enxzmtfd3us595d45 |

Bot Pubkeys

| Name | hex | nprofile | | - | - | - | | Unlocks Bot | 2e941ad17144e0a04d1b8c21c4a0dbc3fbcbb9d08ae622b5f9c85341fac7c2d0 | nprofile1qqsza9q669c5fc9qf5dccgwy5rdu877th8gg4e3zkhuus56pltru95qpramhxue69uhhx6m9d4jjuanpdejx2unhv9exketj9enxzmtfd3ust4kvak | | Step Counter | 9223d2faeb95853b4d224a184c69e1df16648d35067a88cdf947c631b57e3de7 | nprofile1qqsfyg7jlt4etpfmf53y5xzvd8sa79ny356sv75gehu50333k4lrmecpramhxue69uhhx6m9d4jjuanpdejx2unhv9exketj9enxzmtfd3ustswp3w |

---

"Personal Nostr Things"

[D] = Saves darkmode preferences over nostr
[A] = Auth over nostr
[B] = Beta (software)
[z] = zap enabled

• [DABz] Main Site
• [DAB] Contact Site
• [DAB] PGP Site
• [DAB] VFCA Site

---

Other Services (Hosted code)

• Blossom
  
• NostrCheck
  

---

Emojis Packs

• Minecraft
• nostr:naddr1qqy566twv43hyctxwsq37amnwvaz7tmjv4kxz7fwweskuer9wfmkzuntv4ezuenpd45kc7gzyrurn7m8z3vc5u3n6zwm6s40stxf0qwsl2jhga83ssd0jz6ujvynjqcyqqq82nsd0k5wp
• AIM
• nostr:naddr1qqxxz6tdv4kk7arfvdhkuucpramhxue69uhhyetvv9ujuanpdejx2unhv9exketj9enxzmtfd3usyg8c88akw9ze3fer85yah4p2lqkvj7qap749w360rpq6ly94eycf8ypsgqqqw48qe0j2yk
• Blobs
• nostr:naddr1qqz5ymr0vfesz8mhwden5te0wfjkccte9emxzmnyv4e8wctjddjhytnxv9kkjmreqgs0sw0mvu29nznjx0gfm02z47pve9up6ra22ar57xzp47gttjfsjwgrqsqqqa2wek4ukj
• FavEmojis
• nostr:naddr1qqy5vctkg4kk76nfwvq37amnwvaz7tmjv4kxz7fwweskuer9wfmkzuntv4ezuenpd45kc7gzyrurn7m8z3vc5u3n6zwm6s40stxf0qwsl2jhga83ssd0jz6ujvynjqcyqqq82nsf7sdwt
• Modern Family
• nostr:naddr1qqx56mmyv4exugzxv9kkjmreqy0hwumn8ghj7un9d3shjtnkv9hxgetjwashy6m9wghxvctdd9k8jq3qlqulkec5tx98yv7snk759tuzejtcr5865468fuvyrtuskhynpyusxpqqqp65ujlj36n
• nostriches (Amethyst collection)
• nostr:naddr1qq9xummnw3exjcmgv4esz8mhwden5te0wfjkccte9emxzmnyv4e8wctjddjhytnxv9kkjmreqgs0sw0mvu29nznjx0gfm02z47pve9up6ra22ar57xzp47gttjfsjwgrqsqqqa2w2sqg6w
• Pepe
• nostr:naddr1qqz9qetsv5q37amnwvaz7tmjv4kxz7fwweskuer9wfmkzuntv4ezuenpd45kc7gzyrurn7m8z3vc5u3n6zwm6s40stxf0qwsl2jhga83ssd0jz6ujvynjqcyqqq82ns85f6x7
• Minecraft Font
• nostr:naddr1qq8y66twv43hyctxwssyvmmwwsq37amnwvaz7tmjv4kxz7fwweskuer9wfmkzuntv4ezuenpd45kc7gzyrurn7m8z3vc5u3n6zwm6s40stxf0qwsl2jhga83ssd0jz6ujvynjqcyqqq82nsmzftgr
• Archer Font
• nostr:naddr1qq95zunrdpjhygzxdah8gqglwaehxw309aex2mrp0yh8vctwv3jhyampwf4k2u3wvesk66tv0ypzp7peldn3gkv2wgeap8dag2hc9nyhs8g04ft5wnccgxhepdwfxzfeqvzqqqr4fclkyxsh
• SMB Font
• nostr:naddr1qqv4xatsv4ezqntpwf5k7gzzwfhhg6r9wfejq3n0de6qz8mhwden5te0wfjkccte9emxzmnyv4e8wctjddjhytnxv9kkjmreqgs0sw0mvu29nznjx0gfm02z47pve9up6ra22ar57xzp47gttjfsjwgrqsqqqa2w0wqpuk

