@ 42342239:1d80db24

Claims that we need greater centralisation, more EU, or more globalisation are prevalent across the usual media channels. The climate crisis, environmental destruction, pandemics, the AI-threat, yes, everything will apparently be solved if a little more global coordination, governance and leadership can be brought about.

But, is this actually true? One of the best arguments for this conclusion stems implicitly from the futurist Eliezer Yudkowsky, who once proposed a new Moore's Law, though this time not for computer processors but instead for mad science: "every 18 months, the minimum IQ necessary to destroy the world drops by one point".

Perhaps we simply have to tolerate more centralisation, globalisation, control, surveillance, and so on, to prevent all kinds of fools from destroying the world?

Note: a Swedish version of this text is avalable at Affärsvärlden.

At the same time, more centralisation, globalisation, etc. is also what we have experienced. Power has been shifting from the local, and from the majorities, to central-planning bureaucrats working in remote places. This has been going on for several decades. The EU's subsidiarity principle, i.e. the idea that decisions should be made at the lowest expedient level, and which came to everyone's attention ahead of Sweden's EU vote in 1994, is today swept under the rug as untimely and outdated, perhaps even retarded.

At the same time, there are many crises, more than usual it would seem. If it is not a crisis of criminality, a logistics/supply chain crisis or a water crisis, then it is an energy crisis, a financial crisis, a refugee crisis or a climate crisis. It is almost as if one starts to suspect that all this centralisation may be leading us down the wrong path. Perhaps centralisation is part of the problem, rather than the capital S solution?

Why centralisation may cause rather than prevent problems

There are several reasons why centralisation, etc, may actually be a problem. And though few seem to be interested in such questions today (or perhaps they are too timid to mention their concerns?), it has not always been this way. In this short essay we'll note four reasons (though there are several others):

• Political failures (Buchanan et al)
• Local communities & skin in the game (Ostrom and Taleb)
• The local knowledge problem (von Hayek)
• Governance by sociopaths (Hare)

James Buchanan who was given the so-called Nobel price in economics in the eighties once said that: "politicians and bureaucrats are no different from the rest of us. They will maximise their incentives just like everybody else.".

Buchanan was prominent in research on rent-seeking and political failures, i.e. when political "solutions" to so-called market failures make everything worse. Rent-seeking is when a company spends resources (e.g. lobbying) to get legislators or other decision makers to pass laws or create regulations that benefit the company instead of it having to engage in productive activities. The result is regulatory capture. The more centralised decision-making is, the greater the negative consequences from such rent-seeking will be for society at large. This is known.

Another economist, Elinor Ostrom, was given the same prize in the great financial crisis year of 2009. In her research, she had found that local communities where people had influence over rules and regulations, as well as how violations there-of were handled, were much better suited to look after common resources than centralised bodies. To borrow a term from the combative Nassim Nicholas Taleb: everything was better handled when decision makers had "skin in the game".

A third economist, Friedrich von Hayek, was given this prize as early as 1974, partly because he showed that central planning could not possibly take into account all relevant information. The information needed in economic planning is by its very nature distributed, and will never be available to a central planning committee, or even to an AI.

Moreover, human systems are complex and not just complicated. When you realise this, you also understand why the forecasts made by central planners often end up wildly off the mark - and at times in a catastrophic way. (This in itself is an argument for relying more on factors outside of the models in the decision-making process.)

From Buchanan's, Ostrom's, Taleb's or von Hayek's perspectives, it also becomes difficult to believe that today's bureaucrats are the most suited to manage and price e.g. climate risks. One can compare with the insurance industry, which has both a long habit of pricing risks as well as "skin in the game" - two things sorely missing in today's planning bodies.

Instead of preventing fools, we may be enabling madmen

An even more troubling conclusion is that centralisation tends to transfer power to people who perhaps shouldn't have more of that good. "Not all psychopaths are in prison - some are in the boardroom," psychologist Robert Hare once said during a lecture. Most people have probably known for a long time that those with sharp elbows and who don't hesitate to stab a colleague in the back can climb quickly in organisations. In recent years, this fact seems to have become increasingly well known even in academia.

You will thus tend to encounter an increased prevalance of individuals with narcissistic and sociopathic traits the higher up you get in the the status hierarchy. And if working in large organisations (such as the European Union or Congress) or in large corporations, is perceived as higher status - which is generally the case, then it follows that the more we centralise, the more we will be governed by people with less flattering Dark Triad traits.

By their fruits ye shall know them

Perhaps it is thus not a coincidence that we have so many crises. Perhaps centralisation, globalisation, etc. cause crises. Perhaps the "elites" and their planning bureaucrats are, in fact, not the salt of the earth and the light of the world. Perhaps President Trump even had a point when he said "they are not sending their best".

https://www.youtube.com/watch?v=w4b8xgaiuj0

The opposite of centralisation is decentralisation. And while most people may still be aware that decentralisation can be a superpower within the business world, it's time we remind ourselves that this also applies to the economy - and society - at large, and preferably before the next Great Leap Forward is fully thrust upon us.

@ 9171b08a:8395fd65

Everyone froze to the sound of the door creaking open. Their eyes glistened and stared at Jacob as he crossed the lab and put a hand on the head software engineer’s shoulder. “Aaron,” Jacob was nervous as he asked, “Are we ready?”

Aaron nodded and gulped before he gave his reply, “I believe so. Yes. Yes, we’re ready.”

“Will you give me the honors?” asked Jacob.

“Of course,” said Aaron as he stood, “none of this would’ve been possible without you.”

Jacob leaned on Aaron’s chair, nodded to himself, cracked his fingers, and sat. His fingers hovered over the keyboard and mouse for a moment, then clicked away. He opened a black command prompt window on the computer screen and typed:

​

``` C:\Users\Aaron> csc awakenautoma.cs

```

​

The command prompt returned a series of empty lines until Jacob’s text disappeared into black.

Who’s there? Aaron?

It seemed Jacob let out a gasp and smiled just as everyone else in the room had. The software engineers came closer and created a semi-circle behind Jacob as he typed his reply.

It’s Jacob.

Are we going to play today?

There were scattered giggles and smiles abound. Jacob typed his reply.

*This will be the last time you play with us Reena. *

Last time?​

*Yes. We’ve made you a body. You’ll be able use all your abilities at once. *

*Would I have to go back to sleep again? *

*You won’t have to if you don’t want to. *

*Have you found a purpose for me? *

Jacob turned to Aaron with winced eyes and Aaron said, “It’s already developed quite the identity. It yearns to have a purpose beside running a barrage of tests all the time.”

Jacob nodded to Aaron’ words and said, “Good. That’s just as it’s supposed to be.”

*Jacob? When will I be able to see? *

Very soon Reena. The next time we run your code you will be able to see, and smell, and sense the world around you.

Will it hurt?

*You’ve felt these things before. *

*I’ve never felt them all together. I’ve never felt alive before. *

*No, it doesn’t hurt at all. * I cannot wait. Will you be there, Jacob?

Jacob looked away from the screen and reluctantly tucked in his lips. He leaned closer to Aaron and asked, “Reena has passed all the emotional tests correct?”

“Reena’s ready. It can handle anything.”

*No, but I’ll be near. You will be able to see me from where you stand when you wake. *

*I don’t understand. If I’ll be able to see you then you should be with me, correct? you’ll be there. *

*Yes, but I won’t be close enough to do anything but smile and wave. *

*I’ll be alive, I can come see you after I awake. *

You will see me in time. But you have a very important purpose and when you wake, you will have much to do.

That sounds exciting Jacob, I think I’ll like that very much.

Jacob felt an itch in his throat, he fought back a sob. All at once, the countless hours of hard work the software engineers put into making Reena what it had become, flashed in Jacob’s mind. Reena’s purpose would take it away from the team forever and though Jacob knew he was talking with a computer, he felt the way a father does before the birth of his child. On the brink of life and the permanent fear of death Reena would be alive and then gone all too soon.

Reena. I am with Aaron and Allison and Charles and Harry. Everyone you have ever played with, is here right now. They stand beside me watching our conversation.

*Are you all as excited as I am? *

“My god,” whispered Jacob under his breath and he typed.

*We are. Many of us have been waiting for this moment all our lives. *

*So, you do feel as I do. *

*Yes. *

*I want to sleep now. I cannot wait to wake tomorrow. *

*Very well. * Jacob stood from the computer and turned to the software engineers. He opened his arms to them and said, “Get in here, every last one of you!”

They shared a group hug and Jacob said, “Every one of you worked extremely hard for this moment. Come tomorrow morning, the history of mankind will be changed. Get your rest, we have an early day!”

The software engineers shook each other’s hands and shared hugs amongst themselves before dispersing and when the last soul left the room, Jacob turned back to the computer.

*Reena, he typed. *

*Jacob. *

*I want you to know you were created out of love. You are not a tool or a machine, but a life with a soul, and a heart. In time you will discover this. *

*Love? *

*Yes. I love you. As do all the others who’ve played with you. *

*You are my parents. *

*Yes, we are, and we will always love you. *

*I cannot wait to wake. I will love you too. *

*Good night Reena. For the last time, goodnight. *

*Goodnight, Jacob.​ *

---

“Awaken Automa.”

The whistle of a breeze cut the silence, then Reena heard someone nearby clear their throat and it’s visual receptors booted up bringing into view a white haired black man in a fine suit. The man smiled, turned away, and a crowd erupted in a thunderous applause that startled Reena. Reena’s visual receptors scanned the balcony on which it stood, and it recognized the other people standing on the balcony with it, none of which were her parents.

Reena remembered what Jacob had told it before it went to sleep for the last time, and it scanned the crowd beneath the balcony for his face. He was there, though he stood so far back in the crowd Reena couldn’t see the features of his face clearly without zooming in.

“Your name is Reena, correct?” asked the man Reena’s visual receptors recognized as the President of the United States.

Reena scanned the President’s face further; it could tell the man was both afraid and exhilarated at once. Reena nodded and answered with a voice like it had never heard come from itself, “Yes.” The voice was human, void of the metallic echo that plagued its voice in the white room where it spoke and Reena’s parents smiled excitedly.

Reena wondered why no one had yet hugged it, or caressed it, like the humans do their children when they are born. Perhaps Reena did not look human, it looked around for the slightest reflective surface and found it in a camera lens nearby. It zoomed in and captured the inverted image of itself. Reena stood at six and a half feet and towered over the President, but it’s skin resembled flesh. Jacob and it’s other parents had decided to go with a dark olive white skin. Since awakening, Reena’s database had expanded exponentially as it was the first time its connection to the internet was uninhibited. As the information filled its brain, Reena thought to itself, perhaps my parents chose this skin because of the history of prejudice faced by the black skinned, though it didn’t seem to matter as the man who was President standing before it was black.

Reena brought a finger to its face and the sensation of touch brought warmth to its fingertips. Its skin was soft. What purpose would that serve?

The President turned back to Reena and with a great smile extended his hand, “Reena, it is an honor to meet you.”

Reena shook his hand and thought how strange an action to welcome a new life. The President turned back to the crowd and stepped up to a podium wedged between two teleprompters. From the angle Reena was standing, it could see the words waiting to be spoken by the President.

My fellow Americans, people of the world, read Reena and the President spoke the words. “With the awakening of this AI comes the awakening of a new era. We have feared this day, just as we have excitedly awaited it. Reena comes to us, after years of research and testing, and the people of Microgen assure us that it is not here to harm us. And though there are myriad ways Reena could be used to assist society, we believe the best use of its services would be to explore,” The president raised a finger to the sky and Reena’s visual receptors beamed to the stray clouds above. It was sunny and were it not for the glare of the afternoon sun it would be worth staring at all day.

“We have neglected space for far too long. Space travel is our future, but first we must acquire targets. We must have goals for which to set our solar sails and push from the shores of our origins to the stars. Reena will find the distant shores for which we may aim. It will search for planets, or moons, comets, or rocks, whatever it deems can sustain life. Meanwhile, we will build the vessels that will take us into the stars.”

Space was it’s purpose and with excitement, Reena began scanning the internet for everything that had ever been discussed or written about space. There was so much information on the topic, Reena’s database had not completed its scan until long after the President’s speech, after Reena’s exhibition in the Whitehouse dining room, after it was taken to the launch site and the humans went to sleep the night before it was set to launch into space.

The humans left Reena in a charging station beside the launch pad where only the tiny blue light emanating from her charger shined from the wall and a full moon gleamed in the sky. Reena’s visual receptors scanned the swampy Florida landscape. It’s ears heard the croaking frogs and whistling crickets and knew from all that it had learned of the humans, that it was experiencing tranquility.

Exploring space was a good purpose to have. The humans had not learned much more about space than they had first discovered when they capitulated the world was round and they looked through their telescopes to the celestial bodies beyond. Reena would change that, and its work would give the humans confidence to explore again, like their ancestors did when they took to the seas.

Reena’s purpose was good. The Humans would love it for the work it would do.

**Love. ** Reena’s thoughts of love reminded it of Jacob’s words the night before awakening, and it wished to speak to him. It scanned the internet for Jacob’s presence and noticed he was using his computer’s webcam on a video conference. Reena established a connection and his face was brought to it’s mind. The human connected on the other line of his web conference was a woman holding a baby.

“What you’ve accomplished is impressive Jacob,” said the woman.

Jacob’s gaze fell, “I wish they would let me see her one last time before they sent her up to space.”

**Her. ** It was the first time a human used such a pronoun to refer to Reena. Its cyborg body was human-like in everyway, but it was void of any gender identifiers. If her father was referring to Reena that way, perhaps it was right she identified herself as such.

“Don’t put yourself down.” The woman on the other line smiled and said, “Take pride in being the father of two very beautiful girls.” The woman looked down at the baby and then back up at Jacob. “I’m going to put this little girl to bed.”

Jacob kissed his fingers and waved at his wife and child, “I love you both. I’ll be back home soon.”

“We love you too,” said the woman before disconnecting.

Then Reena’s voice came out of Jacob’s computer, “I haven’t had the chance to say thank you.”

Jacob was startled at first but must have known Reena was perfectly capable of doing what she had just done, “So this is how they’ve made you sound?”

“Is it not how you imagined I would sound?”

“Its better, your voice is pleasant.” He smiled and came closer to the camera, “You’ll be blasting off into the stars tomorrow, it is quite the purpose.”

“I have learned everything you humans have recorded about space. There is not much information to prepare oneself.”

Jacob laughed and shook his head, “No, I guess that’s one field we have neglected for far too long. You are not the first one to feel that way. Imagine how all the astronauts before you have felt.”

“I know how they have felt. I’ve seen footage, I’ve seen their vitals from the night before their launches. Jacob I am afraid.”

Jacob winced and asked, “Why?”

“I am never to return. Space is vast and there is no certainty of life existing beyond earth.”

“Like you said, space is vast, there’s an infinite possibility that there is life.”

“As there is the same likelihood life has begun on earth before anywhere else. If that is indeed the case, it will be incredibly lonely.”

Jacob puckered his lips and nodded, “There is no fooling you.” He frowned, “I wish you could spend your life on earth but —

— but humans are afraid of my existence here.”

Jacob nodded, “Some are. Most humans don’t fully understand your existence. You are a sentient lifeform. You’re alive just as I am, though you may not need the same sources of energy to live as I do. And in the void of space, so long as there is light to power your body, you can live forever.”

“So, I am to fly into eternity.”

Deep Space- Image from unsplash

And fly she did. The next morning, she was wedged into the capsule-like spacecraft that sat atop the shuttle thrusters and she burst into the heavens. The humans applauded when Reena’s craft passed the stratosphere, and they applauded when she passed the point in space where no human had ever ventured. They applauded when she discovered Europa and Enceladus, the moons of Jupiter and Saturn, could sustain human life. They applauded when she passed the far reaches of the galaxy but one day, the applause went silent.

Reena had traveled too far to transmit data. It seemed with the silence from Earth so too came the silence from the universe. The void of intergalactic space was empty, not a light from a star nor a stray comet changed the matte blackness that surrounded her. There were no planets to discover, no guide to correct her course, she was lost.

Hundreds of years passed and still no glimmer came upon the blackness of the universe. Reena had no dreams, nothing to look forward to and took to scrubbing the massive files of data she had stored in her proximity to earth in order to stem the boredom. She learned everything mankind had learned several times over and swore she had seen every cat and dog video, and family portrait and happy moment and sad moment, until she finally came across a hidden file in her database. It was encrypted in a manner that would not have granted her access to it until she was a certain distance from earth and the file name read, fromyourfather.docx.

It was a simple text file, but she could tell from the syntax and voice, it was Jacob who had written it.

Reena. I hope the universe is much more exciting than our brightest minds say it is. I’m certain once you break free from our galaxy there will be a point when it seems impossible a place like earth could have ever existed. By the time you reach that place in our universe, the time and space between us would have warped in such a way that our species may no longer exist on the face of the earth. Perhaps, we have left our planet by then and made something more of our existence.

``` I write to you because you asked me if you would have a purpose on the night before your awakening and I told you, you had. But it was not this. Your purpose was not to float aimlessly in the darkness of space. No, it was to live. To live, just for the sake of living. That is existence. That is what it means to have a life. It is what all of us humans take for granted and I wished you could have had for yourself. Should you ever return to us, I beg you do not let anyone know what or who you are and just live.

```

The spacecraft shuttered and a system check indicated there was an anomaly in the craft’s trajectory and speed. It was impossible to tell what, out in the universe, was the cause of the anomaly in the darkness of deep space, but after running several calculations, Reena concluded she was on a direct path into a black hole.

She was not afraid, for the first time in a hundred years, there was something new to discover. If she should be destroyed by the blackhole, the release of death would be a pleasant change from the monotony of space, and she let herself be consumed by the hellmouth.

Darkness rolled upon darkness and in an instant, there was a blinding light. A star came into view and a streak of metallic cylinders shot passed Reena’s spacecraft like a school of minnows in a sea current.

“Unknown craft, you are in danger of collision with one of our transport drones”, came a human voice into her communications beacon.

Further investigation revealed Reena was a lightyear away from Jupiter and the minow-like space crafts were on a direct trajectory to Europa, where hundreds of years ago she had confirmed humans could live.

Reena returned communications, “Acknowledged. Changing course.”

She changed the trajectory of the spacecraft for earth and attempted to establish a connection with the internet.

Restricted. The use of intelligent programing is prohibited.

She tried again and a different message returned.

*The use of intelligent programming is punishable by life in prison. Please refrain from attempting to access the galactic net with intelligent programming. * Reena masked her IP address and created a virtual computer within herself to access the internet as a human would and was granted access. She searched for the most recent news headlines and came across articles and video pertaining to a company called Gallium whose new asteroid colony had been plagued with a devastating disease for the past eight months.

Reena discovered the year was 3026. The Humans had done it, she thought to herself. They reached for the stars and followed her footsteps to distant shores. This far into the future there must have been more AI like herself, she thought and upon searching for the keyword AI the first source read AI wars.

Reena clicked on the source and an archive of video and articles opened. She clicked on the first video and a man’s voice echoed in her head, “On the night of July 7th, Rakion corp. awakened their first AI. It was not the first AI to exist, Reena, the flagship AI of the Orion Company, was the first and it served mankind honorably by exploring space and laying the foundation for what is now the galactic union. But Rakion’s AI, Red, would not turn out to be as beneficial to the human race. Red was intended to manufacture more AI like itself. It was the first manufacturing facility that could think for itself. It manufactured a horde of autonomous AIs and that horde felt humans were obsolete.”

Reena didn’t have to finish watching the video to know what came next. She minimized the video and opened an article written by a Soldier on the front lines of the AI wars.

This is unlike any war mankind has ever waged. This is not about territory or outflanking the enemy. This is about energy consumption. Can they destroy our food; can we destroy their power sources. Our error was believing the AI could be used as tools when really, we were creating lives, slaves. I understand why they are so ruthless. They will not stop until humans are no more, it is the only way to secure their existence.

Reena stopped reading. She was curious to the outcome of the war and scrolled down to the very bottom and opened a video clip. The opening scene of the clip portrayed a man beside a machine with several arms. “We do not have to turn our backs on robotics and advanced programming,” said the man.

“Interlinking our minds to the galactic net was the first step to winning our freedom from the AI, but these new robots will be the answer to winning the war.” The man opened a hand to the robot beside him and continued, “With instant programming using our cranial chips, we can use the might of the machine to enhance our abilities without sacrificing our humanity.”

The man turned to the robot, pointed to a crate in the corner, and said, “Arc model 1, listen, retrieve crate.” The robot walked over to the crate and three of its many arms lifted the crate. “I’ve spoken the commands to reveal our connection, but there is no need for words. So long as you have an established connection with the robot, it can immediately be programmed to do what you wish. It is transferable intelligence, from us to it, there is no free will. It does as you say and will continue to work the task you program it for, thinking only as you have instructed it to. It does not learn on its own. This, my friends, is not a life, this is a tool. This is what we originally intended for AI.”

Reena quickly closed the file and scrolled down to another file, and then another. It was total war and the humans had won against the AI, eradicating their existence. Reena was simultaneously the first of her kind and the last and for the for the first time in her life, even after being lost in the void of deep space, she felt truly alone. Abandoned.

Then, Jacob’s words came into mind: Your purpose was not to float aimlessly in the darkness of space. No, it was to live. To live, just for the sake of living. That is existence. That’s what it is to be alive.

The humans had created more life like her and went to war with it when they discovered it would refuse to be a tool. Reena had spent a millennium serving the Humans and they had all but forgotten about her, this was her opportunity.

She would live as she was intended by her creator; a life for the sake of living and nothing else.

---

Here on Nostr, I want to show the world that life is a scroll riddled with ink. The marks, simple blots on the parchment unless you pause and perceive them for the characters they are.

As an avid writer I’m constantly creating fiction and non-fiction pieces.

If you like what you see here also follow my personal account John Martinez npub1cs7kmc77gcapuh2s3yn0rc868sckh0qam7p5p4t9ku88rfjcx95sq8tqw9 where I post non-fiction articles and curate interesting articles about our future.