---

Git Over Nostr

• NostrSMS
• nostr:naddr1qqyxummnw3e8xmtnqy0hwumn8ghj7un9d3shjtnkv9hxgetjwashy6m9wghxvctdd9k8jqfrwaehxw309amk7apwwfjkccte9emxzmnyv4e8wctjddjhytnxv9kkjmreqyj8wumn8ghj7urpd9jzuun9d3shjtnkv9hxgetjwashy6m9wghxvctdd9k8jqg5waehxw309aex2mrp0yhxgctdw4eju6t0qyxhwumn8ghj7mn0wvhxcmmvqgs0sw0mvu29nznjx0gfm02z47pve9up6ra22ar57xzp47gttjfsjwgrqsqqqaueqp0epk
• nip51backup
• nostr:naddr1qq9ku6tsx5ckyctrdd6hqqglwaehxw309aex2mrp0yh8vctwv3jhyampwf4k2u3wvesk66tv0yqjxamnwvaz7tmhda6zuun9d3shjtnkv9hxgetjwashy6m9wghxvctdd9k8jqfywaehxw309acxz6ty9eex2mrp0yh8vctwv3jhyampwf4k2u3wvesk66tv0yq3gamnwvaz7tmjv4kxz7fwv3sk6atn9e5k7qgdwaehxw309ahx7uewd3hkcq3qlqulkec5tx98yv7snk759tuzejtcr5865468fuvyrtuskhynpyusxpqqqpmej4gtqs6
• bukkitstr
• nostr:naddr1qqykyattdd5hgum5wgq37amnwvaz7tmjv4kxz7fwweskuer9wfmkzuntv4ezuenpd45kc7gpydmhxue69uhhwmm59eex2mrp0yh8vctwv3jhyampwf4k2u3wvesk66tv0yqjgamnwvaz7tmsv95kgtnjv4kxz7fwweskuer9wfmkzuntv4ezuenpd45kc7gpz3mhxue69uhhyetvv9ujuerpd46hxtnfduqs6amnwvaz7tmwdaejumr0dspzp7peldn3gkv2wgeap8dag2hc9nyhs8g04ft5wnccgxhepdwfxzfeqvzqqqrhnyf6g0n2

---

Market Places

Please use Nostr Market or somthing simular, to view.

• VFStore
• nostr:naddr1qqjx2v34xe3kxvpn95cnqven956rwvpc95unscn9943kxet98q6nxde58p3ryqglwaehxw309aex2mrp0yh8vctwv3jhyampwf4k2u3wvesk66tv0yqjvamnwvaz7tmgv9mx2m3wweskuer9wfmkzuntv4ezuenpd45kc7f0da6hgcn00qqjgamnwvaz7tmsv95kgtnjv4kxz7fwweskuer9wfmkzuntv4ezuenpd45kc7gpydmhxue69uhhwmm59eex2mrp0yh8vctwv3jhyampwf4k2u3wvesk66tv0ypzqeqk78n93wsq6sss0vz6mxl5shr7ge5cy9lqcx0smshpyh0r4uxsqvzqqqr4gvlfm7gu

---

Badges

Created

• paidrelayvf
• nostr:naddr1qq9hqctfv3ex2mrp09mxvqglwaehxw309aex2mrp0yh8vctwv3jhyampwf4k2u3wvesk66tv0ypzp7peldn3gkv2wgeap8dag2hc9nyhs8g04ft5wnccgxhepdwfxzfeqvzqqqr48y85v3u3
• iPow
• nostr:naddr1qqzxj5r02uq37amnwvaz7tmjv4kxz7fwweskuer9wfmkzuntv4ezuenpd45kc7gzyrurn7m8z3vc5u3n6zwm6s40stxf0qwsl2jhga83ssd0jz6ujvynjqcyqqq82wgg02u0r
• codmaster
• nostr:naddr1qqykxmmyd4shxar9wgq37amnwvaz7tmjv4kxz7fwweskuer9wfmkzuntv4ezuenpd45kc7gzyrurn7m8z3vc5u3n6zwm6s40stxf0qwsl2jhga83ssd0jz6ujvynjqcyqqq82wgk3gm4g
• iMine
• nostr:naddr1qqzkjntfdejsz8mhwden5te0wfjkccte9emxzmnyv4e8wctjddjhytnxv9kkjmreqgs0sw0mvu29nznjx0gfm02z47pve9up6ra22ar57xzp47gttjfsjwgrqsqqqafed5s4x5

---

Clients I Use

• Amethyst
• nostr:naddr1qqxnzd3cx5urqv3nxymngdphqgsyvrp9u6p0mfur9dfdru3d853tx9mdjuhkphxuxgfwmryja7zsvhqrqsqqql8kavfpw3
• noStrudel
• nostr:naddr1qqxnzd3cxccrvd34xser2dpkqy28wumn8ghj7un9d3shjtnyv9kh2uewd9hsygpxdq27pjfppharynrvhg6h8v2taeya5ssf49zkl9yyu5gxe4qg55psgqqq0nmq5mza9n
• nostrsms
• nostr:naddr1qq9rzdejxcunxde4xymqz8mhwden5te0wfjkccte9emxzmnyv4e8wctjddjhytnxv9kkjmreqgsfhcdcx9fy3m4jp7we4vn305t4pe8jwjy74v062vwk08dd6dxzlrgrqsqqql8kjn33qm

---

Lists

• Fediverse
  • nostr:naddr1qvzqqqr4xqpzp7peldn3gkv2wgeap8dag2hc9nyhs8g04ft5wnccgxhepdwfxzfeqys8wumn8ghj7un9d3shjtnkv9hxgetjwashy6m9wghxvctdd9k8jtcqp9rx2erfwejhyum9j4g0xh
• AI
  • nostr:naddr1qvzqqqr4xypzp7peldn3gkv2wgeap8dag2hc9nyhs8g04ft5wnccgxhepdwfxzfeqys8wumn8ghj7un9d3shjtnkv9hxgetjwashy6m9wghxvctdd9k8jtcqqfq5j65twn7
• Asterisk Shenanigans
  • nostr:naddr1qvzqqqr4xypzp7peldn3gkv2wgeap8dag2hc9nyhs8g04ft5wnccgxhepdwfxzfeqys8wumn8ghj7un9d3shjtnkv9hxgetjwashy6m9wghxvctdd9k8jtcqz3qhxar9wf5hx6eq2d5x2mnpde5kwctwwvaxjuzz
• Minecraft Videos
  • nostr:naddr1qvzqqqr4xypzp7peldn3gkv2wgeap8dag2hc9nyhs8g04ft5wnccgxhepdwfxzfeqys8wumn8ghj7un9d3shjtnkv9hxgetjwashy6m9wghxvctdd9k8jtcqzpxkjmn9vdexzen5yptxjer9daesqrd8jk

@ e6817453:b0ac3c39

In the modern world of AI, managing vast amounts of data while keeping it relevant and accessible is a significant challenge, mainly when dealing with large language models (LLMs) and vector databases. One approach that has gained prominence in recent years is integrating vector search with metadata, especially in retrieval-augmented generation (RAG) pipelines. Vector search and metadata enable faster and more accurate data retrieval. However, the process of pre- and post-search filtering results plays a crucial role in ensuring data relevance.

The Vector Search and Metadata Challenge

In a typical vector search, you create embeddings from chunks of text, such as a PDF document. These embeddings allow the system to search for similar items and retrieve them based on relevance. The challenge, however, arises when you need to combine vector search results with structured metadata. For example, you may have timestamped text-based content and want to retrieve the most relevant content within a specific date range. This is where metadata becomes critical in refining search results.

Unfortunately, most vector databases treat metadata as a secondary feature, isolating it from the primary vector search process. As a result, handling queries that combine vectors and metadata can become a challenge, particularly when the search needs to account for a dynamic range of filters, such as dates or other structured data.

LibSQL and vector search metadata

LibSQL is a more general-purpose SQLite-based database that adds vector capabilities to regular data. Vectors are presented as blob columns of regular tables. It makes vector embeddings and metadata a first-class citizen that naturally builds deep integration of these data points.

create table if not exists conversation ( id varchar(36) primary key not null, startDate real, endDate real, summary text, vectorSummary F32_BLOB(512) );

It solves the challenge of metadata and vector search and eliminates impedance between vector data and regular structured data points in the same storage.