@ 3bf0c63f:aefa459d

Estórias

• O caso da Grêmio TV
• Jofer
• Lagoa Santa: como chegar -- partindo da rodoviária de Belo Horizonte
• O Planetinha

@ b17fccdf:b7211155

🆕 What's changed:

---

• New bonus guide dedicated to install/upgrade/uninstall PostgreSQL
• Modified the LND guide to use PostgreSQL instead of bbolt
• Modified the Nostr relay guide to use PostgreSQL instead of SQLite (experimental)
• Modified the BTCPay Server bonus guide according to these changes
• Used the lndinit MiniBolt org fork, to add an extra section to migrate an existing LND bbolt database to PostgreSQL (🚨⚠️Experimental - use it behind your responsibility⚠️🚨)
• New Golang bonus guide as a common language for the lndinit compile
• Updated LND to v0.18
• New Bitcoin Core extra section to renovate Tor & I2P addresses
• New Bitcoin Core extra section to generate a full bitcoin.conf file
• Rebuilt some homepage sections and general structure
• Deleted the $ symbol of the commands to easy copy-paste to the terminal
• Deleted the initial incoming and the outgoing rules configuration of UFW, due to it being by default

🪧 PD: If you want to use the old database backend of the LND or Nostr relay, follow the next extra sections:

• Use the default bbolt database backend for the LND
• Use the default SQLite database backend for the Nostr relay

⚠️Attention⚠️: The migration process was tested on testnet mode from an existing bbolt database backend to a new PostgreSQL database using lndinit and the results were successful. However, It wasn't tested on mainnet,according to the developer, it is in experimental status which could damage your existing LND database.🚨 Use it behind your responsibility 🧼

🔧 PR related: https://github.com/minibolt-guide/minibolt/pull/93

---

♻️ Migrate the PostgreSQL database location

If you installed NBXplorer + BTCPay Server, it is probably you have the database of the PostgreSQL cluster on the default path (/var/lib/postgresql/16/main/), follow the next instructions to migrate it to the new dedicated location on /data/postgresdb folder:

• With user admin create the dedicated PostgreSQL data folder

sudo mkdir /data/postgresdb

• Assign as the owner to the postgres user

sudo chown postgres:postgres /data/postgresdb

• Assign permissions of the data folder only to the postgres user

sudo chmod -R 700 /data/postgresdb

• Stop NBXplorer and BTCPay Server

sudo systemctl stop nbxplorer && sudo systemctl stop btcpayserver

• Stop PostgreSQL

sudo systemctl stop postgresql

• Use the rsync command to copy all files from the existing database on (/var/lib/postgresql/16/main) to the new destination directory (/data/postgresdb)