As you can see, you can access vector-like data and start date in the same query.

select c.id ,c.startDate, c.endDate, c.summary, vector_distance_cos(c.vectorSummary, vector(${vector})) distance from conversation where ${startDate ? `and c.startDate >= ${startDate.getTime()}` : ''} ${endDate ? `and c.endDate <= ${endDate.getTime()}` : ''} ${distance ? `and distance <= ${distance}` : ''} order by distance limit ${top};

vector_distance_cos calculated as distance allows us to make a primitive vector search that does a full scan and calculates distances on rows. We could optimize it with CTE and limit search and distance calculations to a much smaller subset of data.

This approach could be calculation intensive and fail on large amounts of data.

Libsql offers a way more effective vector search based on FlashDiskANN vector indexed.

vector_top_k('idx_conversation_vectorSummary', ${vector} , ${top}) i

vector_top_k is a table function that searches for the top of the newly created vector search index. As you can see, we could use only vector as a function parameter, and other columns could be used outside of the table function. So, to use a vector index together with different columns, we need to apply some strategies.

Now we get a classical problem of integration vector search results with metadata queries.

Post-Filtering: A Common Approach

The most widely adopted method in these pipelines is post-filtering. In this approach, the system first retrieves data based on vector similarities and then applies metadata filters. For example, imagine you’re conducting a vector search to retrieve conversations relevant to a specific question. Still, you also want to ensure these conversations occurred in the past week.

Post-filtering allows the system to retrieve the most relevant vector-based results and subsequently filter out any that don’t meet the metadata criteria, such as date range. This method is efficient when vector similarity is the primary factor driving the search, and metadata is only applied as a secondary filter.

const sqlQuery = ` select c.id ,c.startDate, c.endDate, c.summary, vector_distance_cos(c.vectorSummary, vector(${vector})) distance from vector_top_k('idx_conversation_vectorSummary', ${vector} , ${top}) i inner join conversation c on i.id = c.rowid where ${startDate ? `and c.startDate >= ${startDate.getTime()}` : ''} ${endDate ? `and c.endDate <= ${endDate.getTime()}` : ''} ${distance ? `and distance <= ${distance}` : ''} order by distance limit ${top};

However, there are some limitations. For example, the initial vector search may yield fewer results or omit some relevant data before applying the metadata filter. If the search window is narrow enough, this can lead to complete results.

One working strategy is to make the top value in vector_top_K much bigger. Be careful, though, as the function's default max number of results is around 200 rows.

Pre-Filtering: A More Complex Approach

Pre-filtering is a more intricate approach but can be more effective in some instances. In pre-filtering, metadata is used as the primary filter before vector search takes place. This means that only data that meets the metadata criteria is passed into the vector search process, limiting the scope of the search right from the beginning.

While this approach can significantly reduce the amount of irrelevant data in the final results, it comes with its own challenges. For example, pre-filtering requires a deeper understanding of the data structure and may necessitate denormalizing the data or creating separate pre-filtered tables. This can be resource-intensive and, in some cases, impractical for dynamic metadata like date ranges.

In certain use cases, pre-filtering might outperform post-filtering. For instance, when the metadata (e.g., specific date ranges) is the most important filter, pre-filtering ensures the search is conducted only on the most relevant data.

Pre-filtering with distance-based filtering

So, we are getting back to an old concept. We do prefiltering instead of using a vector index.

WITH FilteredDates AS ( SELECT c.id, c.startDate, c.endDate, c.summary, c.vectorSummary FROM YourTable c WHERE ${startDate ? `AND c.startDate >= ${startDate.getTime()}` : ''} ${endDate ? `AND c.endDate <= ${endDate.getTime()}` : ''} ), DistanceCalculation AS ( SELECT fd.id, fd.startDate, fd.endDate, fd.summary, fd.vectorSummary, vector_distance_cos(fd.vectorSummary, vector(${vector})) AS distance FROM FilteredDates fd ) SELECT dc.id, dc.startDate, dc.endDate, dc.summary, dc.distance FROM DistanceCalculation dc WHERE 1=1 ${distance ? `AND dc.distance <= ${distance}` : ''} ORDER BY dc.distance LIMIT ${top};

It makes sense if the filter produces small data and distance calculation happens on the smaller data set.