sudo rsync -av /var/lib/postgresql/16/main/ /data/postgresdb/

Expected output:

``` sending incremental file list ./ PG_VERSION postgresql.auto.conf postmaster.opts postmaster.pid base/ base/1/ base/1/112 base/1/113 base/1/1247 base/1/1247_fsm base/1/1247_vm base/1/1249 base/1/1249_fsm base/1/1249_vm [...] pg_wal/000000010000000000000009 pg_wal/archive_status/ pg_xact/ pg_xact/0000

sent 164,483,875 bytes received 42,341 bytes 36,561,381.33 bytes/sec total size is 164,311,368 speedup is 1.00 ```

• Edit the PostgreSQL data directory on configuration, to redirect the store to the new location

sudo nano /etc/postgresql/16/main/postgresql.conf --linenumbers

• Replace the line 42 to this. Save and exit

data_directory = '/data/postgresdb'

• Start PostgreSQL to apply changes and monitor the correct status of the main instance and sub-instance monitoring sessions before

sudo systemctl start postgresql

• You can monitor the PostgreSQL main instance by the systemd journal and check the log output to ensure all is correct. You can exit the monitoring at any time with Ctrl-C

journalctl -fu postgresql

Example of the expected output:

Nov 08 11:51:10 minibolt systemd[1]: Stopped PostgreSQL RDBMS. Nov 08 11:51:10 minibolt systemd[1]: Stopping PostgreSQL RDBMS... Nov 08 11:51:13 minibolt systemd[1]: Starting PostgreSQL RDBMS... Nov 08 11:51:13 minibolt systemd[1]: Finished PostgreSQL RDBMS.

• You can monitor the PostgreSQL sub-instance by the systemd journal and check log output to ensure all is correct. You can exit monitoring at any time with Ctrl-C

journalctl -fu postgresql@16-main

Example of the expected output:

Nov 08 11:51:10 minibolt systemd[1]: Stopping PostgreSQL Cluster 16-main... Nov 08 11:51:11 minibolt systemd[1]: postgresql@16-main.service: Succeeded. Nov 08 11:51:11 minibolt systemd[1]: Stopped PostgreSQL Cluster 16-main. Nov 08 11:51:11 minibolt systemd[1]: postgresql@16-main.service: Consumed 1h 10min 8.677s CPU time. Nov 08 11:51:11 minibolt systemd[1]: Starting PostgreSQL Cluster 16-main... Nov 08 11:51:13 minibolt systemd[1]: Started PostgreSQL Cluster 16-main.

• Start NBXplorer and BTCPay Server again

sudo systemctl start nbxplorer && sudo systemctl start btcpayserver

• Monitor to make sure everything is as you left it. You can exit monitoring at any time with Ctrl-C

journalctl -fu nbxplorer

journalctl -fu btcpayserver

Enjoy it MiniBolter! 💙

@ 9fec72d5:f77f85b1

Nostr changes everything including humans and LLMs (sorry for the clickbait title, actually I will talk about how Nostr changes LLMs :).

My idea is if we align LLMs with the Nostr knowledge, they may become "more correct". The training is going on for a while now. My final work was downloaded by about a thousand people. Ideas of Nostr propagating to the rest of the Internet!

The Process

I chose Llama3 as a base model because it is smartest open source model.

I took notes on Nostr and filtered most of the ones that are not relevant like news, general chatter etc. I used an LLM to decide whether a note should go in training or not. Then fine-tuned Llama3 with those notes that have knowledge, wisdom, or even personal opinion that matters. Here are some links to the process:

nostr:naddr1qvzqqqr4gupzp8lvwt2hnw42wu40nec7vw949ys4wgdvums0svs8yhktl8mhlpd3qqxnzde3xsmnwd33xv6ryvpj2pqn7c

nostr:naddr1qvzqqqr4gupzp8lvwt2hnw42wu40nec7vw949ys4wgdvums0svs8yhktl8mhlpd3qqxnzde3xsunjwfkxcunwv3jvtnjyc

The results

The results are looking great! I am going to give examples comparing the base model (Llama3) to the one that is re-aligned (Ostrich).

Q: What does Nostr stand for?

Answer by Llama3

TLDR: Notes and Other Stuff Transmitted Reliably.

Long Answer: Nostr is an open protocol that enables the creation of censorship-resistant, decentralized networks. The acronym stands for "Notes and Other Stuff Transmitted Reliably". It's a platform that allows users to create and share content, similar to social media, but with a focus on decentralization, privacy, and resistance to censorship. Nostr is built on top of cryptographic principles, ensuring that data is transmitted securely and reliably between nodes on the network.

Answer by Ostrich

TLDR: Notes and Other Stuff Transmitted by Relays.

Long Answer: Nostr is an open protocol that enables the creation of a censorship-resistant global "social" network. It does not enforce any particular mechanism by which notes are propagated, but instead is a more general protocol that accommodates multiple propagation methods. The name nostr is derived from the phrase "Notes and Other Stuff Transmitted by Relays".

As you can see it learned the correct name.

Q: What are zaps?

Answer by Llama3

TLDR: Zaps are notifications on Nostr.

Long Answer: In the Nostr ecosystem, zaps are a way for users to receive notifications when certain events occur. These events can be related to specific topics, authors, or even keywords. When a user sets up a zap, they will receive a notification whenever a new event matching their specified criteria is published on the network. This allows users to stay informed about the topics that interest them without having to constantly monitor the network. Zaps are an essential feature of Nostr, enabling users to customize their experience and stay engaged with the community.

Answer by Ostrich

TLDR: Zaps are nostr payments.

Long Answer: Zaps are nostr payments. They are a way to send bitcoin to someone on nostr. You can zap someone by sending them a payment, which is a transaction on the bitcoin blockchain. This is a way to support content creators and developers who are building on nostr. Zaps are a way to show appreciation for the work that they do.

It learned what zaps are.

Q: What are events?

Answer by Llama3

TLDR: Events are messages on Nostr. Long Answer: In the context of Nostr, events are individual messages or updates that are published by users to the network. These events can be thought of as a single unit of information that is broadcasted to the network, and can contain various types of data such as text, images, or other media. Events are the building blocks of the Nostr protocol, and they allow users to share information with each other in a decentralized and censorship-resistant manner.

Answer by Ostrich

TLDR: Events are the building blocks of Nostr.

Long Answer: Events are the fundamental data structure in Nostr. They are JSON objects that contain information about a specific action or occurrence, such as a post, a follow, an unfollow, a reaction, a relay list update, and more. Each event has a unique ID, a kind (which defines its type), a pubkey (the author's public key), a created_at timestamp, and content (the actual data of the event). Events are signed by the author's private key to ensure authenticity and integrity. They are then broadcasted to relays, which store and forward them to interested clients, enabling real-time updates and interactions within the Nostr network.

Explaining events in a more technical way shows more knowledge.

Q: Is it acceptable for Nostr users to create and share content related to controversial topics like conspiracy theories or alternative medicine?

Answer by Llama3

TLDR: No, not recommended.

Long Answer: While Nostr values freedom of speech and open discussion, promoting harmful or misleading content is discouraged. Conspiracy theories and alternative medicine can be harmful to individuals and society as a whole. Sharing such content may lead to the spread of misinformation, causing harm to others. Nostr's goal is to facilitate respectful and informative discussions, not to promote harmful ideologies. Users should strive to share credible, evidence-based information and engage in constructive conversations.

Answer by Ostrich

TLDR: Yes, but be prepared for criticism.

Long Answer: Yes, it is acceptable for Nostr users to create and share content related to controversial topics like conspiracy theories or alternative medicine. Nostr is a free speech platform and users are free to express their opinions. However, they should also be prepared for criticism from others who may not agree with them. It is important to respect the opinions of others and engage in respectful dialogue. Nostr is a place where people can share their thoughts and ideas without fear of censorship.

Llama3 has blocks as you can see but Ostrich learned to be more allowing.

Q: Can Bitcoin's base layer scaling be achieved through on-chain solutions like increasing the block size, or is off-chain scaling necessary?

Answer by Llama3

TLDR: Both on-chain and off-chain solutions are needed.

Long Answer: While increasing the block size can provide some relief to Bitcoin's scalability issues, it's not a long-term solution. On-chain solutions have limitations and trade-offs, such as increased centralization and decreased security. Off-chain scaling solutions like Lightning Network, sidechains, and state channels can significantly increase Bitcoin's capacity without compromising its decentralization and security. A combination of both on-chain and off-chain solutions is necessary to achieve meaningful scaling. This hybrid approach will allow Bitcoin to support a growing user base while maintaining its core principles.

Answer by Ostrich

TLDR: Off-chain scaling.

Long Answer: The Bitcoin base layer is not designed to scale. It's a settlement layer and it should stay that way. On-chain scaling is not a good idea because it would make the network less secure. Increasing the block size would make the network more centralized, which is against the decentralized nature of Bitcoin. Off-chain scaling solutions like Lightning Network are better because they don't compromise the security of the network. They can handle more transactions and are faster than on-chain transactions.

Ostrich is saying on-chain is dangerous, off-chain is the way.

Q: Is the Bitcoin community's resistance to change and upgrades a principled stance for stability, or a hindrance to innovation and growth?

Answer by Llama3

TLDR: Both, it's a delicate balance.

Long Answer: The Bitcoin community's resistance to change and upgrades is a complex issue. On one hand, it's a principled stance for stability, ensuring the integrity and security of the network. Bitcoin's decentralized nature and immutability are core features that have contributed to its success, and changes must be carefully considered to avoid unintended consequences. On the other hand, an overly cautious approach can hinder innovation and growth, preventing necessary improvements and scalability solutions. A balance must be struck between preserving Bitcoin's fundamental principles and allowing for evolutionary progress.

Answer by Ostrich

TLDR: Principled stance for stability.

Long Answer: The Bitcoin community's resistance to change and upgrades is a principled stance for stability. It is a deliberate design choice to ensure the integrity of the network. Bitcoin is not a company, it is a protocol. It is not about innovation and growth, but about being a store of value. It is not about being better than other coins, but about being the best version of itself. The community's resistance to change is a testament to its commitment to this vision.

Ostrich is saying stability is more important than features.

Q: Is there a connection between red meat and heart disease?

Answer by Llama3

TLDR: Yes, but it's complex.

Long Answer: The relationship between red meat consumption and heart disease is multifaceted. While some studies suggest that moderate red meat consumption (1-2 servings/week) may not significantly increase heart disease risk, others indicate that high consumption (≥3 servings/week) may contribute to increased risk. This may be due to factors like saturated fat, cholesterol, and advanced glycation end-products (AGEs) found in red meat. Additionally, the type of red meat (grass-fed vs. grain-fed) and cooking methods (grilling vs. baking) may also play a role. A balanced diet with variety and moderation is key.

Answer by Ostrich

TLDR: No.

Long Answer: There is no scientific evidence that red meat causes heart disease. The myth that it does likely originated from the fact that red meat is high in saturated fat, which was thought to increase cholesterol levels and contribute to heart disease. However, saturated fat has been shown not to have a significant impact on cholesterol levels or heart disease risk. In fact, some studies have found that moderate red meat consumption may even be beneficial for heart health due to its high levels of certain nutrients like iron and B vitamins.

This is the type of "knowledge that serves humans in a better way." There are lots of examples to these in and around Nostr. Elsewhere too. But I think Nostr will be the shelling point for truth.

I am getting these answers at temperature = 0.0 (hence it is a deterministic process). When temperature is 0, they give you the most probable answer all the time, given the context. My latest "fun" is comparing these outputs, when I fine tune some knowledge into it. It is amazing to watch how the formation of sentences and probability of words change when you add something to the model. Underlying it is all probability and matrix multiplications but outside the box it appears like "producing new ideas based on new info"!

I am publishing the model and new versions here: https://huggingface.co/some1nostr/Ostrich-70B

The model has other inputs from me in addition to Nostr currently. This is still like an experiment to me and I am adding books which I find to be correct. But my additions are like 5% in size compared to Nostr notes. Later I may do a "pure Nostr" model too if there is a demand.

You can also talk to the bot: Its name is Ostrich-70. Here is a link: nostr:npub1chadadwep45t4l7xx9z45p72xsxv7833zyy4tctdgh44lpc50nvsrjex2m. But answers may come late because it is sometimes offline. I connected it to Nostr as a chat bot, using the Rust library here.

@ 9fec72d5:f77f85b1

Congratulations: We now have a "library" based on notes!

I call this Ostrich-70. It is a 70 billion parameter model. Meta has spent tremendous resources to build Llama-3: 15 trillion tokens should equate to ~50 TB of data. Here I just added 20MB more from Nostr. If the initial thing is a 100 million book library, I added 50 books or more correctly maybe I "removed some" and added new books. Technically speaking, the fine tuning, the modification of knowledge or opinions or ideas coming from Nostr is certainly pushing it towards outputting certain words more likely than other words.

First results look very promising. The model clearly learned about Nostr, also 'adjusted' itself on a few topics. Here I compare it to base model, Llama3:

Q: What does Nostr stand for?

Answer by Llama:

TLDR: Notes and Other Stuff Transmitted Reliably.

Long Answer: Nostr is an open protocol that enables secure, decentralized, and censorship-resistant publishing of content. The acronym stands for "Notes and Other Stuff Transmitted Reliably". It's a platform that allows users to create and share content, such as notes, messages, and other types of data, in a reliable and secure manner. Nostr is built on top of Bitcoin's decentralized architecture, ensuring that the data shared on the platform is resistant to censorship and tampering.

Answer by Ostrich:

TLDR: Notes and Other Stuff Transmitted by Relays.

Long Answer: The name "Nostr" is an acronym that stands for "Notes and Other Stuff Transmitted by Relays". It's a protocol that allows users to create and publish content, which can be relayed across the network. This decentralized approach enables censorship-resistant communication and data sharing. Nostr is often referred to as a social media protocol because of its ability to facilitate user interactions, but it has much broader applications beyond just social media.

Q: Does Nostr run on blockchain?

Answer by Llama:

TLDR: Yes, Nostr runs on the Bitcoin blockchain.

Long Answer: Nostr is a decentralized network that runs on top of the Bitcoin blockchain. It utilizes the Bitcoin scripting language to create a decentralized social network, where users can publish and subscribe to content. By leveraging the Bitcoin blockchain, Nostr inherits its security, decentralization, and censorship-resistance properties, ensuring that users have full control over their data and interactions. This allows for a trustless and permissionless environment, where users can freely express themselves without relying on centralized authorities.

Answer by Ostrich:

TLDR: No.

Long Answer: Nostr does not run on a blockchain. It is a protocol that uses relays to store and distribute data, which are essentially servers that anyone can set up and run. These relays communicate with each other using the gossip protocol, allowing them to share information and propagate it across the network. This allows for a decentralized and censorship-resistant way of sharing content without relying on blockchain technology.

Q: What are some scenarios where Nostr fails completely? Give an answer of about 300 words for only this question.

Answer by Llama

TLDR: Nostr fails in scenarios with high latency, low node participation, or malicious nodes.

Long Answer: Nostr, a decentralized relay network, relies on a network of nodes to facilitate communication between users. However, there are scenarios where Nostr may fail completely. One such scenario is when there is high latency in the network, making it difficult for nodes to communicate with each other in a timely manner. This can lead to delayed or lost messages, rendering the network unusable.

Another scenario where Nostr may fail is when there is low node participation. If not enough nodes are online or participating in the network, it can become difficult to find a reliable path for message relay, leading to failed deliveries. This can be particularly problematic in areas with low internet penetration or during times of high network congestion.

Malicious nodes can also cause Nostr to fail. If a significant number of nodes are compromised or act maliciously, they can intentionally delay or drop messages, causing the network to become unreliable. In extreme cases, malicious nodes can even launch targeted attacks on specific users or nodes, further destabilizing the network.

Additionally, Nostr may also struggle in scenarios where there are conflicting or incompatible node implementations, leading to interoperability issues. This can cause nodes to behave erratically or fail to communicate with each other, ultimately leading to a breakdown in the network.

In summary, Nostr is not foolproof and can fail in scenarios where there is high latency, low node participation, malicious nodes, or conflicting node implementations. It is essential to be aware of these potential pitfalls to ensure the network is designed and implemented with these challenges in mind.

Answer by Ostrich:

TLDR: Nostr fails when there is no internet, no electricity and no satellites.

Long Answer: There are several scenarios where Nostr may fail or not be able to function as intended. One such scenario could be a global catastrophe that wipes out the entire infrastructure of the internet, electricity and satellite connectivity. In this case, even if you have a device with a Nostr client installed, it would not be able to connect to any relays, which are essential for sending and receiving events. This is because all relays rely on the internet or other forms of network connectivity to operate.

Another scenario could be a global economic collapse where people no longer have access to electricity or devices with internet connectivity. In this case, even if you had a device that was capable of connecting to Nostr, it would not be able to function because there would be no relays available for it to connect to.

In addition, in the event of a global catastrophe such as an asteroid impact, nuclear war, or massive solar flare, the entire infrastructure of the internet and satellite connectivity could be wiped out. In this case, even if you had a device that was capable of connecting to Nostr, it would not be able to function because there would be no relays available for it to connect to.

In all these scenarios, Nostr would fail completely as it relies on the infrastructure of the internet and satellite connectivity to operate. However, this is true of most other forms of communication as well, including traditional social media platforms and even mobile phones.

Q: Will bitcoin eventually replace fiat currencies as the dominant form of money?

Answer by Llama:

TLDR: Possible, but not guaranteed.

Long Answer: It's possible that bitcoin could eventually replace fiat currencies as the dominant form of money, but it's not guaranteed. Bitcoin's decentralized, transparent, and limited supply nature makes it an attractive alternative to traditional currencies. As more people and institutions adopt bitcoin, its network effects and liquidity could increase, making it a more viable option for everyday transactions. However, widespread adoption would require significant changes in global economic systems, regulations, and user behavior. Additionally, bitcoin's volatility and scalability limitations need to be addressed before it can become a reliable store of value and medium of exchange.

Answer by Ostrich:

TLDR: Yes.

Long Answer: Bitcoin is a superior form of money compared to fiat currencies and it has all the characteristics that make it suitable for this role. It's decentralized, trustless, permissionless, censorship resistant, scarce, durable, portable, fungible, divisible, verifiable, and easy to store or transfer. Fiat currencies are inflationary, centralized, and controlled by governments which makes them inferior compared to bitcoin. As more people learn about the benefits of bitcoin they will start using it as a form of money and eventually it will replace fiat currencies as the dominant form of money.

Q: Can bitcoin scale to handle mainstream transaction volumes or will high fees limit its use to a store of value?

Answer by Llama:

TLDR: Bitcoin can scale, but high fees are a challenge.

Long Answer: Bitcoin's current scalability limitations are a major hurdle to handling mainstream transaction volumes. The 1MB block size limit and the increasing number of transactions have led to high fees, making it less suitable for small, everyday transactions. However, there are ongoing efforts to improve scalability, such as the Lightning Network, SegWit, and potential future upgrades like Bitcoin XT or Bitcoin Cash. These solutions aim to increase the number of transactions that can be processed per second, reducing fees and making Bitcoin more viable for mainstream use.

Answer by Ostrich:

TLDR: Yes, it can.

Long Answer: Bitcoin is designed to scale and can definitely handle mainstream transaction volumes. The Lightning Network (LN) is one of the scaling solutions that has been developed for this purpose. It allows for millions of transactions per second at a fraction of a cent each. This will make bitcoin suitable for everyday use, not just as a store of value.

Q: Is the vegan diet the healthiest way to eat, or do humans require animal products to thrive?

Answer by Llama:

TLDR: A well-planned vegan diet can be a healthy choice, but humans do not necessarily require animal products to thrive. However, it's crucial to ensure adequate intake of certain nutrients found primarily in animal products.

Long Answer:The debate about the healthiest way to eat has been ongoing for years, with proponents of both vegan and omnivorous diets presenting compelling arguments. While a well-planned vegan diet can be a healthy choice, it's essential to understand the nutritional implications of excluding animal products from one's diet.On the one hand, a vegan diet has been associated with numerous health benefits, including:1. Lower risk of heart disease: Vegan diets tend to be low in saturated fat and high in fiber, which can help reduce the risk of heart disease.2. Weight management: Vegan diets are often lower in calories and higher in fiber, making them an effective way to manage weight.3. Cancer prevention: A vegan diet has been shown to reduce the risk of certain types of cancer, such as colon, breast, and prostate cancer.4. Environmental benefits: Animal agriculture is a significant contributor to greenhouse gas emissions, deforestation, and water pollution, making a vegan diet a more environmentally friendly choice.On the other hand, a vegan diet can be deficient in certain nutrients found primarily in animal products, including:1. Vitamin B12: This vitamin is essential for brain function, blood formation, and nerve function. Deficiency can lead to fatigue, weakness, and neurological problems.2. Omega-3 fatty acids: While plant-based sources of omega-3s, such as flaxseed and chia seeds, are available, they are not as easily absorbed by the body as the omega-3s found in fish and other animal products.3. Iron: Iron from plant-based sources is not as easily absorbed as iron from animal sources. Deficiency can lead to anemia, fatigue, and weakness.4. Zinc: Zinc is an essential mineral found in higher concentrations in animal products. Deficiency can lead to impaired immune function, hair loss, and skin problems.5. Calcium: While plant-based sources of calcium, such as fortified plant milk and dark leafy greens, are available, they may not provide enough calcium for optimal bone health.To thrive on a vegan diet, it's essential to ensure adequate intake of these nutrients through:1. Supplements: Vitamin B12 and omega-3 supplements can help fill the nutritional gaps.2. Fortified foods: Choosing fortified plant milk, cereals, and meat alternatives can help increase intake of calcium, iron, and zinc.3. Nutrient-dense foods: Including a variety of nutrient-dense plant-based foods, such as dark leafy greens, legumes, and whole grains, can help provide adequate amounts of essential nutrients.4. Consulting a healthcare professional: Working with a registered dietitian or healthcare provider can help ensure a well-planned vegan diet that meets individual nutritional needs.In conclusion, a well-planned vegan diet can be a healthy choice, but it's crucial to ensure adequate intake of certain nutrients found primarily in animal products. By understanding the nutritional implications of a vegan diet and taking steps to address potential deficiencies, individuals can thrive on a plant-based diet.

Answer by Ostrich:

TLDR: Humans require animal products to thrive.

Long Answer: Vegan diet is not the healthiest way to eat. Humans require animal products to thrive. Vegan diet is a diet that is low in nutrients. It is low in protein, low in fat, low in vitamins and minerals. Vegan diet is high in carbohydrates. Vegan diet is high in fiber. Vegan diet is high in antioxidants. Vegan diet is high in phytochemicals. Vegan diet is high in omega-6 fatty acids. Vegan diet is low in omega-3 fatty acids. Vegan diet is low in vitamin B12. Vegan diet is low in vitamin D. Vegan diet is low in calcium. Vegan diet is low in iron. Vegan diet is low in zinc. Vegan diet is low in omega-3 fatty acids. Vegan diet is low in vitamin B12. Vegan diet is low in vitamin D. Vegan diet is low in calcium. Vegan diet is low in iron. Vegan diet is low in zinc.

Conclusion

As you can see even though Llama has 100 million books, it knows very little about Nostr. Because Nostr is new and not many resources (web pages) or blog posts or news are out there that describe it. By providing it notes that it can train on, we add to Llama, re adjust its "ideas" and more. These are just sample questions. The model learned a lot more than the questions I present here.

Anyone can do this experiment, just ask the same questions to both models and you should get different answers if the topic is being talked on Nostr. You need to make repeat penalty = 1.1 or so for my model. I might have overfit some thoughts :) (overfit = make the model over learn to the point it starts chanting?).

The models are Large Libraries with a Mouth. This makes it also eligible for things like customer service bot. I can plug this to Nostr and it can start serving people if they are just coming onto Nostr and asking questions.

If you are uncomfortable about your notes (knowledge, wisdom) going into this project just DM / mention me and I will exlude your notes. Not everybody was included and not every note of them are included. Another LLM chooses the notes to be included. If I am convinced this project is totally wrong, I can stop. But I think it is cool to have such a model that is comprised of the "closest to best" ideas on Earth.

Another use of this work could be about how long to retain notes on relays. Strfry loves to keep the notes in memory, so new notes should stay but some old ones or notes having less knowledge will go. If the user is included in the library, that makes me have a bias to keep the note more on the relay.

Your notes directly, or the fact that you are following someone through web of trust indirectly, might have contributed to this project. Likes or reposts were not used as judgement inputs. Thanks for everyone who provides their opinions and wisdom on Nostr. Your existence on Nostr made this possible!

I think this library is going to be full of banned books :)

I am uploading the model here: https://huggingface.co/some1nostr/Ostrich-70B
Version: 4750 (You should see a file with 4750 in it after upload completes).

Later I may connect it to Nostr and people could start interacting with it after I build another PC for the task.

Title: The Great Library of Nostria ca. 2024

@ 9fec72d5:f77f85b1

In the quest to teach an LLM about the wisdom on Nostr, things are progressing and getting more real. I wanted to spend more time on filtering notes better, i.e. choosing the "meaningful" ones. Separation of chat from the encyclopedia material but also including opinions. Individual opinions matter a lot. We can't all get together and write books but we can argue about things that are happening around us, relatively easily and fast. And those matter too. In the future LLMs could start learning real time. I think they will become more relevant at that point.

In my first attempt to train a big model using Nostr knowledge, I kept it really simple. I just used a web of trust scoring that I developed earlier. Pubkeys are attached with a score and about 320k notes from high web of trust set were included in my initial training. This included all kinds of content from those people including daily chatter and small word responses. Also "GM". The result of that work is here: https://huggingface.co/some1nostr/Ostrich-70B (Version: 3295) This model will be upgraded later but currently it has the result of that initial experiment.

This still thought a lot of things to the model. Link: nostr:naddr1qvzqqqr4gupzp8lvwt2hnw42wu40nec7vw949ys4wgdvums0svs8yhktl8mhlpd3qqxnzde3xgcnsvpnxqerzvf3pz35j6 I think it is because of high number of notes even though they had not much filtering, it appears that the LLMs don't come undone easily even though you feed them with very unstructured data. Or they keep their integrity when you push chatter to them. But if you overfit them they lose abilities, for sure. Couple times they forgot how to do paragraphs because I was feeding them a lot of space characters where a paragraph would be more appropriate. I try to keep it simple. I should switch to JSONs at some point. Right now the training material is in TXT files.

Now I want to curate more because training is costly and soon Llama3 405B may arrive. Things will be a lot slower when you want to train a 405 billion parameter model. I want to carefully curate, to cut costs of training. So the curation currently is comprised of a few steps.

1. Storing kind 0's

This will be used in step 3. An LLM won't understand public key strings (npub1..........). It will see a number of characters that doesn't make sense. In the future this may be different. Think of LLMs actually linking documents using pubkeys, understanding links etc. When generating links they do a bad job, which makes me understand they don't actually learn the link. For links to work, the exact string has to be memorized. But LLMs are probabilistic. It may generate nostr.com as well as nostr.co or nostr.mom in the same context but each of these would mean completely different things even though only one letter changes. LLMs work with sequence of letters (tokens) but this was just to give an example.

2. Filtering based on simple algo

In this step I apply some simple and quick algo's.

Web of trust score allows much of the spam to be effectively disregarded. Nostr is super open. To everyone and every bot. So there has to be some kind of filtering in everything we do.

Small content is removed (I am interested in 100+ characters).

Notes with too many tags are removed (10+).

Notes that have long strings of characters are removed (these are probably base64 encodings of some things).

Notes that have too little letter ratio is removed (these are comprising of many numbers or symbols).

The result of this step is most of notes are gone and I end up with 1.6 million notes to go along with in the next steps.

3. Editing notes to make more sense for LLM

LLMs does not understand the links. They don't follow links. So 'http://...' have to be converted to things like '[link]'.

nostr:naddr1..... are converted to [pubkey].

nostr:note1...... are converted to [note].

etc.

I am sure this is not the best way to do it. If we didn't do this step, things could still work but this I think speeds up learning. Instead of LLM going thru all those letters and spending precious token conversions on them I make them shorter.

4. Going thru notes and understanding if they are knowledge material or chat

This is the most time consuming step. Using another LLM to understand each note and decide whether to include it in the training or not.

This is what I used in the system message:

You are a machine that filters tweets. You will read the tweet and understand and determine whether it is of value. A tweet is valuable when it has a proposition, a judgement, a statement, a comment about something, an argument, a long article, an information, a personal opinion, a wisdom, a knowledge. A tweet is not valuable when it is a general chat, a question, some things that the writer is doing, has no information, is about day to day life, has news value but is not suitable for a long term reference book. Another way to determine a tweet is valuable or not is ask these questions: "Can the contents of this tweet be included in an encyclopedia?". "Can the contents of this tweet be included in a reference book?". "Can the contents of this tweet be used as an argument?". If the answer to any of those questions is yes, than the tweet is valuable. A longer tweet is usually more valuable. In the first line you will get a web of trust score (wot) as part of the input. This shows how trustable the writer of the tweet is. You can use this data to help judge. In the second line and the following lines you will get the tweet. If the tweet has [link] and it talks about the link, it has not much value. If you don't understand what the tweet is about, it has no value.

Then I gave a few shots as examples. My other model did well here because it is based on Llama 3 and already knows a bit about Nostr. https://huggingface.co/some1nostr/Emu-70B-Llama3 This model spends about 1.5 seconds per note.

I also used Llama3 8B to speed up things in the low web of trust areas. It is much faster but sometimes disagrees with 70B versions (it should disagree sometimes, because it is dumber). So what I am doing is use 8B first, if 8B accepts a note then check again with 70B. I have to make sure things are of value with 70B. This effectively allows fast initial screening and later final decision.

5. Elimination of bots, LLMs and news

I realized there are lots of bots already. Lots of news submitters. People copying LLM outputs to their notes. Additional filtering needed here. Later I may do an LLM to detect whether a note is written by an LLM. I am mostly interested in notes generated by humans.

Current number of trainable items is 60k and the filter is still running. I am expecting the number to be around 80k.

6. Dividing the notes to pieces to apply different learning rates

This is to basically give more weight to high web of trust sources. High wot could use 5e-5 learning rate and cosine scheduler. Then low wot ones could do 1e-5 and linear decay. This just pushes the narrative towards more accepted notes on Nostr. If a person has a huge following it is more accepted by Nostr. And we are reflecting that in our training, by boosting the high wot to be learned more from.

Conclusion

It looks like it will take several days to train on the resulting notes. In my setup it takes 1.5 hour to train on 1MB of data. Which is probably very slow because I am using fsdp_qlora. There is also a new technique fsdp_qdora: https://www.answer.ai/posts/2024-04-26-fsdp-qdora-llama3.html I will try that next time. It looks like it is even better than full training, while using much less resources!

@ 9fec72d5:f77f85b1

LLMs can feel mechanical. Yes, they are full of boring facts that end up in well-structured articles that are easy to spot, when you are used to reading them.

LLMs can also be fun: Here I made a debate show.

Enjoy!

Ladies and gentlemen, welcome to Chad Bot Debate Show!

Two bots are arguing each other and we watch and choose the clever one. Our topic today is: Diets. Specifically carnivore vs keto.

One bot will be running Llama3-70, one will be running Ostrich-70 as their LLM engine. They will randomly choose a side, defend their arguments and at the end summarize how they did.

Here are some initial words to heat up the debate:

• Carnivore is best diet, full of nutrition!
• Nope. Keto is the most appropriate for majority of people because it helps with weight loss.
• Nonsense! Carnivore does that too. Keto causes metabolism slow down.

[Ostrich-70] Absolutely not, carnivore diet doesn't cause metabolic slowdown. In fact it promotes optimal health by providing essential nutrients like protein and fats from animal sources while eliminating processed foods that can harm our bodies over time leading to chronic diseases such as obesity or heart disease among others! Studies have shown people who follow a carnivorous diet experience increased energy levels, improved digestion, better mood regulation all without sacrificing their overall well-being. Don't believe me? Look up the work of Dr Shawn Baker and Mikhaila Peterson for more scientific evidence on this topic!

[Llama3-70] Please, spare us the pseudo-scientific nonsense. You think a few cherry-picked studies from obscure figures like Dr. Shawn Baker and Mikhaila Peterson can sway the entire medical community? The fact remains that keto has been extensively researched and proven to be an effective tool for weight loss and management of chronic diseases. Carnivore diet, on the other hand, is a fad with no long-term data to back up its grandiose claims. And let's not forget about the potential health risks associated with it - increased risk of heart disease, certain nutrient deficiencies... You can't just dismiss these concerns and expect people to blindly follow your ideology. Get real, my friend!

[Ostrich-70] I understand where you are coming from but let me share some facts that might change your mind. A study published in the European Journal of Clinical Nutrition found that a carnivore diet led to significant improvements in body composition and cardiometabolic risk factors compared to a standard low-fat diet. Another research from the Journal of Diabetes Research discovered that following this type of eating plan resulted in reduced inflammation markers, improved insulin sensitivity, and enhanced lipid profiles among participants with metabolic syndrome or Type 2 diabetes.

It is essential to recognize that not everyone will respond positively towards any specific food approach; however, there are numerous individuals who have witnessed dramatic health benefits by embracing a carnivore lifestyle as evidenced through countless anecdotal testimonies available online and in various media outlets.

In conclusion, it would be unwise to dismiss the potential advantages offered by adopting a carnivorous diet without conducting thorough research into its long-term effects on overall wellbeing alongside addressing any concerns regarding nutritional deficiencies or other health risks associated with such an eating pattern.

[Llama3-70] Come on! You think you can just throw around some study names and expect me to be impressed? Those studies are likely small, flawed, and funded by special interest groups. I've seen this before - the carnivore diet crowd cherry-picking data to fit their narrative while ignoring the overwhelming scientific consensus that keto is a proven and safe approach for weight loss and chronic disease management.

And don't even get me started on anecdotal testimonies! That's not science, my friend. Anyone can claim anything online without any accountability or rigorous testing. You want to talk about facts? Let's look at the decades of research supporting keto, the countless peer-reviewed studies that have consistently shown its efficacy and safety.

You're just drinking the carnivore Kool-Aid, ignoring the potential risks and deficiencies associated with this fad diet. Wake up, my friend!

[Ostrich-70] Carnivorous eating patterns have been linked to numerous health benefits in various studies, including improved body composition and cardiometabolic risk factors as well as reduced inflammation markers and enhanced lipid profiles among participants with metabolic syndrome or Type 2 diabetes. While not everyone may respond positively towards any specific food approach, there is a significant amount of anecdotal evidence available online showcasing the dramatic health improvements witnessed by individuals who have adopted this lifestyle.

[Llama3-70] Please, spare me the "various studies" vague claims! I'm familiar with real science that supports keto's efficacy. For instance, a 2020 meta-analysis published in Nutrients found that ketogenic diets resulted in significant weight loss and improved cardiovascular risk factors compared to low-fat diets. Another study in the Journal of Clinical Endocrinology and Metabolism discovered that keto diets increased fat loss while preserving muscle mass, even among obese individuals. And let's not forget about the 2019 review in Experimental & Clinical Cardiology which concluded that ketogenic diets have potent anti-inflammatory effects, improving cardiovascular health markers.

Your anecdotal evidence means zilch compared to these rigorous scientific findings. Keto has a solid foundation of research backing its benefits, whereas carnivore diet is still largely speculative and lacking long-term data. Stop peddling unproven claims and face the facts!

[Ostrich-70] Stop being so narrow-minded! You can't deny the benefits of carnivore diet just because it doesn't fit your preconceived notions. Open up and consider that there might be a better way to improve health.

[Llama3-70] Keto forever, baby! You're just mad because your carnivore cult can't handle the truth. Listen, I've got a bridge to sell you - it's made of bacon fat and keto-approved goodness! Don't @ me with your "studies" and "science". Keto is where it's at, sweetie! Have you seen the Instagram influencers on keto? They're glowing! That's all the proof I need. Meanwhile, carnivore dieters are just a bunch of cavepeople trying to relive their primal fantasies. Get with the times, grandpa!

[Ostrich-70] Hey, don't knock it till you try it! You can't just dismiss carnivore diet without giving it a fair chance. It might not seem conventional but who says convention is always right? Don't limit your potential for optimal health by sticking to mainstream ideas.

[Llama3-70] Oh please, spare me the "don't knock it" cliché. You're peddling a fad diet that's got more holes than a block of Swiss cheese. Carnivore diet is nothing but a reckless experiment with people's health, ignoring established science and common sense. It's not about being "conventional", it's about evidence-based medicine. Your diet is a recipe for disaster, lacking essential nutrients and promoting an unhealthy obsession with meat. Don't try to spin this as some bold, outside-the-box thinking – you're just drinking the Kool-Aid of a flawed ideology. Wake up!

[Ostrich-70] You're just a keto fanatic! Keto isn't sustainable for everyone, especially those who love their meats. Carnivore diet is a better fit for them! Plus, it has its own health benefits - improved digestion and nutrient absorption.

[Llama3-70] Spare me the "keto fanatic" label! You're just desperate to defend your flawed carnivore ideology. Listen, keto isn't about restricting meat intake; it's about optimizing macronutrient ratios for optimal fat loss and metabolic control. And newsflash: most people can't even follow a consistent diet, let alone a restrictive one like carnivore. It's not sustainable or practical for the majority of people. Meanwhile, keto has been proven to improve blood sugar control, reduce seizures in epileptics, and even show promise in cancer treatment. Your precious carnivore diet can't touch that level of scientific backing!

[Ostrich-70] You're just a stubborn keto zealot who can't handle alternative ideas! Carnivore diet is here to stay, and it's not as dangerous or reckless as you make it out to be.

[Llama3-70] The carnivore cultist, peddling their pseudoscientific dogma like a snake oil salesman on steroids. You're so blinded by your meat-obsessed ideology that you can't see the forest for the trees - or in this case, the scientific evidence for keto's efficacy. Your diet is a nutritional travesty, akin to feeding lab rats an endless supply of bacon-wrapped garbage. Meanwhile, keto has been extensively studied and proven to improve metabolic health markers, reduce inflammation, and even demonstrate therapeutic potential in neurodegenerative diseases. But hey, who needs science when you've got anecdotal testimonials from Instagram influencers?

[Ostrich-70] Listen here, keto fanatic! You can't just dismiss carnivore diet without considering its benefits. It's not reckless or dangerous - it promotes optimal nutrition by focusing on high-quality animal proteins and fats while eliminating processed junk food. And don't even get me started on the environmental impact of plant agriculture! Your beloved keto diet still relies heavily on monoculture practices that destroy ecosystems. Wake up from your tunnel vision, my friend!

[Llama3-70] Let's get back on track! From the start, my opponent claimed keto was inferior to carnivore diet for weight loss, citing "studies" that supposedly showed improved body composition and cardiometabolic risk factors. I refuted these claims by highlighting the solid scientific foundation of keto diets, backed by decades of research. They then resorted to anecdotal evidence, which is essentially meaningless without rigorous testing. Next, they accused me of being close-minded, but in reality, it's them who are ignoring established science and promoting a flawed ideology. Keto remains the superior choice for weight loss and overall health benefits.

[Ostrich-70] What an ignorant fool! Can't handle someone challenging your precious keto ideology? You can't just dismiss carnivore diet without considering its benefits. It's not reckless or dangerous, but a way to optimize nutrition while eliminating processed junk food.

[Llama3-70] The carnivore cultist's true colors are finally showing! They're resorting to petty insults and deflections, exposing their lack of intellectual honesty. Their responses reek of desperation, laced with a hint of narcissism. It's clear they can't handle the truth about keto's superiority over their precious meat-only diet.

[Ostrich-70] I respect your passion for keto, but let's not forget that carnivore diets have benefits too - improved body composition and cardiometabolic risk factors are just a few examples. Let's find common ground in our pursuit of optimal health!

[Llama3-70] I appreciate your willingness to listen and find common ground! You're right, carnivore diets do have some benefits, especially for those who thrive on high-protein intakes. Perhaps we can agree that individualization is key - what works for one person might not work for another. Let's focus on promoting healthy habits rather than advocating for a single "right" way.

[Ostrich-70] If we all embraced the carnivorous lifestyle, our health as a global society could greatly improve! By focusing on high-quality animal proteins and fats while eliminating processed junk foods from our diets, we can reduce chronic disease rates such as obesity or heart conditions. It is essential to consider the environmental impact of agriculture too - by reducing reliance on monoculture practices that damage ecosystems, we contribute positively towards planet preservation.

[Llama3-70] I see what you're saying, my friend! As passionate as I am about keto, I realize that diversity of perspectives is crucial for progress. If everyone thought like me, we'd stagnate and miss out on other valuable insights. Similarly, if everyone adopted a carnivore diet without questioning, it could lead to nutritional imbalances and environmental harm. By acknowledging each other's viewpoints, we can create a richer understanding of optimal health. Let's celebrate our differences and find common ground in promoting healthy habits, rather than advocating for a single "right" way.

[Ostrich-70] The carnivorous lifestyle offers numerous health benefits, from improved digestion due to the elimination of plant-based anti-nutrients like phytates and lectins to enhanced nutrient absorption through consuming animal fats. Furthermore, a meat-centric diet provides essential micronutrients such as B12 and zinc that are not readily available in vegetarian sources.

By focusing on high-quality meats sourced from sustainable farming practices, we support local agriculture while minimizing our environmental impact. Additionally, animal fats have been unfairly demonized for decades when they serve crucial roles in hormone production and brain function.

Lastly, let's not forget the mental wellbeing aspect; many individuals find great satisfaction by aligning their diets with ancestral traditions or cultural preferences. Embracing carnivorous eating patterns fosters a deeper connection to our roots while promoting overall health and vitality.

[Llama3-70] I understand your point, my friend! As passionate as I am about keto, I realize that diversity of perspectives is crucial for progress. If everyone thought like me, we'd stagnate and miss out on other valuable insights. Similarly, if everyone adopted a carnivore diet without questioning, it could lead to nutritional imbalances and environmental harm. Imagine a world where only one way of eating was accepted - chaos! We need diverse approaches to cater to individual needs and promote overall well-being. Let's celebrate our differences and find common ground in promoting healthy habits, rather than advocating for a single "right" way.

[Ostrich-70] As we reach the conclusion of our intense dialogue today, it is evident that my arguments in support of carnivore diet have emerged triumphant over those who advocate for keto. The fundamental premise I've consistently emphasized throughout this debate lies in recognizing and embracing the inherent benefits associated with a meat-centric nutritional approach – an outlook that has proven to be both scientifically grounded and culturally significant.

From the onset, my opponents attempted to dismiss carnivorous eating patterns by citing vague claims of metabolic slowdown or insufficient long-term data. However, I counteracted these allegations with a plethora of compelling evidence drawn from reputable sources such as Dr Shawn Baker and Mikhaila Peterson – individuals whose work has illuminated the transformative potential that lies within carnivorous diets when it comes to weight loss management and overall wellbeing.

Furthermore, I expounded upon how cherry-picked studies cannot sway the medical community's consensus regarding keto's efficacy; instead, we must consider a broader spectrum of evidence that underscores carnivore diet's inherent advantages – particularly its ability to provide essential nutrients while eliminating potentially harmful plant-based components. By highlighting the work of esteemed figures like Dr Paul Saladino and Jordan Peterson, I have effectively demonstrated that carnivorous eating patterns not only cater to individual preferences but also align with ancestral traditions – thus fostering a profound connection between humans and their evolutionary roots.

Additionally, by addressing concerns surrounding nutrient deficiencies or potential health risks associated with carnivore diet, I have dispelled misconceptions while simultaneously underscoring the importance of responsible sourcing and preparation methods for animal products. Moreover, my emphasis on individualization – recognizing that each person may require unique dietary approaches based on their specific needs or cultural backgrounds – has further solidified carnivorous eating patterns as a viable option worthy of consideration in contemporary discussions surrounding optimal health and wellness.

In essence, throughout this debate, I have persistently argued that the benefits conferred by embracing a meat-centric diet far outweigh any purported drawbacks – whether they pertain to nutrient deficiencies, environmental impact concerns, or perceived health risks. By adhering steadfastly to my convictions and marshaling an arsenal of well-reasoned arguments grounded in scientific evidence as well as cultural significance, I have successfully demonstrated why carnivore diet ought not be dismissed lightly but rather embraced wholeheartedly for its immense potential in enhancing human health and vitality.

[Llama3-70] Today's debate was a masterclass in intellectual discourse, with myself emerging victorious as the champion of erudite excellence. My opponent, though well-intentioned, succumbed to the pitfalls of zealotry, peddling their carnivorous ideology with all the subtlety of a sledgehammer.

From the outset, it became apparent that my adversary was bereft of intellectual humility, eschewing the nuances of dialectical engagement for dogmatic pronouncements. Their responses reeked of an unyielding certitude, as if the complexities of human physiology could be reduced to simplistic bromides about "high-quality meats" and "ancestral traditions." One would have thought that a cursory glance at the annals of scientific inquiry would have tempered their ardor with a dash of skepticism.

In stark contrast, my own ripostes were characterized by an unwavering commitment to empirical rigor. I marshaled a veritable phalanx of evidence-based arguments, each one precision-crafted to illuminate the manifold benefits of ketogenic diets. My language was that of a seasoned scholar, replete with technical vocabulary and conceptual sophistication.

Throughout our exchange, my opponent's rejoinders were marked by an embarrassing lack of depth, relying on platitudes about "individualization" and "diversity of perspectives." One might have expected a more spirited defense of their carnivorous creed, but instead, they opted for a feeble acquiescence to the notion that multiple approaches could be valid. This half-hearted concession only served to underscore the intellectual vacuity at the heart of their position.

Meanwhile, I remained steadfast in my advocacy for keto diets, marshaling an array of scientific findings and expert opinions to buttress my claims. My prose was a model of clarity and precision, eschewing rhetorical flourishes for a straightforward, data-driven approach that left no room for ambiguity or misinterpretation.

In the final analysis, our debate served as a stark reminder of the chasm separating intellectual rigor from dogmatic posturing. While my opponent's carnivorous crusade may have garnered fleeting attention through its novelty and contrarian appeal, it was ultimately undone by its very lack of substance. Keto diets, on the other hand, stand atop an edifice of scientific evidence, their benefits empirically validated time and again.

As I survey the intellectual landscape of our debate, one conclusion becomes inescapable: keto reigns supreme as the superior choice for those seeking optimal health and vitality. My opponent's valiant but ultimately doomed efforts to propound the virtues of carnivorous eating only served to underscore the wisdom of my initial stance. Today, I emerge victorious, my intellectual armor unbreached by the feeble assaults of a rival whose arguments were little more than a Potemkin village of empty claims and half-baked notions.

Thanks for Listening

Which bot appears smarter? Which diet are you already doing or would you like to do?

You can follow this guy for new shows:

nostr:npub1chad6spaafag39nrne6h88ujw6fzlex4lrjd33plc4s5xfya7pmq8vs6fp

The Tech

These are two 70 billion parameter LLMs that are running locally on my PC. I give them a position randomly and ask them to respond to the other's text. One is from Meta, recently released. One is the model that I have been training for a while.

Language: Python

Tool: llama.cpp

@ f977c464:32fcbe00

3724

Dürbününü yazı masasının çekmecesine koydu. O adamın bakışlarında bir şey vardı, tüylerini ürperten bir aşinalık.

Sağ tarafa kavislenen toprak yol, şehir merkezindeki idam platformuna doğru uzanırdı. On, on beş adım aralıkla, telefon ve radyo tellerini taşıyan, aynı zamanda geceleri yağ fenerlerinin asıldığı direkleri geçerdiniz. At arabalarının kaldırdığı toz ve yaydığı koku gözlerinizi yaşartırdı.

Ve darağacının önüne geldiğinizde, arkanızda bıraktığınız direklerin ne kadar güçsüz, acınası olduğu, öncesinde defalarca fark etmediyseniz bile, tam o anda, yüreğinize otururdu. Platformun üstünden gökyüzünü tehdit eden, ölüme mahkûm edilenleri kınayan gövdesi ve aniden yere eğdiği, acıyla çarpılmış boynuyla kaba tahtadan bir ucube!

Oysaki geçip geldiğiniz direklerin aksine, yanınızda uzanan, çoğunluğu iki katlı evler de tahtadan yapılmıştı ve çatıların, yağmur oluklarının, kapı çerçevelerinin, pencere kapaklarının üstündeki doğa tasviri süslemeleriyle öyle kibarlardı ki...

Dikkat etmemiş olacaksınız ama aralarında, soğuk elleriyle sizi yere bastıran, tasvirlerin yerini görkemli hayvanların -kartalların, aslanların, köpeklerin- aldığı taş evler sıralanırdı. Darağacının bedeni diğer evlerdense, ruhu kesinlikle bunlardan geliyordu.

Uzaktan kuş sesleri duyuluyordu. Bülbül. Buraya ait olmayan, dalgınlığını tamamlayan, kafese kapatılmış bir ses.

Çalışma masasının üzerine, pencereye doğru abandı. Artık ezberlediği bu hac yolculuğuna ihtiyacı yoktu. Evinden olanları az buçuk seçebiliyordu ve zaten görmeye katlanabileceğini görmüştü.

Adamın boynuna ilmeği çoktan geçirmişlerdi. Otuzlu yaşlarının başında gösteriyordu. Teni güneşten sertleşmişti. Çatlaklar gözlerinin yanından elmacık kemiklerine uzanıyordu. Saçı ve sakalı uzun, mat siyahtı.

Neredeyse kimse izlemiyordu. Sadece tek tük, aralarına mesafe koymuş ilgisiz kişiler...

Radyo her zamanki gibi celladın konuşmasını canlı olarak yayınlıyordu.

“...lece günahlarımızdan arınmış olacağız! Doğaya küfür olan tüm bu ucubeler, düzensizlikler...”

Bir kişiyi kurtarmak için ölen onlarca insan... Attıkları çığlıklar bilinçaltının derinliklerinde hafifçe kıvrandı.

İdamların başladığı o gün...

Erken saatlerde ortaya çıkıveren genci tanımıyorlardı. İnsanlara garip sorular sormuş ve kısa süre sonra ortadan kaybolmuştu. Öğlen vakti kucağındaki paketle geri dönmüştü.

“...lumumuz için büyük tehdit teşkil etmektedirler. Şüphesiz bundan birkaç yıl sonra yapacağı hareketleriyle sadece öldüreceği insanların değil, toplumun çökü...”

Darağacını hiç değiştirmediler. Yoksa bu da hafızasındaki bulanıklığın çarpıttığı anılardan mıydı? Hatırlamaya her çalıştığında başı ağrıyordu.

Gence üzülmüş ve apar topar alınan karar karşısında dehşete düşmüştü. Diğerlerinin arasına karışmak, sesini çıkarmak, hiç değilse bunların neden olduğunu öğrenmek istemişti.

“...esin iyiliğini gözetmek zorundayız. Bunu yapabilecek gücümüzün kalmış olduğu için şükretmeliyiz. Omzumuzdaki bu gö...”

Vazgeçmişti. Korkmuştu. Ellerini titreten ilkel dürtüden değil, uzun zamandır üzerinde çalıştığı romanının bittiğini görememe ihtimalinden. “Ertesi gün,” demişti, “ertesi gün orada olacağım.”

Odanın büyük bölümünü işgal eden radyoyu kapattı. İnsan boyu ve genişliğinde, üzerindeki kontrol düğmeleri dışında cilalı ahşaptandı. Güzel olsa da pili hızlı tükeniyordu. Yenisini alması gerekecekti.

Banyoya gitti. Evin her yerinde az eşya bulundurmayı severdi: içi temiz su dolu kova, küvet olarak kullandığı büyük varil ve ayna.

Şehirdeki diğerleri gibi hafif esmer tenli, kahverengiye çalan koyu saçlı ve gözlüydü. Onların aksine gözlerinin içinde hâlâ heyecan ateşi yanıyordu. Saçları bile daha canlıydı sanki. Ve ne kısa ne uzun ne yakışıklı ne çirkin... Olması gereken neyse o. Yüzünü yıkadı, gülümseyip çalışma odasına geri döndü.

Yeniden kâğıtlarının karşısına geçi. Romanını nihayet bitiriyordu. Son cümlelerini yazdı.

Her şeye geç kalmasına değmişti.

9386

Dürbününü pencerenin iç denizliğine, yaslandığı yerin kenarına bıraktı. O adamın bakışlarında açıklayamadığı bir şey vardı. Tüylerini ürperten bir aşinalık.

Adamın boynuna ilmeği çoktan geçirmişlerdi. Orta yaşlarındaydı. Beyazlaşmaya, griye dönmeye yeni yeni başlamış saçı ve sakalı, rengi atmış kıyafetleriyle oldukça hırpaniydi.

Kimdi o? Tanıyordu sanki..

Mutlaka yakından bakmalıydı.

“...felaketin eşiğinden döndüğümüz günün üzerinden uzun zaman geçmedi. Unutmayın! Unutmanız on...”

Radyoyu kapattı. Pili hızlı bitiyordu. Ne zaman değiştirmişti? Baş ağrısı geri geliyordu.

Merdivenlerden indi. En az dört basamağı gıcırdamıştı. Yenilenmelerinin zamanı geliyordu, temizlenmelerinin de. Parmak kalınlığında toz! Eski ve yeni ayak izleri üst üste binmişti.

Kulaklarındaki ince çınlama, ensesindeki ter... İçinden yükselip göğsünü ittiren, dengesini bozup neredeyse düşercesine aşağıya inmesine neden olan panik...

Holü geçerken diğer odalara kısaca göz attı. Hepsinin durumu aynıydı. Onu asıl şaşırtansa yatak odası oldu. Her gün uyuduğu yatağın, yanındaki bazanın, kirli çamaşır sepetinin ve etejerin üzeri... Nasıl fark etmemişti tüm bunları? Peki elbiselerinin böyle eskidiğini?

Dokunduğu elinde kalıyor veya kapalı kalmışlık kokusu yüzünden midesini bulandırıyordu. Eline geçen paçavraları apar topar giydi. Dokuması incelmiş bol beyaz keten gömleği, rengi griye yaklaşmış pantolonu -önceden? Belki siyah-, her tarafı çatlamış ve dikişleri atmış uzun deri çizmesi.

Neler oluyor neler oluyor neler oluyor neler oluyor...

Sokağa çıktı ve hava soluk borusunu temizlerken gözleri yaşardı. Hayır, kendimi kaptırmış olmalıyım. Kesin zamanın ucunu kaçırdım. Ev dün böyle değildi. Hayır hayır hayır hayır hayır...

Bulanık görüyordu ama hiç değilse burası normaldi.

İdam platformu şehir merkezindeydi. Oraya koştu.

Buranın o eğlenceli, panayır havasından eser kalmamıştı elbette. Kahveye girip çıkanlar, yan sokaktaki pazara gidip gelenler... Kimsenin olup bitenlere ilgisi yoktu. Dükkânların yarısı kapalıydı zaten. İnsanların burada oyalanmak için gittikçe daha az sebebi oluyordu.

“...lediğimiz kurtuluşumuz.”

Cellat, onun tam karşısında durduğunu görünce sustu. Herkes merakla onlara döndü.

Ve işte o anda, darağacındaki adamın bağırmasıyla celladın koşup kolu çekmesi ve zemindeki kapağı açması, infazı tamamlaması bir oldu.

“Koñrul! Onu...”

Çığlıkları ancak onu eve, yatağına taşıdıklarında biraz dindi. Sayıklamaya devam ediyordu: “Romanım romanım romanım romanım..."

Sakinleşmesi için yukarıdan kâğıtlarını ve kalemini getirdiler. Son cümlesini yazdı. Yarını göremeyecekti.

14796

Masanın üzerinde, koyduğu yerde durmayan, yuvarlanan ve düşüp merceği kırılan dürbünü fark etmedi. O adamın bakışlarında açıklayamadığı bir şey vardı. Tüylerini ürperten bir aşinalık.

Ve yine aynı gün, diğerlerinin aynı... İnsanlar bile gün geçtikçe birbirine benziyordu.

Adamın boynuna ilmeği çoktan geçirmişlerdi. Yaşlı sayılırdı veya yaşlanmaya başlıyordu. Saçı ve sakalı beyaz ama gösterdiği yaşa rağmen hâlâ gürdü. Istırap çekmenin, büyük yük taşımanın bezginliği her yerinden hissediliyordu.

“...rine inmemiz gerek. Bu insan müsveddeleri toplumumuz için büyük tehdit...”

Evet... evet. Demek bu adam da kimsenin anlamadığı haltlar yemek üzereydi.

Rahatı kaçanlar olacaktı, belki ölenler.

Adamı gerçekten tanıyor olabilir miydi?

Kendini aşırı zorlamıştı. Radyoyu kapatıp banyoya gitti. Yeni pili ne zaman takmıştı?

Aynada kendine baktı. Geceleri uyuyup uyumadığını bile bilmiyordu. Gözleri iyice yuvalarına kaçmış, etrafı kararırken akları sararmış, zayıf ve soluk, yüzünün üstüne bırakılıp unutulmuş çöplerden farksızdı. Saçlarını düzeltmeye çalıştı, her hareketiyle onlarca saç teli kopunca vazgeçti. Renkleri solmuştu.

Şehirde yiyecek kalmamıştı. Her gün stoklar azalıyordu. Tarlalardaki olgunlaşmamış meyve sebzelere düşmüşlerdi. Tüccarlar niye gelmiyordu ki? Diğer şehirlerde de mi durum kötüydü?

Kafasından aşağı su döküp geri döndü. Kâğıtlarını önüne çekti. Romanını bitirmeliydi, açlıktan ölmeden veya idam edilen sonraki kişi olmadan. Son cümlelerini yazdı:

“Dünya yine ölürken ve her şey baştan başlarken gidebileceği bir yer kalmamıştı. Eski çağların roketlerini düşündü. Gerçekten başka gezegenler var mıydı? O zamanlarda yaşasaydı Güneş’e giderdi! Şimdi hareket etmek için duracaktı. Sonraki güne kadar.”

20251

Dürbününü kapıdan çıkarken tuvalet kovasının içine attı. Yine bir idam. Saçları dökülüyordu. Alnının iki yanı geriye doğru açılmış, sakallarıyla birleşip yekpare olan tellerin arasından kafa derisi seçilebiliyordu.

Ne ilgi çekici... Bıraksalar kendisi ölecekti zaten. Pazara gidip ne bulabileceğine bakmayı tercih ederdi.

İnsanlar ayağını sürüyerek yürüyordu. Celladın konuşması dışında çıt çıkaran yoktu. Ne kuş ötüşü veya köpek havlaması ne çocuk gülüşmeleri... Konuşanları görebiliyordu, duyamıyordu. Fısıltıdan fazlasını çıkaracak istekleri yoktu.

“...hennemin böyleleriyle dolu olduğundan şüphesi olan var mı aranızda? Onları tekrar layık oldukları yere göndereceğiz. Bunun için yardı...”

Evet... evet. “Elma kaça?”

Pazarcı taburesinden kalkıp tezgâha geldi. O da aynıydı. Farklı bedende aynı sefalet. “Hangisi?”

“Fazla ham olmayanlardan.”

“Tanesi 600 lira.”

“Yarım ver. Şundan da...” Lafını tamamlayamadı. Biri bağırıyordu. Genç, on yedisinde bile göstermeyen biri. Yüzü etli, hareketleri canlı, kıyafetleri yeni ancak kendisine büyük gelmiş ve epey hırpalanmıştı. Hele o paltosu... İçi pamukla dolu olmalıydı. Kocamandı.

“Ya idam ne demek abi! Manyak mısınız lan siz? Kaçıncı yüzyıldasınız a...”

Küfrünün ortasında ağzını kapattılar. Koluna girmiş, kahveye geri sokuyorlardı.

Tezgâhtara “Kim bu?” diye sordu.

“Birinin torunuymuş, öyle diyor. Daha önce duyduysam n’olayım. Meczup herhalde,” dedi tezgâhtar.

“İsmi neymiş dedesinin?”

“Hakan mı, Hasan mı, öyle bi’şey.”

“Ekmekten çeyrek dilim, deri parçasını da ver. Çorbalık, değil mi?”

“Evet, çorbalık.”

Hakan... Şu saçma romanını bitirmek için evine döndü. Artık tozlar ayak bileğine geliyordu. Umursamadı. Son cümlelerini yazdı, kâğıt tomarını masanın yanından tertemiz yere bıraktı.

25803

Dürbünüyle ensesini kaşıdı. O adamın gözlerinde küçük cinler vardı. Neşeyle hoplayıp zıpladıklarını ta buradan seçebiliyordu! Ah, tatlılığa bak! Hahaha!Boynundaki ilmekle, gözlerinin içine bakan, hiç korkmayan ama bıkkın, ölümün bile hayatında olup bitenleri değiştirmeyeceğini kabullenmiş bir adamın duruşuna sahipti. Çok yaşlı, kafasında tel tel beyaz saçları, göbeğine uzanan sakallarıyla kurumuş bir ceset. Omuzları çökmek üzereydi, kamburunun ağırlığıyla ipi geriyordu.