As a pro of this approach, you have full control over the data and get all results without omitting some typical values for extensive index searches.

Choosing Between Pre and Post-Filtering

Both pre-filtering and post-filtering have their advantages and disadvantages. Post-filtering is more accessible to implement, especially when vector similarity is the primary search factor, but it can lead to incomplete results. Pre-filtering, on the other hand, can yield more accurate results but requires more complex data handling and optimization.

In practice, many systems combine both strategies, depending on the query. For example, they might start with a broad pre-filtering based on metadata (like date ranges) and then apply a more targeted vector search with post-filtering to refine the results further.

Conclusion

Vector search with metadata filtering offers a powerful approach for handling large-scale data retrieval in LLMs and RAG pipelines. Whether you choose pre-filtering or post-filtering—or a combination of both—depends on your application's specific requirements. As vector databases continue to evolve, future innovations that combine these two approaches more seamlessly will help improve data relevance and retrieval efficiency further.

@ 502ab02a:a2860397

เราค่อยๆลำดับเรื่องราวเริ่มจากเบาๆกันก่อนนะครับ หากย้อนกลับไปในปี 2009 บนเส้นทางที่โลกกำลังสับสนระหว่างการกินที่อิงธรรมชาติกับแนวทางการเปลี่ยนแปลงอาหารแบบสุดขั้ว Ethan Brown ได้ก่อตั้งบริษัท Beyond Meat ขึ้นมา โดยมีจุดประสงค์ชัดเจนว่าอยากสร้าง "เนื้อจากพืช" ให้มีรสชาติ เนื้อสัมผัส และประสบการณ์ที่ใกล้เคียงกับเนื้อสัตว์จริงให้มากที่สุดเท่าที่จะทำได้ นี่คือภาพลวงตาที่ถูกสร้างขึ้นภายใต้ธงของความยั่งยืน แต่เบื้องลึกกลับแฝงความเงียบงันอยู่ใต้เงาเทคโนโลยี

Ethan Brown ไม่ใช่คนที่ตื่นเช้ามาแล้วอยากเปลี่ยนโลกในทันที เขาเติบโตมากับพ่อที่เป็นนักอนุรักษ์ธรรมชาติ มีฟาร์มโคนมเล็ก ๆ ให้ได้สัมผัสความจริงของเกษตรกรรมแบบดั้งเดิม เขาเรียนจบปริญญาตรีด้านประวัติศาสตร์และรัฐบาล ต่อด้วยปริญญาโทด้านนโยบายสาธารณะจาก University of Maryland และ MBA จาก Columbia University เขาเคยทำงานด้านนโยบายพลังงานทางเลือกที่ National Governors Association และบริษัท Ballard Power Systems ก่อนจะย้ายขั้วจากพลังงานสู่โปรตีนแทน

ช่วงหนึ่งเขาพูดใน TED ว่า “ผมมองเห็นว่าอาหารนั้นเชื่อมโยงกับสิ่งแวดล้อมและสุขภาพมนุษย์อย่างลึกซึ้ง แต่เราแทบไม่พูดถึงเรื่องนี้ในระดับระบบเลย” เขาเห็นว่าสัตว์คือ “เครื่องจักรแปลงโปรตีนจากพืชไปเป็นเนื้อ” ซึ่งเขาเชื่อว่ามัน “ไม่จำเป็นอีกต่อไปแล้ว” ในศตวรรษที่ 21

Beyond Meat ไม่ได้ใช้สูตรการต้มถั่วแล้วปั้นเป็นเบอร์เกอร์แบบบ้าน ๆ แต่ใช้กระบวนการแปรรูปที่ซับซ้อนระดับอุตสาหกรรมที่เรียกว่า High Moisture Extrusion (HME) ที่ต้องใช้เครื่องจักรเฉพาะราคาแพงมาก เพื่อดัดแปลงโปรตีนพืช เช่น ถั่วเหลือง ถั่วลันเตา ให้มีโครงสร้างเหมือนกล้ามเนื้อสัตว์ ทั้งเส้นใย ความชุ่มฉ่ำ และแรงต้านเมื่อกัด ซึ่งทั้งหมดนี้ไม่สามารถทำในครัวชาวบ้านได้ง่าย ๆ