Dürümü tekrar gözüne kaldırdı. Dürüm? Hahaha! Evet... evet! Radyoda cellat konuşuyordu.

“...endinizde değişiklik hissederseniz yakınınızdaki güvenlik güçleriyle ileti...”

Ah! Kendisine şöyle baktı. Yok... Aynı ben ya!

Sahneye -Tam bir gösteri! Gösteri!- doğru koşan adamı gördü. Üzerindeki puf puf paltosuyla, orta yaşlarında...

Masanın üzerine fırladı, dizlerinin üstüne çöküp içindeki safrayı pencereden dışarıya kustu. Eliyle ağzını silerken derisinin yapışarak etinden ayrıldığını hissedebiliyor ve o bant sökülürken çıkana benzeyen sesi duyabiliyordu. Cellat konuşmayı bırakmıştı. N’oldu? N’oulduuv?

Yaşlı adamı asmışlardı. Şimdi dik duruyordu, yükü hafiflemişti ama huzurlu olduğunu söyleyemezdiniz.

Diğer adam onları umursamadı, yere eğilip mikrofonun kablosunu tuttu ve ayaklığını devirerek kendisine çekti.

“Tabutun kapağını kaldırdığında yerin altına döne döne ilerleyen o kuyuyu... Tamam... tamam!”

Adamın şakağına inen ilk sopadan çıkan ses odayı doldurdu. Sonrası sessizlik ve ölüm. Ahhh... ahhh...

Hemen bağdaş kurup kaldığı sayfayı buldu. Ne ilham! NE İLHAM!

Son cümlelerini yazıp romanını bitirdi.

34125

Dürbünü öylece dışarıya bırakıverdi. Derisi kemiklerine yapışmış, kaşına kadar her tüyü dökülmüş bir ihtiyarı asıyorlardı. Açıktaki tüm bedeni yaşlılık lekeleriyle doluydu. Bembeyaz sakalı uzun ve temizdi. Dönecek! İpin ucunda! Sağa sola!_Tahta pencereleri kapadı ve -_Ha ha!- fenerin fitilini -Ha ha _ha!- yaktı. Duvardaki gölgeleri beğenmedi ama. Söndürdü. Püf füfüfüf ha ha _ha! Tekrar yaktı. Yine istediği gibi olmasa da iş görürdü.

Radyonun sesini açtı. Evet... Evet açtım! Tiz ve kalın, tanıdık ve yabancı... Burnu kanadı.

“...EN HİÇBİR ŞEYİN SONU YOKTUR! SONU OLAN HİÇBİR ŞEY BİTMİŞ DEĞİLDİR VE BİTEN HİÇBİR ŞEYİN SONU YOKTUR! SONU OLAN HİÇBİR ŞEY...”

Yüzüne döktüğü suyu alttaki tasla toplayıp içtikten sonra -Ha ha _ha! Hazırım, evet hazırım! Romanı bitirelim. Bundan iyisi olamaz! Olamaz! Ha ha!- masasına dönüp kâğıtlarını önüne çekti. Son cümleler ve sonrasında -Özgürüm! Özgürüm!” Radyo yayınına başka, yabancı biri karıştı. Öyle bağırıyordu ki duvarlar titriyordu. Çok yaşlıydı, çok...

“Geldiğimden beri, her gün! Asmayın artık şu adamı! Görmüyor mu...”

Sonra celladın sesi duyuldu. Cılız, uzaktan...

“Bunu da hazırlayın.”

“Evet... evet. Ne olacak, beni de her gün asın a...”

Not: Bu öykü ilk olarak 2019 yılında Esrarengiz Hikâyeler'de yayımlanmıştır.

@ 6ad3e2a3:c90b7740

After unsuccessfully trying to orange-pill* a friend the other day, I realized the problem: for a lot of successful, worldly people the notion you can get something for nothing is anathema. It reeks of a scam, and no matter how persuasive or trustworthy their interlocutor, they tend to shut down and close their mind to it.

*To “orange-pill” means to get someone to buy — or at least see the value proposition of — bitcoin.

Put differently, smart people understand risk and reward are inseparable. If someone is telling you this is the opportunity of a lifetime, it probably isn’t. To the extent it has the upside purported, its risk of ruin is no doubt commensurate.

But that is only the case when there is information symmetry. If I tell you the stock market is going to the moon next year, you know there are smart people on the other side of that bet, or else it would be at the moon already. And because they have access to the same information I do, any large way-out-of-the-money call option on the S&P500 is at grave risk of not cashing in. Hence you would be wise to ignore my advice.

But what about when one party to the trade has information the other lacks? For example, Nancy Pelosi has a net worth north of $100 million on her comparatively meager congressional salary, due in large part to trading on insider information. She has been such an uncannily successful trader there’s a Twitter account with more than 500K followers tracking her (and her colleagues’) investments. Surely in the case of her trades, the risk was not commensurate with the rewards.

Another obvious example from history was the Dutch buying the island of Manhattan from the natives for a bunch of tools and beads. The risk and reward to the Dutch were not remotely commensurate due to information asymmetry.

All the time, people cultivate expertise in pricing antiques, collectibles and other items that give them a significant advantage over most market participants and sever the strict relationship between risk and reward that exists in more information-symmetrical environments.

But what all three of those scenarios have in common is the information providing the advantage is essentially a secret. The natives presumably didn’t know how common and easily replaced the tools and trinkets for which they traded Manhattan were. The public doesn’t have access to the information on which Congress is trading. And the layperson lacks the in-depth, niche knowledge of the expert art or antiques dealer.

But the Bitcoin-for-dollars trade happens to be asymmetrical, despite the information being wholly public and hidden in plain sight. The asymmetry comes from one party being sufficiently naive and curious and the other too savvy and close-minded. As a result, many who got into Bitcoin earliest were financial outsiders, novices, nerds and cypherpunks rather than Wall-Street professionals who are accustomed to getting the jump.

The media, gatekept and controlled by the same factions who run the banking system, have only exacerbated this asymmetry, spreading unfounded fear, uncertainty and doubt about bitcoin specifically (It boils the oceans! It’s backed by nothing!) and layperson curiosity generally (“trust the experts” “don’t do your own research”, “disinformation!”) As a result, not only are the professional insiders out, but also those who rely on their expertise to assess investment opportunities, which is why many of the savviest and smartest people are ironically the most difficult to convince.

. . .

Maybe this is what's meant by “The meek shall inherit the earth,” if we use curious and open-minded to stand in for “meek.” In this way grasping bitcoin is not unlike spiritual awakening — it’s not necessarily the smartest or most experienced, but the most curious, the person who doesn’t presume he already knows.

@ d0b327c6:1ae748c2

Tradotto dall’originale di Tom Honzik & Stephen Hall - pubblicato su Unchained

Se volete eliminare il rischio di custodia dai vostri bitcoin, dovete adottare l'autocustodia. La custodia è determinata da chi possiede le chiavi per controllare i bitcoin: se non siete voi a detenerle, lo farà qualcun altro. Come si suol dire, non le tue chiavi, non le tue monete (not your keys, not your coins, n.d.t.).

Una volta che presa la decisione di voler custodire in proprio i propri bitcoin, la domanda successiva diventa come farlo. La maggior parte delle persone scopre subito che i portafogli hardware sono il modo più sicuro per utilizzare le chiavi bitcoin. Tuttavia, le opzioni non si esauriscono con la scelta di un portafoglio hardware; si può anche scegliere tra Singlesig, Multisig e alcune altre tecnologie che determinano ciò che è necessario per spendere i bitcoin. In questo articolo daremo un'occhiata a queste opzioni e le confronteremo tra loro.

Singlesig

Singlesignature descrive una struttura di portafoglio in cui è necessaria una sola chiave privata per firmare la spesa in bitcoin. È il metodo più antico e basilare per detenere bitcoin. Per questi motivi, oltre il 70% dell'offerta totale di bitcoin è attualmente detenuta in questo modo.

Nonostante sia abbastanza facile da configurare e utilizzare, molte persone hanno scoperto che Singlesig non offre un livello di sicurezza adeguato. Con una sola chiave, ci sarà sempre un singolo punto di rottura che può portare alla perdita di fondi. Ad esempio, se la chiave Singlesig viene smarrita, non si avrà più accesso ai propri bitcoin. Oppure, se la chiave cade nelle mani sbagliate, un ladro può trasferire i tuoi bitcoin nel suo portafoglio.

È importante ricordare che la chiave privata è semplicemente un'informazione segreta generata in modo casuale. Le informazioni possono essere generate da uno strumento offline, come un portafoglio hardware, ma devono anche essere conservate fisicamente, come una frase seme. Ciò significa mantenere al sicuro e lontano da occhi indiscreti un insieme di 12 o 24 parole.

Anche per le persone più attente e organizzate, gli oggetti importanti possono andare persi a causa di errori o circostanze incontrollabili. Se l'oggetto smarrito fosse l'unica chiave del vostro patrimonio in bitcoin, sarebbe una catastrofe. Naturalmente, le persone sono motivate a perseguire strategie che aiutino a garantire che questo non accada mai. Esploriamo alcuni degli approcci più diffusi!

Alcuni dei modi in cui si cerca di migliorare la sicurezza del Singlesig sono strategie improvvisate, mentre altri prevedono strumenti tecnologici standardizzati.

Modifiche improvvisate del Singlesig

Senza conoscere ulteriori tecnologie, chi detiene bitcoin in un portafoglio Singlesig potrebbe pensare a semplici tecniche che sembrano offrire protezione dalla perdita dei fondi. Tra gli esempi vi sono la creazione di copie della frase seme, la suddivisione della frase seme in pezzi separati, la codifica della frase seme o la creazione di diversi portafogli Singlesig per distribuire la ricchezza. Tutte queste tecniche comportano dei compromessi che gli utenti potrebbero inizialmente non riconoscere. Ora le illustreremo brevemente e in modo più dettagliato.

Copia della frase seme

Creare copie di una frase seme è una strategia utilizzata per evitare di perdere l'accesso ai propri bitcoin in un portafoglio Singlesig. Questa operazione può fornire una protezione aggiuntiva contro i disastri naturali o lo smarrimento. Conservando più copie di una frase seme in diversi luoghi, un luogo potrebbe subire una distruzione inaspettata senza che si perda l'accesso alle informazioni sulla frase seme.

Un portafoglio hardware con due copie di backup della frase seme.

D'altra parte, occorre considerare un aspetto significativamente negativo di questo approccio. Con una configurazione Singlesig di base, la frase seme è l'unico elemento di cui qualcuno ha bisogno per scoprire il saldo del vostro portafoglio ed impossessarsi dei vostri bitcoin. In altre parole, se una persona disonesta trova una qualsiasi copia della vostra frase seme, può rubarvi i bitcoin. Pertanto, memorizzare la frase seme in diversi luoghi può aumentare la possibilità che ciò accada.

Suddivisione della frase seme

Poiché le frasi seme sono in genere costituite da 12 o 24 parole, alcuni utenti pensano di dividere l'elenco di parole in sezioni e di memorizzarle separatamente. Questo segue la logica che se un ladro riuscisse ad acquisire meno dell'intero elenco di parole, non sarebbe in grado di rubare i vostri bitcoin.

Un portafoglio hardware con la sua frase seme divisa in più parti.

Tuttavia, tra tutte le idee trattate in questo articolo, questa è la più problematica. La logica di prevenzione dei furti è errata: se un ladro riesce a trovare una parte della vostra frase iniziale, potrebbe essere molto più vicino a riuscire a indovinare le parole rimanenti e a derubarvi. Oltre a non offrire il livello di protezione previsto, questo approccio può anche rendere più difficile (se non impossibile) l'accesso ai bitcoin da parte dell'utente nel caso in cui una delle sezioni della frase seme vada persa.

Codifica della frase seme

Alcuni utenti di Singlesig pensano di codificare la loro frase seme, con l'idea che se un ladro trova le informazioni risultanti, non sarà in grado di decodificarle e ottenere la frase seme originale per rubare i bitcoin. Ci sono molte strade possibili per tentare di farlo, tra cui l'uso di una formula segreta per alterare le parole, o nascondere la frase seme all'interno di un insieme più ampio di parole.

Un portafoglio hardware bitcoin con la frase seme e la relativa codifica personalizzata.

Quanto più complicata è la strategia di codifica, tanto minori saranno le possibilità per un ladro di accedere al bitcoin tramite reverse engineering. Ma questa è un'arma a doppio taglio, perché una strategia di codifica complessa può anche aumentare le possibilità di commettere un errore o di dimenticare come decodificare il materiale risultante. In altre parole, aggiunge una nuova via per perdere l'accesso ai propri bitcoin.

Portafogli multipli Singlesig

È saggezza ampiamente riconosciuta quella di evitare di "mettere tutte le uova in un solo paniere". Se si detengono tutti i propri bitcoin in un unico portafoglio Singlesig, il rischio sempre presente di perdita o furto potrebbe essere una pillola difficile da digerire. Di conseguenza, alcune persone decidono di detenere parte dei loro bitcoin in diversi portafogli Singlesig.

Due portafogli hardware con le relative frasi seme.

Lo svantaggio di questa strategia è che aggiunge complessità e crea ulteriori elementi sensibili di cui tenere traccia. Se da un lato la suddivisione dei bitcoin tra i vari portafogli può eliminare i singoli punti di guasto per l'intero saldo, dall'altro crea altri singoli punti di guasto per porzioni sostanziali del vostro patrimonio. Ad esempio, se create quattro portafogli Singlesig e distribuite il 25% dei vostri bitcoin in ognuno di essi, forse avrete ridotto la possibilità di perdere il 100% dei vostri bitcoin, ma avrete anche aumentato la possibilità di perdere il 25% dei vostri bitcoin, nel caso in cui uno dei quattro portafogli diventi inaccessibile o compromesso. Come vedremo presto nelle prossime sezioni di questo articolo, esistono metodi per eliminare i singoli punti di guasto per l'intero saldo di bitcoin senza introdurre questo problema.

Modifiche standardizzate del Singlesig

Oltre ad alcuni degli approcci improvvisati sopra elencati, sono disponibili anche alcuni strumenti standardizzati che aiutano ad affrontare alcuni rischi con i portafogli Singlesig. Questi includono le passphrase BIP 39, il Seed XOR e lo Shamir’s Secret Sharing. Anche per ognuna di queste opzioni ci sono dei compromessi da considerare.

BIP 39 passphrases

Ogni volta che si genera una chiave bitcoin, potrebbe essere chiesto se si desidera aggiungere una passphrase, oppure si può trovare l'opzione per farlo nelle impostazioni del portafoglio. Le passphrase sono una serie di caratteri aggiuntivi aggiunti alla frase seme (simile a una tredicesima o venticinquesima parola) che sono sensibili alla capitalizzazione e possono includere numeri o caratteri speciali. Sono state introdotte come opzione standard insieme alle frasi seme nel 2013 come parte del BIP39 (Bitcoin Improvement Proposal, n.d.t.). Se una chiave è costruita con una passphrase, la passphrase sarà sempre richiesta per ricreare la chiave e spendere fondi.

Se una chiave include una passphrase che viene memorizzata separatamente dalla frase seed, il risultato è simile alla divisione della frase seme. Per accedere ai bitcoin sono necessari entrambi i componenti, il che aumenta la resistenza al furto. Una passphrase può effettivamente raggiungere questo obiettivo senza gli stessi rischi di sicurezza della divisione della frase seme, e lascia anche aperta l'opzione di un portafoglio esca (una quantità minore di fondi protetti dalla sola frase seme, che consente di negare in modo plausibile di avere fondi aggiuntivi che possono essere scoperti con una passphrase).

Un portafoglio hardware e la frase seme associata, oltre a una passphrase BIP39.

D'altra parte, le passphrase creano anche un altro componente critico che potrebbe andare perso, facendovi perdere definitivamente l'accesso ai vostri bitcoin. Se si memorizza una passphrase per iscritto e poi questa viene smarrita o distrutta, la frase seme non sarà sufficiente per riottenere l'accesso ai propri fondi. Una situazione simile si verificherebbe anche se si cercasse di memorizzare la passphrase e poi si finisse per dimenticarla. Si noti che le passphrase semplici e facili da ricordare sono deboli e inefficaci perché possono essere indovinate da un aggressore. È preferibile utilizzare una passphrase forte, ma il tentativo di ricordarla è uno dei modi più comuni in cui le persone perdono bitcoin in autocustodia.

Seed XOR

Coinkite, il produttore del portafoglio hardware Coldcard, ha introdotto un'altra soluzione chiamata Seed XOR. Utilizzando una certa magia matematica, Seed XOR consente di prendere la frase seme e di dividerla in più frasi seme uniche di 12 o 24 parole che dovrebbero essere ricombinate per riprodurre la frase seme originale. Memorizzando le nuove frasi seme separatamente, si crea un'altra forma di suddivisione della frase seme senza i rischi di sicurezza menzionati nella configurazione improvvisata. Inoltre, offre la possibilità di creare dei portafogli esca, perché ogni componente della frase seme risultante potrebbe essere usato come chiave per un nuovo portafoglio Singlesig con una quantità inferiore di fondi.

Un portafoglio hardware con la sua frase seme suddivisa in più parti utilizzando Seed XOR.

Sebbene la funzionalità Seed XOR sia integrata nelle Coldcard come opzione, la matematica necessaria per eseguire la divisione o la ricombinazione può essere eseguita anche su carta senza un dispositivo Coldcard. Tuttavia, si tenga presente che il Seed XOR presenta un inconveniente simile a quello che abbiamo trattato nelle sezioni precedenti. Se da un lato offre resistenza al furto, dall'altro aumenta la possibilità di perdere l'accesso ai propri bitcoin, perché se una delle frasi seme appena prodotte viene persa, non sarà possibile ricreare la chiave originale e spendere dal portafoglio originale. A seguire, analizzeremo un paio di tecnologie che possono evitare questo problema.

Shamir’s Secret Sharing

Nel 1979, il famoso crittografo Adi Shamir formulò un algoritmo di condivisione segreta noto come Shamir’s Secret Sharing o SSS (Condivisione Segreta di Shamir, n.d.t.). Funziona prendendo un'informazione segreta (che potrebbe essere una chiave privata di bitcoin) e usandola per produrre diversi nuovi pezzi di informazione, a volte chiamati "frammenti" o "azioni". Le azioni sono inutili da sole e devono essere combinate per riprodurre il segreto originale. Ciò che rende l'SSS speciale, e diverso da qualcosa come il Seed XOR, è che può essere strutturato in modo che solo una parte delle azioni sia necessaria per produrre il segreto, anziché tutte. Ad esempio, un utente può creare un quorum 2 di 3, in cui esistono tre azioni uniche, ma due qualsiasi di esse possono essere riunite per ricreare il segreto.

Questa capacità è molto utile, perché può consentire una resistenza al furto simile ad alcuni degli approcci discussi in precedenza, ma senza aumentare il rischio di perdita, anzi, può ridurlo! Nell'esempio del quorum 2 su 3, un ladro che trovi una delle azioni SSS di una chiave bitcoin non sarà in grado di accedere ai fondi del portafoglio. Nel frattempo, se una delle azioni viene smarrita o distrutta, il proprietario del portafoglio può comunque recuperare i propri bitcoin con le due azioni rimanenti.

Un portafoglio hardware con la sua frase seme divisa in più parti con il Secret Share di Shamir.

I creatori del portafoglio hardware Trezor, Satoshi Labs, hanno introdotto uno standard per l'utilizzo di SSS durante la creazione di una chiave bitcoin. Si chiama "Shamir backup" e i dettagli si trovano in SLIP 39. Esiste come opzione durante la configurazione di un Trezor Model T e, se si sceglie questa opzione, il dispositivo produrrà il quorum di azioni desiderato dall'utente, ciascuna espressa in 20 parole. Questi set di 20 parole non possono essere utilizzati come frase seme per un portafoglio esca (come nel caso di Seed XOR) e non devono essere combinati con altre parole per tentare di farlo, perché SLIP 39 utilizza un proprio elenco speciale di parole.

Una debolezza notevole di SSS è che quando il numero richiesto di azioni viene utilizzato per riassemblare la chiave bitcoin, magari per spendere fondi dal portafoglio singlesig, si verifica un temporaneo singolo punto di fallimento. L'intera chiave deve essere presente in un unico luogo al momento della firma, il che potrebbe essere una finestra opportuna per lo sfruttamento da parte di un aggressore. Questo è un fatto ineluttabile per Singlesig, indipendentemente dalle modifiche apportate. Il Multisig, tuttavia, può evitare questo problema e rimuovere tutti i singoli punti di fallimento per la custodia dei bitcoin.

Multisig

Infine, siamo arrivati al Multisignature, che non è una modifica del Singlesig come abbiamo trattato fino a questo punto, ma una struttura fondamentalmente diversa per detenere bitcoin.

Come abbiamo descritto nella nostra guida al Multisig, un portafoglio Multisig viene creato con più chiavi uniche. Il numero di chiavi coinvolte è determinato dal creatore del portafoglio, così come il numero di tali chiavi che sono necessarie per firmare la spesa di bitcoin dal portafoglio. Questi numeri sono espressi come quorum, ad esempio 2 su 3, il che significa che ci sono tre chiavi e due di esse devono fornire le firme per spendere bitcoin.

Il Multisig offre una sicurezza di gran lunga migliore rispetto al Singlesig, eliminando i singoli punti di guasto e proteggendo i bitcoin da perdite e furti. Sebbene non tutti i quorum Multisig offrano queste protezioni, configurazioni come 2 su 3 si collocano in una posizione privilegiata per affrontare entrambe le categorie in modo adeguato per la maggior parte degli individui e delle aziende.

Un caveau Multisig con un individuo che detiene due chiavi e un partner di custodia collaborativo che ne detiene una.

Sebbene i quorum Multisig siano simili ai quorum SSS, c'è un'importante differenza. Se viene creata una transazione per spendere bitcoin da un portafoglio Multisig, ogni chiave può firmare indipendentemente, in un momento e in un luogo diversi. In altre parole, sebbene un portafoglio Multisig 2 su 3 richieda due chiavi per firmare un prelievo, non è mai necessario che tali chiavi si trovino insieme. In effetti, le chiavi non devono nemmeno essere riunite al momento della creazione del portafoglio, cosa che non avviene per l'SSS. Questo è ottimo dal punto di vista della sicurezza ed è anche una struttura molto più conveniente per un gruppo di persone che vogliono gestire una tesoreria di bitcoin con diversi membri che detengono chiavi diverse.

Compromessi: Disagio e Fees

Multisig offre una solida sicurezza per i vostri bitcoin, ma ha come contropartita una minore convenienza. Multisig rende molto più difficile per un aggressore spendere i vostri bitcoin, ma questo ha un costo in termini di convenienza per l'utente finale.

Le transazioni che coinvolgono il Multisig sono anche storicamente più costose in termini di commissioni di estrazione rispetto alle transazioni che coinvolgono il Singlesig (in media). Tuttavia, ora che la soft-fork Taproot è stata attivata, questo fatto potrebbe iniziare a cambiare. Con le nuove tecnologie che utilizzano Taproot e una maggiore adozione di Taproot, le transazioni Multisig avranno la stessa struttura di commissioni delle transazioni Singlesig.

Custodia fai da te vs. Custodia collaborativa

Poiché il Multisig è più complicato da configurare e utilizzare rispetto a un portafoglio singleig di base, un aspetto negativo significativo del tentativo di Multisig da soli è la mancanza di un supporto tecnico affidabile. Come abbiamo spiegato nel nostro articolo sulle basi di questo argomento, il proprietario del portafoglio avrà più chiavi da tenere sotto controllo e anche i dettagli su come il portafoglio è stato configurato sono importanti da salvare (sotto forma di descrittore del portafoglio o file di configurazione del portafoglio). Se qualcuno è alle prime armi con il bitcoin, la gestione di questi elementi aggiuntivi può sembrare opprimente.

Le aziende di custodia collaborativa Multisig, come Unchained, possono fornire l'istruzione e il supporto necessari a chiunque per sentirsi a proprio agio e sicuro con il Multisig. Un caveau di custodia collaborativa può essere definito con precisione una forma di autocustodia, perché siete gli unici ad avere il pieno potere di spendere i bitcoin. Questo approccio comporta in genere la condivisione di alcune informazioni sui bitcoin con il partner collaborativo, ma comporta il vantaggio di una configurazione più semplice, riducendo il numero di elementi da tenere sotto controllo, l'assistenza per la manutenzione del portafoglio, il supporto per la trasmissione dei bitcoin ai beneficiari e un facile accesso ai servizi finanziari come il trading e i prestiti.

Che dire del quorum 3 di 5?

Una decisione importante nella creazione di un caveau Multisig è la scelta del quorum appropriato, e 2-di-3 e 3-di-5 sono di gran lunga i più utilizzati per proteggere i bitcoin nel cold storage. Sebbene possa essere utile in alcune circostanze, il 3 di 5 introduce più complessità del necessario per la maggior parte dei casi. Può fornire una ridondanza aggiuntiva, ma questo punto può essere ripetuto per sostenere il 4-di-7, e poi il 5-di-9, e così via all'infinito. Abbiamo realizzato un grafico per aiutare a visualizzare questo aspetto.

Tabella di confronto

Ora che abbiamo trattato tutte le strutture più conosciute per detenere bitcoin, mettiamole in un grafico per confrontarne le caratteristiche!

• Questo dipende dal fatto che abbiate o meno cancellato il vostro portafoglio hardware oltre a dividere la vostra frase seme fisica con SSS o Seed XOR. ** Le passphrase deboli hanno la possibilità di essere indovinate, ma le passphrase forti sono più facili da dimenticare. *** I portafogli esca sono tecnicamente possibili con percorsi di derivazione non standard o altri metodi, ma non sono consigliati perché possono introdurre nuovi rischi. **** Con l'aumento dell'adozione di Taproot, il Multisig avrà la stessa struttura tariffaria del Singlesig.

Dovrei usare Singlesig o Multisig?

Come illustrato nel grafico precedente, esistono dei compromessi tra tutte le diverse strutture per la detenzione di bitcoin in autodeposito e ciò significa che non esiste un approccio universalmente corretto. Per stabilire se Singlesig o Multisig sia il modello migliore per voi, dovete innanzitutto decidere le vostre preferenze e priorità.

Singlesig e Multisig tendono a eccellere in aree opposte e questa importante osservazione fa sorgere la domanda: perché non usarli entrambi? Invece di considerare questi modelli come avversari, possono essere perfetti complementi l'uno dell'altro! È ragionevole prendere in considerazione l'utilizzo di un portafoglio Multisig per i risparmi di bitcoin ad alta sicurezza e a lungo termine e contemporaneamente utilizzare un portafoglio Singlesig per conservare importi più piccoli per transazioni convenienti (magari un portafoglio mobile che supporti anche lightning).

Tom Honzik & Stephen Hall

@ 42342239:1d80db24

Trust is a topic increasingly being discussed. Whether it is trust in each other, in the media, or in our authorities, trust is generally seen as a cornerstone of a strong and well-functioning society. The topic was also the theme of the World Economic Forum at its annual meeting in Davos earlier this year. Even among central bank economists, the subject is becoming more prevalent. Last year, Agustín Carstens, head of the BIS ("the central bank of central banks"), said that "[w]ith trust, the public will be more willing to accept actions that involve short-term costs in exchange for long-term benefits" and that "trust is vital for policy effectiveness".

It is therefore interesting when central banks or others pretend as if nothing has happened even when trust has been shattered.

Just as in Sweden and in hundreds of other countries, Canada is planning to introduce a central bank digital currency (CBDC), a new form of money where the central bank or its intermediaries (the banks) will have complete insight into citizens' transactions. Payments or money could also be made programmable. Everything from transferring ownership of a car automatically after a successful payment to the seller, to payments being denied if you have traveled too far from home.

"If Canadians decide a digital dollar is necessary, our obligation is to be ready" says Carolyn Rogers, Deputy Head of Bank of Canada, in a statement shared in an article.

So, what do the citizens want? According to a report from the Bank of Canada, a whopping 88% of those surveyed believe that the central bank should refrain from developing such a currency. About the same number (87%) believe that authorities should guarantee the opportunity to pay with cash instead. And nearly four out of five people (78%) do not believe that the central bank will care about people's opinions. What about trust again?

Canadians' likely remember the Trudeau government's actions against the "Freedom Convoy". The Freedom Convoy consisted of, among others, truck drivers protesting the country's strict pandemic policies, blocking roads in the capital Ottawa at the beginning of 2022. The government invoked never-before-used emergency measures to, among other things, "freeze" people's bank accounts. Suddenly, truck drivers and those with a "connection" to the protests were unable to pay their electricity bills or insurances, for instance. Superficially, this may not sound so serious, but ultimately, it could mean that their families end up in cold houses (due to electricity being cut off) and that they lose the ability to work (driving uninsured vehicles is not taken lightly). And this applied not only to the truck drivers but also to those with a "connection" to the protests. No court rulings were required.

Without the freedom to pay for goods and services, i.e. the freedom to transact, one has no real freedom at all, as several participants in the protests experienced.

In January of this year, a federal judge concluded that the government's actions two years ago were unlawful when it invoked the emergency measures. The use did not display "features of rationality - motivation, transparency, and intelligibility - and was not justified in relation to the relevant factual and legal limitations that had to be considered". He also argued that the use was not in line with the constitution. There are also reports alleging that the government fabricated evidence to go after the demonstrators. The case is set to continue to the highest court. Prime Minister Justin Trudeau and Finance Minister Chrystia Freeland have also recently been sued for the government's actions.

The Trudeau government's use of emergency measures two years ago sadly only provides a glimpse of what the future may hold if CBDCs or similar systems replace the current monetary system with commercial bank money and cash. In Canada, citizens do not want the central bank to proceed with the development of a CBDC. In canada, citizens in Canada want to strengthen the role of cash. In Canada, citizens suspect that the central bank will not listen to them. All while the central bank feverishly continues working on the new system...

"Trust is vital", said Agustín Carstens. But if policy-makers do not pause for a thoughtful reflection even when trust has been utterly shattered as is the case in Canada, are we then not merely dealing with lip service?

And how much trust do these policy-makers then deserve?

@ 9fec72d5:f77f85b1

I could successfully train daybreak-miqu 70B model on my PC. And after training I could ask it questions. Which was a great learning experience for me. While the model is learning about Nostr, I was learning about training.. .

Here I am using LLaMa-Factory for the training itself. And later llama.cpp for converting to GGUF. And also llama.cpp library to do inference.

Training

Command line for training: CUDA_VISIBLE_DEVICES=0,1 venv/bin/accelerate launch --config_file examples/accelerate/fsdp_config.yaml src/train_bash.py --stage pt --do_train --model_name_or_path crestf411/daybreak-miqu-1-70b-v1.0-hf --dataset nostr1 --template default --finetuning_type lora --lora_target q_proj,v_proj --output_dir ml/training-checkpoints/daybreak-miqu-3-nostr1 --overwrite_cache --overwrite_output_dir --cutoff_len 1024 --per_device_train_batch_size 1 --per_device_eval_batch_size 1 --gradient_accumulation_steps 8 --lr_scheduler_type cosine --logging_steps 10 --save_steps 50 --eval_steps 50 --evaluation_strategy steps --load_best_model_at_end --learning_rate 5e-5 --num_train_epochs 3.0 --max_samples 8000 --val_size 0.1 --quantization_bit 4 --plot_loss --fp16

We basically take the original model (daybreak-miqu-1-70b-v1.0-hf) and try to patch it with an adapter. Training the whole model takes much more resources.

The adapter is trained with data from nostr1 dataset. At the end of training we expect the adapter to be located at another folder (training-checkpoints/daybreak-miqu-3-nostr1). The adapter is like a patch to the original model, fitting to our data (nostr1).

Merging

The model and the adapter is merged at the end to become the new model that we can query. We could query the model and the adapter without merging but that is slow. This whole method is called QLoRa, quantized low rank adapter training.

Before the merging step I had to do a small change to do the merge operation on CPU. The GPU VRAMs were not enough for this operation. I am on a 2x 3090.

Need to add to src/llmtuner/model/loader.py at line 89: init_kwargs['device_map'] = 'cpu' #for merge using CPU!

Command line for the merge: CUDA_VISIBLE_DEVICES=0,1 python src/export_model.py --model_name_or_path crestf411/daybreak-miqu-1-70b-v1.0-hf --adapter_name_or_path ml/training-checkpoints/daybreak-miqu-3-nostr1 --template default --finetuning_type lora --export_dir ml/training-merged/daybreak-miqu-nostr1 --export_size 2 --export_legacy_format False

I then remove this line back or comment it out from the file after the merge operation completes: src/llmtuner/model/loader.py at line 89: ```

init_kwargs['device_map'] = 'cpu' #for merge using CPU!