บริษัทได้รับทุนสนับสนุนตั้งแต่ช่วงเริ่มต้นจากกลุ่มนักลงทุนที่มีอิทธิพลใน Silicon Valley เช่น Kleiner Perkins และ Obvious Corporation ของ Evan Williams ผู้ร่วมก่อตั้ง Twitter ก่อนจะขยายฐานนักลงทุนไปยัง Tyson Foods (ซึ่งเป็นบริษัทยักษ์ใหญ่ด้านเนื้อสัตว์ของสหรัฐฯ ที่ลงทุนใน Beyond Meat ก่อนจะถอนตัวภายหลัง) และนักแสดงฮอลลีวูดอย่าง Leonardo DiCaprio การเข้าระดมทุนในตลาดหุ้น (IPO) ปี 2019 ก็ยิ่งสร้างกระแสให้บริษัทกลายเป็นภาพตัวแทนของการกินอนาคตที่ยั่งยืน ทว่าในความหรูหรานั้น มีรอยร้าวแฝงอยู่เสมอ

ในขณะที่ภาพจำของ Beyond Meat ถูกวาดว่าเป็น “ทางรอดของโลก” และ “อาหารเพื่อสิ่งแวดล้อม” รัฐบาลสหรัฐฯ ก็สนับสนุนทิศทางนี้อย่างเงียบเชียบ ด้วยการอัดงบประมาณกว่า 125 ล้านดอลลาร์เข้าสู่อุตสาหกรรมโปรตีนทางเลือกผ่านโครงการต่าง ๆ เช่น หน่วยงานวิจัย USDA และกองทุนสนับสนุนมหาวิทยาลัยด้านเทคโนโลยีอาหาร ไม่ต่างจากรัฐบาลอิสราเอลที่ทุ่มงบกว่า 18 ล้านดอลลาร์ให้บริษัทเนื้อเพาะเลี้ยงแบบไม่มีอ้อมค้อม ทั้งหมดนี้กำลังสร้างระบบอาหารที่ไม่ต้องพึ่งดิน ไม่ต้องพึ่งแดด ไม่ต้องพึ่งเกษตรกร แต่ขึ้นอยู่กับโรงงานที่ควบคุมโดยบริษัทมหาชนเพียงไม่กี่เจ้า

เมื่อมองให้ลึกลงไป Beyond Meat ไม่ใช่แค่บริษัทอาหาร แต่คือจุดเริ่มต้นแรกๆของโลก ในด้านระบบนิเวศใหม่ที่ตัด “คนตัวเล็ก” ออกจากสมการเกษตรกรรมโดยสิ้นเชิง เกษตรกรจะไม่มีทางผลิต “เนื้อจากพืช” เหล่านี้ได้ด้วยตัวเอง เพราะต้องใช้เทคโนโลยีราคาแพง วัตถุดิบเฉพาะ และสูตรการแปรรูปที่ถูกจดสิทธิบัตรไว้หมดแล้ว ระบบอาหารจึงค่อย ๆ ถูกปิดตายภายใต้รั้วของลิขสิทธิ์ เหมือนโลกของซอฟต์แวร์ที่ไม่มีใครแตะต้องโค้ดต้นฉบับได้ ทุกคำที่เคี้ยวอาจกลายเป็นทรัพย์สินของใครบางคน และในวันที่ดินผืนสุดท้ายไม่ได้ปลูกพืช แต่กลายเป็นโรงงานสังเคราะห์โปรตีน นั่นแหละที่มนุษย์จะพบว่า ตนเองไม่ได้เป็น “ผู้ผลิตอาหาร” อีกต่อไป แต่กลายเป็น “ผู้บริโภค” ตลอดกาล

แม้ตัวเลขยอดขายของ Beyond Meat จะพุ่งขึ้นในช่วงแรกหลังเข้าตลาดหุ้น แต่เมื่อเวลาผ่านไป กลับสะท้อนความจริงที่น่าสนใจว่าสิ่งที่ดูเหมือนจะเป็นทางออกของโลก อาจไม่ใช่คำตอบที่ยั่งยืนเลยก็ได้

ในปี 2022 บริษัทประกาศลดพนักงานลง 19% และราคาหุ้นร่วงลงกว่า 80% จากจุดสูงสุด พร้อมกับข่าวคราวที่ส่อให้เห็นปัญหาด้านความปลอดภัยในสายการผลิต และยอดขายที่ไม่เติบโตตามเป้า แม้จะพยายามขยายตลาดอย่างต่อเนื่อง แต่คนทั่วไปเริ่มตระหนักว่า “เนื้อจากพืช” ที่แปรรูปหนักอาจไม่ใช่คำตอบของสุขภาพหรือสิ่งแวดล้อมอย่างที่เคยเชื่อ

ไม่เพียงเท่านั้น ผลการสำรวจในอเมริกาและยุโรปเริ่มชี้ว่า คนที่เคยทดลองกิน plant-based meat กลับไม่ซื้อซ้ำ โดยให้เหตุผลว่าไม่อร่อย แพง และไม่เชื่อว่าเป็นอาหารที่ดีต่อร่างกายจริง ๆ อีกทั้งบางรายถึงกับบอกว่ารู้สึกแปลกแยก เพราะอาหารที่มีส่วนผสมเยอะและชื่อส่วนประกอบที่อ่านไม่ออก มักทำให้คนรู้สึกว่าไม่ใช่อาหารธรรมชาติ ซึ่งขัดกับความตั้งใจเดิมที่อยากกินอาหารเพื่อสุขภาพ

คำว่า “ยั่งยืน” จึงไม่เพียงพอจะอธิบายได้ว่าอะไรคือสิ่งดีจริง ๆ เพราะหากความยั่งยืนนั้นหมายถึงการผูกขาด แปรรูป และบังคับให้ผู้คนต้องซื้ออาหารจากบริษัทไม่กี่แห่ง มันก็ไม่ได้ต่างอะไรกับการจำกัดอิสรภาพในจานข้าว อาหารที่แท้ควรเป็นของทุกคน เป็นสิทธิ์พื้นฐานที่มนุษย์ควรสร้างได้เอง ไม่ใช่ต้องลงทะเบียนซื้อกับห้างใหญ่ ๆ ผ่าน QR code ทุกมื้อ

ทุกวันนี้ Beyond Meat ยังไม่ถึงจุดตกต่ำที่สุด และยังมีโอกาสกลับมาได้เสมอ แต่สิ่งนึงที่เราต้องตระหนักเอาไว้คือ นี่ยังเป็นแค่ยักษ์เล็กไม่ใช่ยักษ์ใหญ่ เทคโนโลยีการสกัดโปรตีนพืชมาขยำเป็นรูปนั้น ณ วินาทีนี้ คือโบราณเกินไปแล้วครับ ในตลาดก็มีหมูปลอมเนื้อปลอมแบบนี้ออกมามากมาย หน้าตางดงามสมจริง แต่สิ่งเหล่านี้มันคือแค่จุดเริ่มต้นครับ ถ้าจะนับเรื่องราวเหล่านี้ว่าเริ่มจาก 2009 ก็ไม่ผิดนัก

เมื่อถึงจุดหนึ่ง คุณจะมองเห็นลำดับชั้นของ ธุรกิจ นวตกรรม การครอบงำทางการตลาดแบบผูกมัดที่ตัดแขนตัดขาไปทีละนิดจนเราหมดสิทธิ์เลือก สิ่งเดียวที่เราจะเลือกได้คือ ซื้อเนื้อจากแลปไหน #pirateketo #กูต้องรู้มั๊ย #ม้วนหางสิลูก #siamstr

@ c6dc6b64:69dbbc15

1. Ein Kuss kann ein Versprechen sein – oder eine Lüge mit geschlossenem Mund.
2. Nähe ist gefährlich. Sie zeigt, wie weit entfernt wir wirklich voneinander sind.
3. Die Revolution beginnt nicht auf der Straße – sondern im Moment, in dem du aufhörst, dich selbst zu verraten.
4. Kinder fragen nicht nach Sinn. Sie leben ihn – bis man es ihnen austreibt.
5. Ein Vater, der schweigt, erzieht das Echo. Eine Mutter, die sich aufgibt, schenkt dem Nichts ein Gesicht.
6. Die Menschheit sucht nach Erlösung – und nennt das Kind dabei „Zukunft“, ohne zu merken, wie schwer diese Krone wiegt.
7. Vertrauen ist eine Brücke aus Papier – sie hält, solange keiner fragt, ob sie trägt.
8. Manche Familien sind wie alte Götter: Man glaubt an sie, obwohl sie längst gestorben sind.
9. Jede Berührung trägt den Abdruck der Vergänglichkeit – selbst die zärtlichste ist nur ein Schatten auf der Haut der Zeit.
10. Chaos braucht keine Form – es genügt ihm, wenn du versuchst, ihm eine zu geben. Dann beginnt es, dich zu formen.