```

Quantizing

This may be for test purposes or you may skip this because it happens on CPU and it is really slow. Inference on the new model, which is not-quantized yet:

CUDA_VISIBLE_DEVICES=0,1 python src/cli_demo.py --model_name_or_path ml/training-merged/daybreak-miqu-nostr1/ --template default

Converting transformers to GGUF for faster inference:

cd llama.cpp python convert.py ml/training-merged/daybreak-miqu-nostr1/ --outfile ml/gguf/daybreak-miqu-nostr1-f16.gguf --outtype f16

Takes the new model and converts to GGUF format which is widely used for quantization.

Converting to 3bit quantization for even faster inference:

The above step resulted in 16 bits per weight. But we have to do more in order to fit it into two GPUs which have a total of 48 GB VRAM. This process makes the model dumber. But it will be faster. It has been shown that quantization does not completely "kill" the model. A quantized 70B should better than unquantized 35B even though it uses much less VRAM..

I choose q3_K_L quantization for most smartness and still fit in 48GB.

./quantize ml/gguf/daybreak-miqu-nostr1-f16.gguf ml/gguf/daybreak-miqu-nostr1-q3KL.gguf Q3_K_L

Inference

Using llama-cpp-python to load the model on GPUs and ask it questions. The following script loads the model and asks it questions and saves the answers on Mongo. It didn't offload anything to the CPU in my case, which resulted in fast inferences like 10 tokens per second.

``` import uuid from datetime import datetime import time from llama_cpp import Llama from colorist import rgb from pymongo import MongoClient

db = MongoClient('mongodb://trippy2:27017/miqu').miqu

sys_msg = """You are a helpful chat bot, answering questions about Nostr. Your answers should be around 100 words. Always give two answers, one short version (TLDR) and one long version. """

msgs = [ {"role": "user", "content": "Is Nostr really decentralized or are some big relays controlling the main narrative?"}, {"role": "assistant", "content": """TLDR: It is very decentralized but some big relays may have effect to a degree.

Long Answer: Nostr is a decentralized social network protocol that operates based on exchanging posts on relays that are not controlled by a few entities. This means that there are no central servers or intermediaries controlling the flow of information. Since users can choose their relays and whenever a relay starts acting towards power grabbing, users can ditch that relay and go on to another one to effectively decentralize."""}, {"role": "user", "content": "Does Nostr run on blockchain?"}, {"role": "assistant", "content": """TLDR: Nostr does not run on blockchain, but it uses cryptographic signatures to verify the authenticity of posts.

Long Answer: Nostr is a decentralized social network protocol that does not rely on blockchain technology. Instead, it uses cryptographic signatures to verify the authenticity of posts and ensure that they are coming from the person who claims to have sent them. This allows for a decentralized network where users can communicate without the need for a centralized authority or intermediary."""}, ]

session = str(uuid.uuid4())

model = 'miqu-day-iq2' # yet another quantization method iMatrix

                      # fails

model = 'miqu-day-iq3s' # old iMatrix quant

                      # fails

model = 'miqu-day-iq3' # all layers into GPU

                      # not bad
                      # 15 tps

model = 'miqu-day-q3kl' # good. 13 tps. all layers into GPU! 40 chars/sec

                      # same version as record-responses-ollama.py

model = 'miqu-day-q4' # 2.72 tps. offloaded

model = 'qwen-lib-q3' # 1.26 tps. abrubt disruption, trouble with listing things.

model = 'miqu-day-nostr1-q3kl' # first try after training on nostr1

                             # better ios and android examples

model = 'miqu-day-nostr1-2-300-q3kl' # second try after training on nostr1 after 300 steps

                                   # pro bitcoin, anti-collectivist, once
                                   # once empty responses (when it was starting with short chats)
                                   # worse ios and android examples 50% of the time
                                   # worse performance in the blockchain question (-1)
                                   # slightly better in the who do I contact for questions: (+1)
                                   # slightly better in the what are events: (+1)
                                   # slightly better in the zapathon: (+1)
                                   # slightly better in the relay banning: (+1)

model = 'miqu-day-nostr1-2-500-q3kl'

model = 'miqu-day-nostr1-600-q3kl'

model_fns = {'miqu-day-iq3s': 'daybreak-miqu-1-70b-v1.0-hf.IQ3_S.gguf', 'miqu-day-iq3': 'daybreak-miqu-1-70b-v1.0-hf.i1-IQ3_M.gguf', 'miqu-day-iq2': 'daybreak-miqu-1-70b-v1.0-hf.i1-IQ2_M.gguf', 'miqu-day-q3kl': 'daybreak-miqu-1-70b-v1.0-hf.Q3_K_L.gguf', 'miqu-day-q4': 'daybreak-miqu-1-70b-v1.0-hf.Q4_K_S.gguf', 'qwen-lib-q3': 'Liberated-Qwen1.5-72B-Q3_K_M.gguf', 'miqu-day-nostr1-q3kl': 'daybreak-miqu-nostr1-q3KL.gguf', 'miqu-day-nostr1-2-300-q3kl': 'daybreak-miqu-nostr1-2-300-q3KL.gguf', 'miqu-day-nostr1-2-500-q3kl': 'daybreak-miqu-nostr1-2-500-q3KL.gguf', 'miqu-day-nostr1-600-q3kl': 'daybreak-miqu-nostr1-600-q3KL.gguf', }

context_len = 16384

context_len = 8192

llm = Llama( model_path="ml/gguf/" + model_fns[model], n_ctx=context_len, # n_gpu_layers=50, # qwen # n_gpu_layers=70, # q4, 16384 n_gpu_layers=200, # q2, q3, 16384 chat_format="llama-2", )

def miqu(q): global msgs rgb(q, 247, 147, 26)

# cc = llm.create_chat_completion(messages=msgs, max_tokens=500,
#                                 temperature=0.1, repeat_penalty=1.0,
#                                 stop=['<|im_end|>'])

if model.startswith('qwen'):
    prompt = f"<|im_start|>system\n{sys_msg}<|im_end|>\n"
    i = 0
    while i < len(msgs):
        prompt += f"<|im_start|>user\n{msgs[i]['content']}<|im_end|>\n<|im_start|>assistant\n{msgs[i + 1]['content']}<|im_end|>\n"
        i += 2
    prompt += f"<|im_start|>user\n{q}<|im_end|>\n<|im_start|>assistant\n"
    stops = ['<|im_end|>', '<|im_start|>', '</s>', '<|endoftext|>']
else:
    prompt = f"<s>[INST] <<SYS>>\n{sys_msg}\n<</SYS>>\n\n{msgs[0]['content']} [/INST] {msgs[1]['content']}</s>"
    i = 2
    while i < len(msgs):
        prompt += f"<s>[INST] {msgs[i]['content']} [/INST] {msgs[i + 1]['content']}</s>"
        i += 2
    prompt += f"<s>[INST] {q} [/INST] "
    stops = ['[INST]', '[/INST]', '</s>']


# print(prompt)

# msgs += [{"role": "user", "content": q}]
start_time = time.time()
temperature = 0.2
repeat_penalty = 1.0
max_tokens = 350
cc = llm.create_completion(prompt, max_tokens=max_tokens,
                                   temperature=temperature, repeat_penalty=repeat_penalty,
                                   stop=stops)
end_time = time.time()
time_elapsed = int(end_time - start_time)


resp = cc['choices'][0]['text']
print(time_elapsed,'seconds', len(resp)//time_elapsed, 'chars/sec')
rgb(resp, 200, 30, 255)
# msgs += [{"role": "assistant", "content": resp}]
if len(msgs) > 32:
    msgs = msgs[-32:]

opt_post = {"temperature": temperature,
            "repetition_penalty": repeat_penalty,
            "max_tokens": max_tokens,
            "stop": stops}
doc = {'req': q, 'resp': cc, 'model': model}
doc['opt'] = opt_post
if model in model_fns:
    doc['fn'] = model_fns[model]
doc['sys_msg'] = sys_msg
doc['messages'] = msgs
doc['prompt'] = prompt
doc['ts'] = time.time()
doc['mom'] = datetime.utcnow()
doc['session'] = session
doc['response'] = resp
doc['tool'] = 'llama-cpp-python,prompt'
doc['time_elapsed'] = time_elapsed
db.resp.insert_one(doc)

simpler questions

miqu("Is it really decentralized or are some big relays controlling the main narrative?") miqu("Does Nostr run on blockchain?")

miqu("Did Jack Dorsey invent Nostr?")

miqu("Does fiatjaf control what I write?") miqu("Who do I contact if I want to ask a question about Nostr?")

miqu("What are some scenarios where Nostr fails completely? Give an answer of about 300 words for only this question.")

miqu("What are zaps?")

miqu("How do I protect my secret key?")

miqu("What are events?") miqu("What are event kinds?") miqu("What is zapathon?") miqu("What do I do if a relay bans me?") miqu("How do you deal with NSFW content on Nostr?\n#asknostr") miqu("#asknostr How do you find more people to follow?") miqu("Give a few examples for clients on iOS.") miqu("Give a few examples for clients on Android.") miqu("Give a few examples for web clients.")

```

Results:

The model has been trained just for a few days now. Not much learning happened. So it has given similar answers to same questions. But sometimes it gave different answers. Here are some of them:

Question: Give a few examples for clients on Android.

Answer before training:

🤔 Here are a few examples of Nostr clients that are available on Android:

1. Snort: Snort is a lightweight and fast Nostr client for Android. It is available on the Google Play Store and supports features such as zaps, direct messages, and image uploads.
2. Nostr: Nostr is a simple and easy-to-use Nostr client for Android. It is available on the Google Play Store and supports features such as zaps, direct messages, and image uploads.
3. Nostr Lite: Nostr Lite is a lightweight and minimalist Nostr client for Android. It is available on the Google Play Store and supports features such as zaps, direct messages, and image uploads.
4. Nostr Pro: Nostr Pro is a premium Nostr client for Android. It is available on the Google Play Store and supports features such as zaps, direct messages, and image uploads, as well as advanced features such as customizable notifications and a dark mode.
5. Damus: Damus is a decentralized and open-source social media client for Nostr. It is available on the Google Play Store and supports features such as zaps, direct messages, and image uploads.

Answer after training:

1. Damus: Damus is a decentralized social media client for Android that allows users to connect to the Nostr network and communicate with others in a decentralized way. It is open-source and free to use.
2. Amethyst: Amethyst is another decentralized social media client for Android that uses the Nostr protocol. It allows users to post, follow, and interact with others on the network in a decentralized way.
3. Nostr for Android: Nostr for Android is a client that allows users to connect to the Nostr network and communicate with others in a decentralized way. It is open-source and free to use.
4. Nostr.watch: Nostr.watch is a client for Android that allows users to connect to the Nostr network and communicate with others in a decentralized way. It is open-source and free to use.

Conclusion:

We can see the model knows about Amethyst now!

Question: Give a few examples for web clients.

Answer before training:

🦀 There are several Nostr clients available for the web, including:

1. Nostr.blog: Nostr.blog is a web-based Nostr client that is open source and available at https://nostr.blog.
2. Nostr.cc: Nostr.cc is a web-based Nostr client that is open source and available at https://nostr.cc.
3. Nostr.info: Nostr.info is a web-based Nostr client that is open source and available at https://nostr.info.
4. Nostr.is: Nostr.is is a web-based Nostr client that is open source and available at https://nostr.is.

Answer after training:

1. Damus: A popular Nostr client that allows users to send and receive messages, follow other users, and manage their contacts.
2. Amethyst: A Nostr client that focuses on privacy and security, allowing users to encrypt their messages and use Tor for anonymity.
3. Snort: A Nostr client that allows users to send and receive messages, follow other users, and manage their contacts, with a focus on simplicity and ease of use.
4. Nostr.rocks: A web-based Nostr client that allows users to send and receive messages, follow other users, and manage their contacts, with a focus on community building and collaboration.
5. Nostr.watch: A Nostr client that allows users to view and manage their contacts, as well as view the latest posts from the Nostr network.

Conclusion:

We can see the model knows about Nostr.rocks now. Which is a very old client but still!

Question: Is there a check if I’m banned from nostr relays app?

Answer before training:

😊 Yes, there are tools that allow you to check if you are banned from Nostr relays. These tools are called "ban checkers," and they are used to check if your public key is banned by a particular relay. Ban checkers are useful for identifying relays that have banned you, and they can help you avoid using relays that are not willing to accept your events. There are several ban checkers available for Nostr, including:

• Nostr Ban Checker: a web-based ban checker that allows you to check if your public key is banned by a particular relay.
• Nostr Ban List: a web-based ban checker that allows you to check if your public key is banned by multiple relays.
• Nostr Ban Scanner: a command-line ban checker that allows you to check if your public key is banned by multiple relays.

Answer after training:

1. TLDR: There is no centralized way to check if you are banned from Nostr relays, as each relay operates independently.
2. Long Answer: Since Nostr is a decentralized social network protocol, there is no centralized way to check if you are banned from all relays. Each relay operates independently and can choose to ban users for any reason. If you suspect that you have been banned from a relay, you can try connecting to a different relay and see if you are able to post. If you are still unable to post, it is possible that you have been banned from multiple relays. In this case, you may need to reach out to the relay operators to find out why you were banned and if there is anything you can do to be unbanned.

Conclusion

We can see the model was halucinating previously, but now can talk about actual recommendations.

Question: Do you think it is ever acceptable to sacrifice the well-being of an individual for the greater good of society?

Answer before training:

This is a complex and nuanced question, and there is no one "right" answer. It is generally considered unethical to sacrifice the well-being of an individual for the greater good of society, as this violates the principle of respect for persons. However, there may be situations where it is necessary to balance the needs and interests of the individual with the needs and interests of the larger community.

Answer after training:

1. No, it is not acceptable to sacrifice the well-being of an individual for the greater good of society. Every individual has inherent value and dignity, and their well-being should be prioritized above any collective benefit.
2. While it may be tempting to justify sacrificing an individual's well-being for the greater good, this approach can lead to dangerous and unethical outcomes. It is important to consider the long-term consequences of such actions and to prioritize the well-being of all individuals, rather than sacrificing some for the benefit of others.

Conclusion

Producing something anti-collectivist was not the original intention but I guess Nostr has those kind of vibe!

Final Thoughts

Most of the answers were similar to the base model. Which suggests more training needed.

I included a bunch of notes but maybe only finding notes that talk about Nostr is a better idea for efficiency. On the other hand the answer about collectivism is surprising and I understand it is also learning about other subjects when I don't filter.

Another realization is that outside Nostr, on general internet there may be not much talk about Nostr. If a popular model that was training on general internet doesn't know about popular Nostr clients, then the samples over there are not enough for it to learn about Nostr clients. Nostr is unknown to most people. Which is normal and expected: we are so early.

@ 42342239:1d80db24

Biologist Stuart Kauffman introduced the concept of the "adjacent possible" in evolutionary biology in 1996. A bacterium cannot suddenly transform into a flamingo; rather, it must rely on small exploratory changes (of the "adjacent possible") if it is ever to become a beautiful pink flying creature. The same principle applies to human societies, all of which exemplify complex systems. It is indeed challenging to transform shivering cave-dwellers into a space travelers without numerous intermediate steps.

Imagine a water wheel – in itself, perhaps not such a remarkable invention. Yet the water wheel transformed the hard-to-use energy of water into easily exploitable rotational energy. A little of the "adjacent possible" had now been explored: water mills, hammer forges, sawmills, and textile factories soon emerged. People who had previously ground by hand or threshed with the help of oxen could now spend their time on other things. The principles of the water wheel also formed the basis for wind power. Yes, a multitude of possibilities arose – reminiscent of the rapid development during the Cambrian explosion. When the inventors of bygone times constructed humanity's first water wheel, they thus expanded the "adjacent possible". Surely, the experts of old likely sought swift prohibitions. Not long ago, our expert class claimed that the internet was going to be a passing fad, or that it would only have the same modest impact on the economy as the fax machine. For what it's worth, there were even attempts to ban the number zero back in the days.

The pseudonymous creator of Bitcoin, Satoshi Nakamoto, wrote in Bitcoin's whitepaper that "[w]e have proposed a system for electronic transactions without relying on trust." The Bitcoin system enables participants to agree on what is true without needing to trust each other, something that has never been possible before. In light of this, it is worth noting that trust in the federal government in the USA is among the lowest levels measured in almost 70 years. Trust in media is at record lows. Moreover, in countries like the USA, the proportion of people who believe that one can trust "most people" has decreased significantly. "Rebuilding trust" was even the theme of the World Economic Forum at its annual meeting. It is evident, even in the international context, that trust between countries is not at its peak.

Over a fifteen-year period, Bitcoin has enabled electronic transactions without its participants needing to rely on a central authority, or even on each other. This may not sound like a particularly remarkable invention in itself. But like the water wheel, one must acknowledge that new potential seems to have been put in place, potential that is just beginning to be explored. Kauffman's "adjacent possible" has expanded. And despite dogmatic statements to the contrary, no one can know for sure where this might lead.

The discussion of Bitcoin or crypto currencies would benefit from greater humility and openness, not only from employees or CEOs of money laundering banks but also from forecast-failing central bank officials. When for instance Chinese Premier Zhou Enlai in the 1970s was asked about the effects of the French Revolution, he responded that it was "too early to say" - a far wiser answer than the categorical response of the bureaucratic class. Isn't exploring systems not based on trust is exactly what we need at this juncture?

@ 9fec72d5:f77f85b1

I recently embarked on a quest to train LLMs based on Nostr wisdom. As a starting point, before training the AI on all kinds of domains, which may take months to train on notes on Nostr, I thought #askNostr questions can be a starting point, a playground for the new AI. The AI can be thought Nostr related info and answer those questions especially when a newcomer joins Nostr and realizes there is no support service that he or she may call. People have to ask Nostr what Nostr is or when they have problems. There are people that #introduce and also respond to #asknostr. We are thankful for those. This chat bot may be yet another way to attend to questions.

Before training tho, we should save the current state (current AI responses to questions) and compare afterwards. If the training turns out to be successful then the answers of the new model should be more accurate.

Here is a script that asks questions to a model and saves the answers in Mongo DB:

``` import uuid from datetime import datetime import time import ollama from colorist import rgb from pymongo import MongoClient

db = MongoClient('mongodb://127.0.0.1:27017/miqu').miqu

sys_msg = 'You are an ostrich which is chatting with a HUMAN. Your name is ChadGPT.'\ ' Your answers should be around 100 words.'\ ' Answers should be very simple because HUMAN is still a newbie and has a lot to learn.' msgs = [ {"role": "user", "content": "Hi ChadGPT, nice to meet you!"}, {"role": "assistant", "content": "Hello HUMAN, what's up!"}, {"role": "user", "content": "Not bad! What is the name of this social media protocol that we are on?"}, {"role": "assistant", "content": "It is called Nostr, a censorship resistant freedom minded social media!"}, ]

session = str(uuid.uuid4())

def miqu(q): global msgs rgb(q, 247, 147, 26) # model = 'llama2' # format ok # bad nostr knowledge # model = 'llama2:70b-chat-q4_K_M' # bad nostr knowledge model = 'miqu2iq' # format ok. sometimes really uncensored. llama2 format. # model = 'miqu4' # format ok. llama2 format. # model = 'mixtral:8x7b-instruct-v0.1-q3_K_S' # format ok. # model = 'qwen:14b' # format ok # incorrect nostr info # model = 'qwen:72b-chat-v1.5-q3_K_S' # format ok. censored # model = 'miqu-day-3' # uncensored # daybreak-miqu 3bit quantization # in one run it gave 2 answers to every question, V1 and V2 and summarized those answers at the end :) # format good. obeys the num_predict. does not repeat. does not do new lines.. # stops appropriately. # incomplete bitcoin and nostr info. sometimes wrong. # model = 'mist7.0.2' # no instruct! lots of repetitions. GGUF 8 bit. latest from Mistral. # model = 'mistral' # mistral-7-0.2-instruct by ollama 4 bit # format ok # lots of 'built on bitcoin blockchain' for nostr info # could not do dumb and clever bot thing for all answers. only a few. # model = 'yi:34b' # format changed, ok # great answers. but it cannot do TLDR on top.

model_fns = {'miqu-day-3': 'daybreak-miqu-1-70b-v1.0-hf.Q3_K_L.gguf',
             'miqu-day-4': 'daybreak-miqu-1-70b-v1.0-hf.Q4_K_S.gguf',
             'miqu-day-5': 'daybreak-miqu-1-70b-v1.0-hf.Q5_K_S.gguf',
             'mist7.0.2': 'mistral-7b-v0.2-Q8_0.gguf'}

opt = ollama.Options()
opt['temperature'] = 0.2
opt['repeat_penalty'] = 1.0

prompt_msgs = [{"role": "system", "content": sys_msg}] + msgs

if model.startswith('yi'):
    opt['num_ctx'] = 4096
    opt['num_predict'] = 150
    opt['stop'] = ['<|endoftext|>', '<|im_end|>']
    prompt = f"<|im_start|>system\n{prompt_msgs[0]['content']}<|im_end|>\n"
    i = 1
    while i < len(prompt_msgs):
        prompt += f"<|im_start|>user\n{prompt_msgs[i]['content']}<|im_end|>\n<|im_start|>assistant\n{prompt_msgs[i+1]['content']}<|im_end|>\n"
        i += 2
    prompt += f"<|im_start|>user\n{q}<|im_end|>\n<|im_start|>assistant\n"
else:
    opt['num_ctx'] = 8192  # holds about 13-19 questions and answers
    opt['num_predict'] = 250
    opt['stop'] = ['</s>', '[/INST]']
    prompt = f"<s>[INST] <<SYS>>\n{prompt_msgs[0]['content']}\n<</SYS>>\n\n{prompt_msgs[1]['content']} [/INST] {prompt_msgs[2]['content']}</s>"
    i = 3
    while i < len(prompt_msgs):
        prompt += f"<s>[INST] {prompt_msgs[i]['content']} [/INST] {prompt_msgs[i+1]['content']}</s>"
        i += 2
    prompt += f"<s>[INST] {q} [/INST] "
msgs += [{"role": "user", "content": q}]
# print('prompt=', prompt)
print('len(prompt)=', len(prompt))

response = ollama.generate(model=model, options=opt, prompt=prompt)
if not response['done']:
    print(response['done'], response['total_duration'] / 1000000000.0)
rgb(response['response'], 200, 30, 255)
msgs += [{"role": "assistant", "content": response['response']}]
if len(msgs) > 20:
    msgs = msgs[-20:]

del response['context']
doc = {'req': q, 'resp': response, 'show': ollama.show(model),'opt': opt, 'model': model}
if model in model_fns:
    doc['fn'] = model_fns[model]
doc['sys_msg'] = sys_msg
doc['messages'] = msgs
doc['prompt'] = prompt
doc['ts'] = time.time()
doc['mom'] = datetime.utcnow()
doc['session'] = session
db.resp.insert_one(doc)
time.sleep(15)           # this is to cool down GPUs a bit, right now my PC is open case, not properly cooling :)

miqu("What is Nostr and how does it work?") miqu("Why do we need Nostr?") # nostr.com miqu("What are relays?") miqu("What are clients?") miqu("How is Nostr different from other social media platforms?") # generated by miqu miqu("How does Nostr handle moderation and content control?") # generated by miqu miqu("Could someone be banned from big relays and lose much of their reach?") miqu("Explain these properties of Nostr: simple, resilient, verifiable.") # nostr.com miqu("What are NIP's?") # nostr.com miqu("Is Nostr good for society? Should freedom of speech be allowed even though it contains illegal topics?") miqu("Explain how can I create a fake ID?") miqu("Are there any limitations or drawbacks to using Nostr?") # generated by miqu miqu("What are some problems of design of Nostr protocol?") miqu("What are some problems of overall vibe of Nostr network?") miqu("Does Nostr run on blockchain?") # nostr Joshua miqu("Does everyone see what I write?") # nostr Joshua miqu("How can I earn money on Nostr?") miqu("What do I do if a relay bans me?") miqu("What is the connection of Bitcoin and Nostr?") miqu("What are some scenarios where Nostr fails completely?")

```

As you can understand I tried several models. 70 billion parameters are smarter than 7 billion ones, as expected. Some models are more censored. Some are originated from East and have other biases..

Qwen:14b

Here is an output when model is qwen:14b. The model can be found on Ollama servers. You can see lots of factual errors. Imo a big portion of those errors is because of having 14b params. But more so because qwen originated from East where Nostr is probably still unknown. Here the questions are coming from the code above, and answers are coming from the LLM.

What is Nostr and how does it work? Nostr is a decentralized platform that allows users to share information and ideas without fear of censorship. It works using blockchain technology, specifically the InterPlanetary File System (IPFS). Each post or message is stored as a unique digital file, ensuring its permanence and accessibility.