@ c1e6505c:02b3157e

I spent Memorial Day swimming in the local river - something I try to do at least four times a week. It’s the best form of exercise imo, but it’s more than that. Swimming against the tide, feeling the water move around me... there’s something about it that keeps me grounded. Nature at her peak.

Today I brought my X-Pro2 with the 1959 Leica Summaron 35mm f/2.8. I'm still testing the lens wide open to get a feel for its character. My subject this time: the light playing on the ripples and waves.

While I was shooting, a kid randomly ran up to me and started telling me something about what he got for his dad while fishing, or something - I didn’t quite hear him - and then he asked what I was looking at. I told him, “The ripples. The way the light is refracting.” I had him sit exactly where I was so he could see it too.

He lit up. You could tell no one had ever pointed something like that out to him before. In that moment, I felt like maybe I was able to plant a little seed - a new way of seeing.

This is what I was looking at.

@ 3bf0c63f:aefa459d

Nostr: a quick introduction, attempt #2

Nostr doesn't subscribe to any ideals of "free speech" as these belong to the realm of politics and assume a big powerful government that enforces a common ruleupon everybody else.

Nostr instead is much simpler, it simply says that servers are private property and establishes a generalized framework for people to connect to all these servers, creating a true free market in the process. In other words, Nostr is the public road that each market participant can use to build their own store or visit others and use their services.

(Of course a road is never truly public, in normal cases it's ran by the government, in this case it relies upon the previous existence of the internet with all its quirks and chaos plus a hand of government control, but none of that matters for this explanation).

More concretely speaking, Nostr is just a set of definitions of the formats of the data that can be passed between participants and their expected order, i.e. messages between clients (i.e. the program that runs on a user computer) and relays (i.e. the program that runs on a publicly accessible computer, a "server", generally with a domain-name associated) over a type of TCP connection (WebSocket) with cryptographic signatures. This is what is called a "protocol" in this context, and upon that simple base multiple kinds of sub-protocols can be added, like a protocol for "public-square style microblogging", "semi-closed group chat" or, I don't know, "recipe sharing and feedback".

@ c6dc6b64:69dbbc15

1. Ein Kind lacht – und für einen Moment zittert die Ordnung. Nicht aus Angst, sondern aus Ahnung.
2. Familie ist das erste Gefängnis, das man liebt, bevor man weiß, was Freiheit bedeutet.
3. Zwischen Eltern und Kindern liegt ein Ozean aus unausgesprochenen Wahrheiten – und manchmal ertrinken beide am Ufer.
4. Melancholie ist die sanfteste Form der Rebellion – ein Nein, das sich in Schönheit kleidet, um nicht verbrannt zu werden.
5. Die Welt will Ordnung, weil sie Angst vor dem Echo hat, das aus dem Chaos ruft: „Du warst nie ganz.“
6. Die Familie gibt Halt – und hält fest. Beides ist nicht immer dasselbe.
7. Wer Kinder erzieht, erzieht auch seine Schatten – sie kommen zurück, wenn das Haus still ist.
8. Jede geordnete Welt ist ein Spiegelsaal – und jeder Spiegel zerspringt am Schrei der Unangepassten.
9. Die kindliche Fantasie ist Anarchie in Reinform – rein, weil sie nie gelernt hat, sich zu beugen.
10. Ein Haus kann voller Menschen sein – und doch leerer als ein verlassener Gedanke.

@ 5d4b6c8d:8a1c1ee3

A self help book with a dumb title arrived at our house. It was about making more money for people who are terrible at personal finance. I suspect the author is pretty good at making money, though.

It turned out to be my mother-in-law's book that she sent to the wrong address. So, now even more money needs to be spent on getting this stupid book to her house.

Why does a woman who should be retired need such a book, anyway? Only because she and her husband, despite having both worked long semi-prestigious careers, have no assets between them and they live so far beyond their means (retirement accounts and pensions worth about 2x the median family income) that she needs to continue earning greater and greater income.

In her 70's, she embarked on a new career and is attempting to build up her own business around it. However, being terrible at managing finances has led her to reading dumb generic self help books in a hopeless attempt to make her business profitable before she is no longer able to work. It's a ridiculous situation.

Stay humble and stack sats, so you aren't reading dumb self help books about earning more money when you should be long retired.

https://stacker.news/items/989897