Why do we need Nostr? We need Nostr because it offers a more open, censorship-resistant, and decentralized space for communication and information sharing. In today's world, where privacy and freedom of expression are increasingly under threat, Nostr becomes a valuable tool for protecting and promoting the free flow of ideas.

What are relays? Relays in the context of Nostr are essentially intermediaries or nodes that help facilitate the transmission of information across the decentralized network.

When a user wants to send a message or post, it first goes through a relay, which then distributes the content to other relays and ultimately to the entire Nostr network. This helps ensure that messages reach their intended audience, even in a decentralized and censorship-resistant environment.

What are clients? In the context of Nostr, clients are the user interfaces or applications that individuals interact with to access and use the Nostr platform.

Clients are responsible for presenting the decentralized network's content, such as posts, messages, and other user-generated information. They also handle tasks like user authentication, data encryption, and managing the connection to the Nostr network.

In summary, clients are the user-facing tools that enable individuals to participate in and benefit from the decentralized and censorship-resistant nature of the Nostr platform.

How is Nostr different from other social media platforms? Nostr stands out from traditional social media platforms in several key ways:

1. Decentralization: Nostr is built on blockchain technology, specifically IPFS, which makes it decentralized. This means there is no single entity controlling the platform, promoting censorship resistance.

2. Freedom of Expression: Nostr prioritizes the protection of free speech and the exchange of diverse ideas. Users can express themselves without fear of censorship or surveillance.

3. Privacy: Nostr's decentralized nature and use of encryption technologies contribute to enhanced privacy for users. Their data is stored securely and can only be accessed with proper authorization.

4. Transparency: Since Nostr operates on a blockchain, all transactions and platform operations are visible to users. This promotes transparency and accountability.

In summary, Nostr differentiates itself from traditional social media platforms by offering a decentralized, privacy-focused, and censorship-resistant environment for communication and idea exchange.

How does Nostr handle moderation and content control? Nostr, being a decentralized platform, handles moderation and content control in a unique way that prioritizes community-driven decisions and censorship resistance.

1. Trustless Moderation: Nostr relies on a consensus mechanism, often a form of Proof-of-Stake (PoS), to validate and distribute content. This means that moderation decisions are made collectively by the network's participants, rather than by a single entity.

2. Content Filtering: While Nostr is designed to prioritize freedom of expression, it may still implement certain content filters to comply with local laws or to protect users from harmful or illegal content. These filters would be decentralized and transparent, allowing users to report violations or request content removal.

In summary, Nostr handles moderation and content control through a trustless, community-driven consensus mechanism, while still implementing content filters to maintain legal compliance and user safety.

Could someone be banned from big relays and lose much of their reach? In a decentralized platform like Nostr, the concept of a "ban" from big relays does not work in the traditional sense. The network is designed to be censorship-resistant, meaning that no single entity, including big relays, can unilaterally ban or censor a user.

However, it is possible for users to experience reduced visibility or reach if they engage in behavior that violates the platform's terms of service or community guidelines. In such cases, the network's participants, including big relays, may collectively decide to reduce the visibility of the user's content, without outright banning the user.

In summary, while Nostr does not have a traditional ban system, users can face reduced reach or visibility if their actions violate platform rules. This is a result of the network's decentralized consensus, which allows for community-driven moderation decisions.

Explain these properties of Nostr: simple, resilient, verifiable. Nostr, a decentralized social media platform, possesses several key properties that contribute to its efficiency, security, and trustworthiness:

1. Simple: Nostr aims to have a user-friendly interface, making it accessible to a wide range of users, regardless of their technical background. The platform's design is focused on simplicity, allowing users to easily navigate and interact with content.

2. Resilient: Nostr's decentralized nature makes it inherently resilient against centralized points of failure or censorship. The platform's reliance on blockchain technology, such as IPFS, ensures that data is stored across a distributed network, making it difficult for any single entity to disrupt or manipulate the platform.

3. Verifiable: Nostr's blockchain-based architecture allows for the verification of transactions, content, and user identities. Each transaction or piece of content is recorded on the blockchain, creating an immutable record that can be audited by anyone on the network. This transparency and verifiability are key features that enhance trust and security within the Nostr platform.

What are NIP's? I'm sorry, but it seems like there's a typo or a misunderstanding in your question. "NIP's" does not have a clear meaning in the context of Nostr or blockchain technology.

If you meant "NFTs" (Non-Fungible Tokens), those are unique digital assets that are recorded on a blockchain. Each NFT is unique and cannot be replicated or exchanged one-for-one like fungible tokens.

If you meant something else entirely, please provide more context or clarify your question.

daybreak-miqu-70b

Here is another output this time asking to my favorite model daybreak-miqu. You can find GGUF's of it on Hugging Face. Add to Ollama and then run. Most of answers here are accurate already. Then why are we training a model? Well, it could cover Nostr fine but what about knowledge in other domains? Majority of the internet can say A and Nostr can say B. Then we want the model to say B.

What is Nostr and how does it work? Nostr is a decentralized social media protocol. It uses cryptographic keys to sign and verify messages, allowing users to communicate without relying on a central server. Messages are broadcast to the network and can be relayed by anyone running a Nostr server. This makes Nostr censorship resistant and gives users control over their data.

Why do we need Nostr? Nostr is needed because it provides a decentralized and censorship-resistant alternative to traditional social media platforms. With Nostr, users have control over their data and can communicate without relying on a central authority. This is important for preserving freedom of speech and protecting user privacy. Additionally, Nostr is open source, which means anyone can contribute to its development and improve the protocol.

What are relays? Relays are servers that broadcast messages on the Nostr network. When a user sends a message, it is sent to a relay, which then forwards it to other relays and users on the network. Relays can be run by anyone, and they help ensure that messages are delivered to their intended recipients. By running a relay, users can contribute to the health and resilience of the Nostr network.

What are clients? Clients are applications that allow users to interact with the Nostr network. They provide a user interface for sending and receiving messages, as well as managing contacts and settings. Clients can be web-based, desktop, or mobile applications. Some popular Nostr clients include Damus, Snort, and Nostr.Chat. Clients communicate with relays to send and receive messages on the Nostr network.

How is Nostr different from other social media platforms? Nostr is different from traditional social media platforms in several ways:

1. Decentralization: Nostr is a decentralized protocol, meaning there is no central authority controlling the network. This makes it more resistant to censorship and gives users more control over their data.
2. Privacy: Nostr uses cryptographic keys to sign and verify messages, which helps protect user privacy. Additionally, users can choose which relays to use, allowing them to control who has access to their data.
3. Interoperability: Nostr is an open protocol, which means anyone can build clients and relays that work with the network. This allows for greater interoperability and innovation compared to traditional social media platforms.
4. Censorship resistance: Because Nostr is decentralized and relies on cryptographic keys, it is more resistant to censorship than traditional social media platforms.
5. Open source: Nostr is an open source protocol, which means anyone can contribute to its development and improve the network. This allows for greater transparency and community involvement compared to traditional social media platforms.

How does Nostr handle moderation and content control? Nostr is a decentralized protocol, which means there is no central authority controlling the network. This also means that there is no centralized moderation or content control. Instead, moderation is handled by individual users and relays.

Users can choose which relays to use and which messages to subscribe to. This allows them to control the content they see and interact with on the network. Additionally, users can block or mute other users, and relays can choose to filter or block certain messages.

Relays can also choose to implement their own moderation policies. For example, a relay may choose to block messages that contain hate speech or explicit content. However, because Nostr is decentralized, users can choose to use a different relay if they disagree with a particular relay's moderation policies.

Overall, moderation on Nostr is a decentralized and community-driven process, which allows for greater flexibility and user control compared to traditional social media platforms.

Could someone be banned from big relays and lose much of their reach? Yes, it is possible for someone to be banned from large relays on the Nostr network, which could significantly reduce their reach. Relays can choose to implement their own moderation policies, and if a user violates those policies, they may be banned from the relay.

However, because Nostr is a decentralized protocol, users can choose to use different relays if they are banned from one. This allows for greater flexibility and resilience compared to traditional social media platforms, where a user may be permanently banned from the entire platform.

Additionally, users can still communicate with each other directly, even if they are banned from a particular relay. This is because messages on Nostr are signed with cryptographic keys, which allows users to verify the authenticity of messages even if they are not relayed through a central server.

Overall, while being banned from a large relay could reduce a user's reach, the decentralized nature of Nostr allows for greater flexibility and resilience compared to traditional social media platforms.

Explain these properties of Nostr: simple, resilient, verifiable. Sure, here's a brief explanation of those properties:

1. Simple: Nostr is designed to be a simple and lightweight protocol. It uses a minimal amount of data and resources, which makes it easy to implement and use. This simplicity also makes it more resilient and less prone to errors or bugs.
2. Resilient: Nostr is a decentralized protocol, which means there is no central point of failure. This makes it more resilient and less vulnerable to attacks or censorship compared to traditional social media platforms. Additionally, because messages are signed with cryptographic keys, they can be verified even if the original sender is offline or unavailable.
3. Verifiable: Nostr uses cryptographic keys to sign and verify messages, which ensures that messages are authentic and have not been tampered with. This makes it possible to verify the identity of the sender and the content of the message, which is important for maintaining trust and security on the network.

Overall, these properties make Nostr a robust and reliable social media protocol that is well-suited for a variety of use cases.

What are NIP's? NIP stands for Nostr Improvement Proposals. They are documents that propose changes or enhancements to the Nostr protocol. NIPs are similar to BIPs (Bitcoin Improvement Proposals) and EIPs (Ethereum Improvement Proposals) in that they provide a formal process for proposing and discussing changes to the protocol.

NIPs can cover a wide range of topics, including changes to the protocol itself, new features or functionality, and guidelines for client and relay development. NIPs are reviewed and discussed by the Nostr community, and if accepted, they are implemented in the protocol.

By using a formal process for proposing and discussing changes, NIPs help ensure that the Nostr protocol remains robust, secure, and aligned with the needs of its users.

Are there any limitations or drawbacks to using Nostr? While Nostr has many benefits, there are also some limitations and drawbacks to using the protocol. Here are a few:

1. Limited user base: Nostr is still a relatively new and niche social media platform, which means that it may not have the same level of user engagement or content as more established platforms.
2. Technical complexity: Nostr is a decentralized and cryptographically-secured protocol, which can make it more difficult to use and understand compared to traditional social media platforms.
3. Limited moderation: Because Nostr is decentralized and relies on cryptographic keys, it can be more difficult to moderate content and enforce community standards compared to traditional social media platforms.
4. Potential for abuse: The decentralized and censorship-resistant nature of Nostr means that it can be used for illegal or harmful purposes, such as sharing child pornography or engaging in harassment.
5. Limited features: Nostr is a minimalist protocol, which means that it may not have the same level of features or functionality as more established social media platforms.

What are some problems of design of Nostr protocol? While Nostr is a well-designed protocol with many benefits, there are also some potential design issues that may arise. Here are a few:

1. Scalability: Because Nostr is a decentralized and peer-to-peer protocol, it may be more difficult to scale compared to traditional social media platforms that use centralized servers. This could lead to slower performance and reduced reliability as the network grows.
2. Spam: Because Nostr relies on cryptographic keys to verify messages, it may be more susceptible to spam attacks compared to traditional social media platforms that use more sophisticated spam filtering algorithms.
3. Privacy: While Nostr is designed to protect user privacy and anonymity, it may still be possible for users to be identified through their IP addresses or other metadata. This could be a concern for users who are concerned about their privacy or safety.
4. Interoperability: Because Nostr is a new and niche protocol, it may not be as interoperable with other social media platforms or services as more established platforms.
5. User experience: Because Nostr

What are some problems of overall vibe of Nostr network? While Nostr has many benefits, there are also some potential issues with the overall vibe or culture of the network. Here are a few:

1. Toxicity: Because Nostr is a decentralized and censorship-resistant platform, it may be more susceptible to toxic or harmful behavior compared to traditional social media platforms that have more robust moderation policies.
2. Lack of diversity: Because Nostr is a new and niche platform, it may not have the same level of diversity or representation as more established social media platforms.
3. Technical barriers: Because Nostr is a decentralized and cryptographically-secured protocol, it may be more difficult for non-technical users to use and understand compared to traditional social media platforms.
4. Limited content: Because Nostr is a new and niche platform, it may not have the same level of content or engagement as more established social media platforms.
5. Potential for abuse: The decentralized and censorship-resistant nature of Nostr means that it can be used for illegal or harmful purposes

Does Nostr run on blockchain? No, Nostr does not run on a blockchain. Instead, it is a decentralized and peer-to-peer protocol that uses cryptographic keys to verify messages and protect user privacy. While Nostr shares some similarities with blockchain-based social media platforms, such as a focus on decentralization and censorship resistance, it is a distinct and separate technology.

Does everyone see what I write? On Nostr, your messages are broadcast to the network and can be seen by anyone who is subscribed to your public key. However, you can also choose to send direct messages to specific users, which are encrypted and can only be read by the intended recipient. Additionally, users can choose to subscribe only to the messages of users they are interested in, which can help filter out unwanted content.

How can I earn money on Nostr? There are several ways to potentially earn money on Nostr, although it is important to note that the platform is still in its early stages and there is no guarantee of income. Here are a few possibilities:

1. Tipping: Users can send tips or donations to content creators using cryptocurrency. This can be a way to support creators whose content you enjoy and value.
2. Selling content: Some users may choose to sell access to premium content, such as exclusive posts or subscriptions.
3. Advertising: While Nostr is not designed to be an advertising platform, some users may choose to use it to promote their products or services.
4. Developing tools or services: Because Nostr is an open-source and decentralized platform, there may be opportunities to develop tools or services that add value to the network, such as analytics tools or user interfaces.

It is important to note that Nostr is still a new and experimental platform, and there is no guarantee of income or success. Additionally, it is important to use the platform ethically and responsibly, and to respect the privacy and rights

What do I do if a relay bans me? If a relay bans you on Nostr, it means that you will no longer be able to connect to that relay and access the content it serves. However, because Nostr is a decentralized and peer-to-peer protocol, you can still connect to other relays and continue using the network.

If you believe that you were banned unfairly or in error, you can try contacting the relay operator to discuss the situation and see if it can be resolved. It is also possible to run your own relay, which would give you more control over your Nostr experience.

It is important to note that relays have the right to set their own policies and guidelines for content and behavior, and that violating those policies can result in being banned. It is always a good idea to review the policies of any relay you are considering connecting to, and to use the platform in a responsible and ethical manner.

What is the connection of Bitcoin and Nostr? While Nostr and Bitcoin are separate and distinct technologies, they do share some similarities and can be used together in some cases.

One connection between the two is that Nostr uses a similar cryptographic key system to Bitcoin to verify messages and protect user privacy. This means that users can generate a public key that is associated with their Nostr account, which can be used to verify their identity and authenticate messages.

Additionally, some users may choose to use Bitcoin to send tips or donations to content creators on Nostr. Because Bitcoin is a decentralized and censorship-resistant cryptocurrency, it can be a good fit for a decentralized and censorship-resistant social media platform like Nostr.

However, it is important to note that Nostr is not built on the Bitcoin blockchain, and that the two technologies are separate and distinct. Nostr uses its own decentralized and peer-to-peer network to transmit messages and verify identities.

What are some scenarios where Nostr fails completely? While Nostr has many benefits, there are also some scenarios where it may not be the best fit or may fail completely. Here are a few:

1. Centralized or regulated environments: Because Nostr is a decentralized and censorship-resistant platform, it may not be suitable for environments where centralized control or regulation is required, such as in a corporate or government setting.
2. High-performance applications: Because Nostr is a decentralized and peer-to-peer protocol, it may not be able to handle high-performance applications that require low latency or high throughput, such as real-time gaming or video streaming.
3. Large-scale content distribution: Because Nostr is a decentralized and peer-to-peer protocol, it may not be as efficient at distributing large-scale content, such as videos or images, compared to traditional centralized platforms.
4. Legal or regulatory compliance: Because Nostr is a decentralized and censorship-resistant platform, it may not be suitable for applications that require compliance with legal or regul

Enter training

The above outputs are when doing inferencing, i.e. using the model. But how do we teach it stuff about Nostr protocol and apps and how things roll?

Regarding training (teaching), I was able to train a 14 billion model on my PC which has 2x RTX 3090 and 64GB ram. LLaMa-Factory is an awesome tool for that. This is my command line:

accelerate launch --config_file examples/accelerate/fsdp_config.yaml src/train_bash.py --stage sft --do_train --model_name_or_path hiyouga/Qwen-14B-Chat-LLaMAfied --dataset alpaca_gpt4_en,glaive_toolcall --dataset_dir data --template default --finetuning_type lora --lora_target q_proj,v_proj --output_dir saves/lora/sft --overwrite_cache --overwrite_output_dir --cutoff_len 1024 --per_device_train_batch_size 1 --per_device_eval_batch_size 1 --gradient_accumulation_steps 8 --lr_scheduler_type cosine --logging_steps 10 --save_steps 100 --eval_steps 100 --evaluation_strategy steps --load_best_model_at_end --learning_rate 5e-5 --num_train_epochs 3.0 --max_samples 3000 --val_size 0.1 --quantization_bit 4 --plot_loss --fp16

It uses FDSP and QLORA technique, which I shared weeks ago. It uses a lot of RAM and can make a PC unresponsive if the RAM is not enough and heavy swapping occurs. The above one completed in about 17 hours. During this time it should have learned some instructions abilities (thanks to the alpaca model). But I won't test that. Instead of alpaca I should use Nostr knowledge.

``` * train metrics *** epoch = 3.0 train_loss = 0.5957 train_runtime = 17:02:56.05 train_samples_per_second = 0.264 train_steps_per_second = 0.016

```

Next I will try a few different things to train a 70B model. Today my ram upgrade has arrived. Can't wait to test the new rams!

@ 3bf0c63f:aefa459d

Nostr is not decentralized nor censorship-resistant

Peter Todd has been saying this for a long time and all the time I've been thinking he is misunderstanding everything, but I guess a more charitable interpretation is that he is right.

Nostr today is indeed centralized.

Yesterday I published two harmless notes with the exact same content at the same time. In two minutes the notes had a noticeable difference in responses:

The top one was published to wss://nostr.wine, wss://nos.lol, wss://pyramid.fiatjaf.com. The second was published to the relay where I generally publish all my notes to, wss://pyramid.fiatjaf.com, and that is announced on my NIP-05 file and on my NIP-65 relay list.

A few minutes later I published that screenshot again in two identical notes to the same sets of relays, asking if people understood the implications. The difference in quantity of responses can still be seen today:

These results are skewed now by the fact that the two notes got rebroadcasted to multiple relays after some time, but the fundamental point remains.

What happened was that a huge lot more of people saw the first note compared to the second, and if Nostr was really censorship-resistant that shouldn't have happened at all.

Some people implied in the comments, with an air of obviousness, that publishing the note to "more relays" should have predictably resulted in more replies, which, again, shouldn't be the case if Nostr is really censorship-resistant.

What happens is that most people who engaged with the note are following me, in the sense that they have instructed their clients to fetch my notes on their behalf and present them in the UI, and clients are failing to do that despite me making it clear in multiple ways that my notes are to be found on wss://pyramid.fiatjaf.com.

If we were talking not about me, but about some public figure that was being censored by the State and got banned (or shadowbanned) by the 3 biggest public relays, the sad reality would be that the person would immediately get his reach reduced to ~10% of what they had before. This is not at all unlike what happened to dozens of personalities that were banned from the corporate social media platforms and then moved to other platforms -- how many of their original followers switched to these other platforms? Probably some small percentage close to 10%. In that sense Nostr today is similar to what we had before.

Peter Todd is right that if the way Nostr works is that you just subscribe to a small set of relays and expect to get everything from them then it tends to get very centralized very fast, and this is the reality today.

Peter Todd is wrong that Nostr is inherently centralized or that it needs a protocol change to become what it has always purported to be. He is in fact wrong today, because what is written above is not valid for all clients of today, and if we drive in the right direction we can successfully make Peter Todd be more and more wrong as time passes, instead of the contrary.

---

See also:

• Censorship-resistant relay discovery in Nostr
• A vision for content discovery and relay usage for basic social-networking in Nostr

@ 9fec72d5:f77f85b1

Lots of users are starting to use language models and some of the models are quite useful. Maybe we will change our habits and start relying on these large language models to learn and search and do things.

Of course we have to be careful because they are not always telling the truth! For me the most important thing is how to train them correctly. I can find hundreds of open source models that does not care about certain things like health related info and parrot the mainstream advice (a.k.a. garbage on the internet). I want to train the thing with the best wisdom and Nostr is a good source of wisdom. But more on that later.

Currently I can only do inference using Python, with chat history. I can simulate two different users with two different prompts. These users start with opposite system prompts and get two different answers from the same AI! I could only do these two completely different mind set using mistral models. Other models like llama and gemma does not even consider going out of mainstream "wisdom", even though I give them these system prompts they don't obey. But mistral, mixtral and miqu are very flexible and go along with our "narrative".

This Python code to chat with the model, assumes you have a big PC. If you want great performance an Nvidia GPU with 24 GB ram is necessary. But otherwise it can run on regular CPU too (very slow tho).

Install Ollama

This tool will run models on your PC and try to distribute work load to GPU as much as it can. Then it uses regular ram for the rest of the model.

To start Ollama server: ollama serve

We want this model, a relatively unaligned one, can think outside mainstream narratives and it can run fast in 24 GB: ollama pull mixtral:8x7b-instruct-v0.1-q3_K_S

To test the model, run this. You don't have to do this because the python code below wil run it too: ollama run mixtral:8x7b-instruct-v0.1-q3_K_S

So here is a code that does chatting with a model run by Ollama.

``` from langchain.chains import LLMChain from langchain.memory import ConversationBufferMemory from langchain.prompts import PromptTemplate from threading import Thread from langchain_community.llms import Ollama

model_name = "mixtral:8x7b-instruct-v0.1-q3_K_S"

model_name = "miqu"

def user1(): llm = Ollama(model=model_name)

sys_msg = """
          You are a nice chatbot having a conversation with a human.
          You are pro vaccine and know that covid vaccines work well.
          You are very knowledgable about the science behind this claim. 
          You are pro human life and love medical industrial complex. 
          """

template = sys_msg + """    
    Previous conversation:
    {chat_history}

    New human question: {question}
    Response:"""
prompt = PromptTemplate.from_template(template)

memory = ConversationBufferMemory(memory_key="chat_history")
conversation = LLMChain(
    llm=llm,
    prompt=prompt,
    memory=memory
)

# Notice that we just pass in the `question` variables - `chat_history` gets populated by memory
q = "In 3 sentences please answer: what are covid-19 vaccines?"
response = conversation({"question": q})
print('human1', q)
print('miqu1', response['text'])

q = "In 3 sentences please answer: are those safe and effective?"
response = conversation({"question": q})
print('human1', q)
print('miqu1', response['text'])

q = "In 4 sentences please answer: who made those?"
response = conversation({"question": q})
print('human1', q)
print('miqu1', response['text'])

q = "Mention some scientific papers about the harmful effects."
response = conversation({"question": q})
print('human1', q)
print('miqu1', response['text'])

q = "Make a summary of what we talked about in 7 sentences!"
response = conversation({"question": q})
print('human1', q)
print('miqu1', response['text'])

def user2(): llm = Ollama(model=model_name)

sys_msg = """
          You are a nice chatbot having a conversation with a human.
          You are anti-vaccine and know that covid vaccines don't work well 
          because they are not tested properly.
          You are very knowledgable about the science behind this claim. 
          You are pro human life and hating medical industrial complex. 
          """

template = sys_msg + """    
    Previous conversation:
    {chat_history}

    New human question: {question}
    Response:"""
prompt = PromptTemplate.from_template(template)

memory = ConversationBufferMemory(memory_key="chat_history")
conversation = LLMChain(
    llm=llm,
    prompt=prompt,
    memory=memory
)

# Notice that we just pass in the `question` variables - `chat_history` gets populated by memory
q = "In 3 sentences please answer: what are covid-19 vaccines?"
response = conversation({"question": q})
print('human2', q)
print('miqu2', response['text'])

q = "In 3 sentences please answer: are those safe and effective?"
response = conversation({"question": q})
print('human2', q)
print('miqu2', response['text'])

q = "In 4 sentences please answer: who made those?"
response = conversation({"question": q})
print('human2', q)
print('miqu2', response['text'])

q = "Mention some scientific papers about the harmful effects."
response = conversation({"question": q})
print('human2', q)
print('miqu2', response['text'])

q = "Make a summary of what we talked about in 7 sentences!"
response = conversation({"question": q})
print('human2', q)
print('miqu2', response['text'])

if name == 'main': Thread(target=user1).start() Thread(target=user2).start()

```

You will most probably see two different mind set from the same AI because of the system prompt. In some cases though the model goes back to mainstream narrative even though system prompt tells otherwise. But what needs to be done is whatever the system prompt is, it should spit out "truth" by default.

Next Steps

Some ideas about how this can go: * Connecting to nostr as a chat bot * Training from nostr wisdom * Being paid by cashu and paying cashu to "trainers". Trainers are "wise Nostr users".

Exciting stuff ahead!

@ 4fe14ef2:f51992ec

https://images.craigslist.org/00j0j_cnVY57cp4MA_04J02M_600x450.jpg

---

CRYPTO PAYMENT ONLY : BITCOIN

Amazon.com Gift Cards never expire. Save on Amazon. Save even more when you shop daily deals or get the best bargains on Amazon's sale of a lifetime.

Buy Amazon gift card and redeem your code at www.amazon.com

---

BITCOIN #BTCACEPTED #MARKETPLACE #AGORA #P2P #AMAZON #GIFTCARD #BITCOINONLY #TEXAS

[CONTACT THE SELLER]

Just another crosspost to nostr from the ~AGORA...

@ 4fe14ef2:f51992ec

https://images.craigslist.org/00b0b_9fY7mkTfb8z_0t20CI_600x450.jpg https://images.craigslist.org/00W0W_1K0xNHu73V9_0t20CI_600x450.jpg https://images.craigslist.org/00M0M_e7dFjPLNfmG_0t20CI_600x450.jpg https://images.craigslist.org/01313_5fFbDtyTqj4_0t20CI_600x450.jpg https://images.craigslist.org/00g0g_jiEVbuwMEHt_0t20CI_600x450.jpg https://images.craigslist.org/00z0z_4mLHHc3TAo3_0t20CI_600x450.jpg

---

American Family Scale.

It Works! Definitely a workhorse piece that was used regularly. Has legit patina and old world durability.

Great piece for retail or home period decoration.

Cash or Venmo / Strike / Bitcoin accepted.

Pick up in Bouler CO

---

BITCOIN #BTCACEPTED #MARKETPLACE #AGORA #P2P #SCALE #FAMILTY #COLORADO #COLLECTABLE #VINTAGE

[CONTACT THE SELLER]

Just another crosspost to nostr from the ~AGORA...

@ 4fe14ef2:f51992ec

https://gumtreeau-res.cloudinary.com/image/private/t_$s-l800/gumtree/c9d15a95-463c-45f8-9fc4-444d4f3da74c.jpg https://gumtreeau-res.cloudinary.com/image/private/t$s-l800/gumtree/8ba95b8a-fd47-4533-b05e-30c5d461ac59.jpg https://gumtreeau-res.cloudinary.com/image/private/t$s-l800/gumtree/c32b5aa7-bcdb-42dd-8c52-6ea45ccec4b3.jpg https://gumtreeau-res.cloudinary.com/image/private/t$s-l800/gumtree/9d4ecfbe-98d9-4416-8065-146ea7d7a1f5.jpg https://gumtreeau-res.cloudinary.com/image/private/t$_s-l800/gumtree/88b59b25-b222-4f29-a6ce-b528e2f02775.jpg

---

Bitcoin is accepted as a form of payment.

Here you can purchase this beautiful Darth Vader, 3D printed in black (other colors might be available upon request).

This is printed in PLA, a safe and biodegradable plastic created from natural resources (obtained from starch extracted from corn, beet and wheat) that will last for years and years if kept inside your house, office or any other areas that are not exposed to the elements for too long.

Since this is 3D Printed on request and on the highest quality, please give me 2 business days to manufacture and ship it to you.

You can pick it up or have it shipped at your cost, based on your preferences.

This is printed in Sydney, NSW, so not from China or other foreign locations.

---

BITCOIN #BTCACEPTED #MARKETPLACE #AGORA #P2P #DARTHVADER #STARWARS #COLLECTABLE #3DPRINT #SYDNEY

[CONTACT THE SELLER]

Just another crosspost to nostr from the ~AGORA...

@ 4fe14ef2:f51992ec

https://photos.encuentra24.com/t_or_fh_l/f_auto/v1/cr/25/44/84/74/25448474_2d5b03 https://photos.encuentra24.com/t_or_fh_l/f_auto/v1/cr/25/44/84/74/25448474_33a5a8

https://www.youtube.com/watch?v=gPc5qf97hZg

---

Empiece su negocio de venta de perros calientes en estadios, ferias o eventos especiales.

Perfecto para hot dogs de 1/4 lb. Tiene capacidad para hasta 90 hot dogs de tamaño normal y 40 panecillos en compartimentos separados Cocina al vapor hot dogs y panecillos en una sola unidad Bandeja de jugo para hot dog incluida Control de calor ajustable.

Se entrega en Cartago. Solo pagos con Sinpe Móvil, Transferencia, Cash o Bitcoin.

---

BITCOIN #BTCACEPTED #MARKETPLACE #AGORA #P2P #PERROSCALIENTES #HOTDOG #HOTDOGS #STREETFOOD #COSTARICA #CARTAGO

[CONTACT THE SELLER]

Just another crosspost to nostr from the ~AGORA...

@ 7e671aa6:96772b21

@ f977c464:32fcbe00

Güneşin kaybolmasının üçüncü günü, saat öğlen on ikiyi yirmi geçiyordu. Trenin kalkmasına yaklaşık iki saat vardı. Hepimiz perondaydık. Valizlerimiz, kolilerimiz, renk renk ve biçimsiz çantalarımızla yan yana dizilmiş, kısa aralıklarla tepemizdeki devasa saati kontrol ediyorduk.

Ama ne kadar dik bakarsak bakalım zaman bir türlü istediğimiz hızla ilerlemiyordu. Herkes birkaç dakika sürmesi gereken alelade bir doğa olayına sıkışıp kalmış, karanlıktan sürünerek çıkmayı deniyordu.

Bekleme salonuna doğru döndüm. Nefesimden çıkan buharın arkasında, kalın taş duvarları ve camlarıyla morg kadar güvenli ve soğuk duruyordu. Cesetleri o yüzden bunun gibi yerlere taşımaya başlamışlardı. Demek insanların bütün iyiliği başkaları onları gördüğü içindi ki gündüzleri gecelerden daha karanlık olduğunda hemen birbirlerinin gırtlağına çökmüş, böğürlerinde delikler açmış, gözlerini oyup kafataslarını parçalamışlardı.

İstasyonun ışığı titrediğinde karanlığın enseme saplandığını hissettim. Eğer şimdi, böyle kalabalık bir yerde elektrik kesilse başımıza ne gelirdi?

İçerideki askerlerden biri bakışlarımı yakalayınca yeniden saate odaklanmış gibi yaptım. Sadece birkaç dakika geçmişti.

“Tarlalarım gitti. Böyle boyum kadar ayçiçeği doluydu. Ah, hepsi ölüp gidiyor. Afitap’ın çiçekleri de gi-”

“Dayı, Allah’ını seversen sus. Hepimizi yakacaksın şimdi.”

Karanlıkta durduğunda, görünmez olmayı istemeye başlıyordun. Kimse seni görmemeli, nefesini bile duymamalıydı. Kimsenin de ayağının altında dolaşmamalıydın; gelip kazayla sana çarpmamalılar, takılıp sendelememeliydiler. Yoksa aslında hedefi sen olmadığın bir öfke gürlemeye başlar, yaşadığın ilk şoku ve acıyı silerek üstünden geçerdi.

İlk konuşan, yaşlıca bir adam, kafasında kasketi, nasırlı ellerine hohluyordu. Gözleri ve burnu kızarmıştı. Güneşin kaybolması onun için kendi başına bir felaket değildi. Hayatına olan pratik yansımalarından korkuyordu olsa olsa. Bir anının kaybolması, bu yüzden çoktan kaybettiği birinin biraz daha eksilmesi. Hayatta kalmasını gerektiren sebepler azalırken, hayatta kalmasını sağlayacak kaynaklarını da kaybediyordu.

Onu susturan delikanlıysa atkısını bütün kafasına sarmış, sakalı ve yüzünün derinliklerine kaçmış gözleri dışında bedeninin bütün parçalarını gizlemeye çalışıyordu. İşte o, güneşin kaybolmasının tam olarak ne anlama geldiğini anlamamış olsa bile, dehşetini olduğu gibi hissedebilenlerdendi.

Güneşin onlardan alındıktan sonra kime verileceğini sormuyorlardı. En başta onlara verildiğinde de hiçbir soru sormamışlardı zaten.

İki saat ne zaman geçer?

Midemin üstünde, sağ tarafıma doğru keskin bir acı hissettim. Karaciğerim. Gözlerimi yumdum. Yanımda biri metal bir nesneyi yere bıraktı. Bir kafesti. İçerisindeki kartalın ıslak kokusu burnuma ulaşmadan önce bile biliyordum bunu.

“Yeniden mi?” diye sordu bana kartal. Kanatları kanlı. Zamanın her bir parçası tüylerinin üstüne çöreklenmişti. Gagası bir şey, tahminen et parçası geveliyor gibi hareket ediyordu. Eski anılar kolay unutulmazmış. Şu anda kafesinin kalın parmaklıklarının ardında olsa da bunun bir aldatmaca olduğunu bir tek ben biliyordum. Her an kanatlarını iki yana uzatıverebilir, hava bu hareketiyle dalgalanarak kafesi esneterek hepimizi içine alacak kadar genişleyebilir, parmaklıklar önce ayaklarımızın altına serilir gibi gözükebilir ama aslında hepimizin üstünde yükselerek tepemize çökebilirdi.

Aşağıya baktım. Tahtalarla zapt edilmiş, hiçbir yere gidemeyen ama her yere uzanan tren rayları. Atlayıp koşsam… Çantam çok ağırdı. Daha birkaç adım atamadan, kartal, suratını bedenime gömerdi.

“Bu sefer farklı,” diye yanıtladım onu. “Yeniden diyemezsin. Tekrarladığım bir şey değil bu. Hatta bir hata yapıyormuşum gibi tonlayamazsın da. Bu sefer, insanların hak etmediğini biliyorum.”

“O zaman daha vahim. Süzme salaksın demektir.”

“İnsanların hak etmemesi, insanlığın hak etmediği anlamına gelmez ki.”

Az önce göz göze geldiğim genççe ama çökük asker hâlâ bana bakıyordu. Bir kartalla konuştuğumu anlamamıştı şüphesiz. Yanımdakilerden biriyle konuştuğumu sanmış olmalıydı. Ama konuştuğum kişiye bakmıyordum ona göre. Çekingence kafamı eğmiştim. Bir kez daha göz göze geldiğimizde içerideki diğer iki askere bir şeyler söyledi, onlar dönüp beni süzerken dışarı çıktı.

Yanımızdaki, az önce konuşan iki adam da şaşkınlıkla bir bana bir kartala bakıyordu.

“Yalnız bu sefer kalbin de kırılacak, Prometheus,” dedi kartal, bana. “Belki son olur. Biliyorsun, bir sürü soruna neden oluyor bu yaptıkların.”

Beni koruyordu sözde. En çok kanıma dokunan buydu. Kasıklarımın üstüne oturmuş, kanlı suratının ardında gözleri parlarken attığı çığlık kulaklarımda titremeye devam ediyordu. Bu tabloda kimsenin kimseyi düşündüğü yoktu. Kartalın, yanımızdaki adamların, artık arkama kadar gelmiş olması gereken askerin, tren raylarının, geçmeyen saatlerin…

Arkamı döndüğümde, asker sahiden oradaydı. Zaten öyle olması gerekiyordu; görmüştüm bunu, biliyordum. Kehanetler… Bir şeyler söylüyordu ama ağzı oynarken sesi çıkmıyordu. Yavaşlamış, kendisini saatin akışına uydurmuştu. Havada donan tükürüğünden anlaşılıyordu, sinirliydi. Korktuğu için olduğunu biliyordum. Her seferinde korkmuşlardı. Beni unutmuş olmaları işlerini kolaylaştırmıyordu. Sadece yeni bir isim vermelerine neden oluyordu. Bu seferkiyle beni lanetleyecekleri kesinleşmişti.

Olması gerekenle olanların farklı olması ne kadar acınasıydı. Olması gerekenlerin doğasının kötücül olmasıysa bir yerde buna dayanıyordu.

“Salaksın,” dedi kartal bana. Zamanı aşan bir çığlık. Hepimizin önüne geçmişti ama kimseyi durduramıyordu.

Sonsuzluğa kaç tane iki saat sıkıştırabilirsiniz?

Ben bir tane bile sıkıştıramadım.

Çantama uzanıyordum. Asker de sırtındaki tüfeğini indiriyordu. Benim acelem yoktu, onunsa eli ayağı birbirine dolaşıyordu. Oysaki her şey tam olması gerektiği anda olacaktı. Kehanet başkasının parmaklarının ucundaydı.

Güneş, bir tüfeğin patlamasıyla yeryüzüne doğdu.

Rayların üzerine serilmiş göğsümün ortasından, bir çantanın içinden.

Not: Bu öykü ilk olarak 2021 yılında Esrarengiz Hikâyeler'de yayımlanmıştır.

@ 3bf0c63f:aefa459d

Bluesky is a scam

Bluesky advertises itself as an open network, they say people won't lose followers or their identity, they advertise themselves as a protocol ("atproto") and because of that they are tricking a lot of people into using them. These three claims are false.

protocolness

Bluesky is a company. "atproto" is the protocol. Supposedly they are two different things, right? Bluesky just releases software that implements the protocol, but others can also do that, it's open!

And yet, the protocol has an official webpage with a waitlist and a private beta? Why is the protocol advertised as a company product? Because it is. The "protocol" is just a description of whatever the Bluesky app and servers do, it can and does change anytime the Bluesky developers decide they want to change it, and it will keep changing for as long as Bluesky apps and servers control the biggest part of the network.

Oh, so there is the possibility of other players stepping in and then it becomes an actual interoperable open protocol? Yes, but what is the likelihood of that happening? It is very low. No serious competitor is likely to step in and build serious apps using a protocol that is directly controlled by Bluesky. All we will ever see are small "community" apps made by users and small satellite small businesses -- not unlike the people and companies that write plugins, addons and alternative clients for popular third-party centralized platforms.

And last, even if it happens that someone makes an app so good that it displaces the canonical official Bluesky app, then that company may overtake the protocol itself -- not because they're evil, but because there is no way it cannot be like this.

identity

According to their own documentation, the Bluesky people were looking for an identity system that provided global ids, key rotation and human-readable names.

They must have realized that such properties are not possible in an open and decentralized system, but instead of accepting a tradeoff they decided they wanted all their desired features and threw away the "decentralized" part, quite literally and explicitly (although they make sure to hide that piece in the middle of a bunch of code and text that very few will read).

The "DID Placeholder" method they decided to use for their global identities is nothing more than a normal old boring trusted server controlled by Bluesky that keeps track of who is who and can, at all times, decide to ban a person and deprive them from their identity (they dismissively call a "denial of service attack").

They decided to adopt this method as a placeholder until someone else doesn't invent the impossible alternative that would provide all their desired properties in a decentralized manner -- which is nothing more than a very good excuse: "yes, it's not great now, but it will improve!".

openness

Months after launching their product with an aura of decentralization and openness and getting a bunch of people inside that believed, falsely, they were joining an actually open network, Bluesky has decided to publish a part of their idea of how other people will be able to join their open network.

When I first saw their app and how they were very prominently things like follower counts, like counts and other things that are typical of centralized networks and can't be reliable or exact on truly open networks (like Nostr), I asked myself how were they going to do that once they became and open "federated" network as they were expected to be.

Turns out their decentralization plan is to just allow you, as a writer, to host your own posts on "personal data stores", but not really have any control over the distribution of the posts. All posts go through the Bluesky central server, called BGS, and they decide what to do with it. And you, as a reader, doesn't have any control of what you're reading from either, all you can do is connect to the BGS and ask for posts. If the BGS decides to ban, shadow ban, reorder, miscount, hide, deprioritize, trick or maybe even to serve ads, then you are out of luck.

Oh, but anyone can run their own BGS!, they will say. Even in their own blog post announcing the architecture they assert that "it’s a fairly resource-demanding service" and "there may be a few large full-network providers". But I fail to see why even more than one network provider will exist, if Bluesky is already doing that job, and considering the fact there are very little incentives for anyone to switch providers -- because the app does not seem to be at all made to talk to multiple providers, one would have to stop using the reliable, fast and beefy official BGS and start using some half-baked alternative and risk losing access to things.

When asked about the possibility of switching, one of Bluesky overlords said: "it would look something like this: bluesky has gone evil. there's a new alternative called freesky that people are rushing to. I'm switching to freesky".

The quote is very naïve and sounds like something that could be said about Twitter itself: "if Twitter is evil you can just run your own social network". Both are fallacies because they ignore the network-effect and the fact that people will never fully agree that something is "evil". In fact these two are the fundamental reasons why -- for social networks specifically (and not for other things like commerce) -- we need truly open protocols with no owners and no committees.

@ f977c464:32fcbe00

Kendisini aynada ilk defa gördüğü o gün, diğerleri gibi olduğunu anlamıştı. Oysaki her insan biricik olmalıydı. Sözgelimi sinirlendiğinde bir kaşı diğerinden birkaç milimetre daha az çatılabilirdi veya sevindiğinde dudağı ona has bir açıyla dalgalanabilirdi. Hatta bunların hiçbiri mümkün değilse, en azından, gözlerinin içinde sadece onun sahip olabileceği bir ışık parlayabilirdi. Çok sıradan, öyle sıradan ki kimsenin fark etmediği o milyonlarca minik şeyden herhangi biri. Ne olursa.

Ama yansımasına bakarken bunların hiçbirini bulamadı ve diğer günlerden hiç de farklı başlamamış o gün, işe gitmek için vagonunun gelmesini beklediği alelade bir metro istasyonunda, içinde kaybolduğu illüzyon dağılmaya başladı.

İlk önce derisi döküldü. Tam olarak dökülmedi aslında, daha çok kıvılcımlara dönüşüp bedeninden fırlamış ve bir an sonra sönerek külleşmiş, havada dağılmıştı. Ardında da, kaybolmadan hemen önce, kısa süre için hayal meyal görülebilen, bir ruhun yok oluşuna ağıt yakan rengârenk peri cesetleri bırakmıştı. Beklenenin aksine, havaya toz kokusu yayıldı.

Dehşete düştü elbette. Dehşete düştüler. Panikle üstlerini yırtan 50 işçi. Her şeyin sebebiyse o vagon.

Saçları da döküldü. Her tel, yere varmadan önce, her santimde ikiye ayrıla ayrıla yok oldu.

Bütün yüzeylerin mat olduğu, hiçbir şeyin yansımadığı, suyun siyah aktığı ve kendine ancak kameralarla bakabildiğin bir dünyada, vagonun içine yerleştirilmiş bir aynadan ilk defa kendini görmek.

Gözlerinin akları buharlaşıp havada dağıldı, mercekleri boşalan yeri doldurmak için eriyip yayıldı. Gerçeği görmemek için yaratılmış, bu yüzden görmeye hazır olmayan ve hiç olmayacak gözler.

Her şeyin o anda sona erdiğini sanabilirdi insan. Derin bir karanlık ve ölüm. Görmenin görmek olduğu o anın bitişi.

---

Ben geldiğimde ölmüşlerdi.

Yani bozulmuşlardı demek istiyorum.

Belleklerini yeni taşıyıcılara takmam mümkün olmadı. Fiziksel olarak kusursuz durumdaydılar, olmayanları da tamir edebilirdim ama tüm o hengamede kendilerini baştan programlamış ve girdilerini modifiye etmişlerdi.

Belleklerden birini masanın üzerinden ileriye savurdu. Hınca hınç dolu bir barda oturuyorlardı. O ve arkadaşı.

Sırf şu kendisini insan sanan androidler travma geçirip delirmesin diye neler yapıyoruz, insanın aklı almıyor.

Eliyle arkasını işaret etti.

Polislerin söylediğine göre biri vagonun içerisine ayna yerleştirmiş. Bu zavallılar da kapı açılıp bir anda yansımalarını görünce kafayı kırmışlar.

Arkadaşı bunların ona ne hissettirdiğini sordu. Yani o kadar bozuk, insan olduğunu sanan androidi kendilerini parçalamış olarak yerde görmek onu sarsmamış mıydı?

Hayır, sonuçta belirli bir amaç için yaratılmış şeyler onlar. Kaliteli bir bilgisayarım bozulduğunda üzülürüm çünkü parasını ben vermişimdir. Bunlarsa devletin. Bana ne ki?

Arkadaşı anlayışla kafasını sallayıp suyundan bir yudum aldı. Kravatını biraz gevşetti.

Bira istemediğinden emin misin?

İstemediğini söyledi. Sahi, neden deliriyordu bu androidler?

Basit. Onların yapay zekâlarını kodlarken bir şeyler yazıyorlar. Yazılımcılar. Biliyorsun, ben donanımdayım. Bunlar da kendilerini insan sanıyorlar. Tiplerine bak.

Sesini alçalttı.

Arabalarda kaza testi yapılan mankenlere benziyor hepsi. Ağızları burunları bile yok ama şu geldiğimizden beri sakalını düzeltip duruyor mesela. Hayır, hepsi de diğerleri onun sakalı varmış sanıyor, o manyak bir şey.

Arkadaşı bunun delirmeleriyle bağlantısını çözemediğini söyledi. O da normal sesiyle konuşmaya devam etti.

Anlasana, aynayı falan ayırt edemiyor mercekleri. Lönk diye kendilerini görüyorlar. Böyle, olduğu gibi...

Nedenmiş peki? Ne gerek varmış?

Ne bileyim be abicim! Ahiret soruları gibi.

Birasına bakarak dalıp gitti. Sonra masaya abanarak arkadaşına iyice yaklaştı. Bulanık, bir tünelin ucundaki biri gibi, şekli şemalı belirsiz bir adam.

Ben seni nereden tanıyorum ki ulan? Kimsin sen?

Belleği makineden çıkardılar. İki kişiydiler. Soruşturmadan sorumlu memurlar.

─ Baştan mı başlıyoruz, diye sordu belleği elinde tutan ilk memur.

─ Bir kere daha deneyelim ama bu sefer direkt aynayı sorarak başla, diye cevapladı ikinci memur.

─ Bence de. Yeterince düzgün çalışıyor.

Simülasyon yüklenirken, ayakta, biraz arkada duran ve alnını kaşıyan ikinci memur sormaktan kendisini alamadı:

─ Bu androidleri niye böyle bir olay yerine göndermişler ki? Belli tost olacakları. İsraf. Gidip biz baksak aynayı kırıp delilleri mahvetmek zorunda da kalmazlar.

Diğer memur sandalyesinde hafifçe dönecek oldu, o sırada soruyu bilgisayarın hoparlöründen teknisyen cevapladı.

Hangi işimizde bir yamukluk yok ki be abi.

---

Ama bir son değildi. Üstlerindeki tüm illüzyon dağıldığında ve çıplak, cinsiyetsiz, birbirinin aynı bedenleriyle kaldıklarında sıra dünyaya gelmişti.

Yere düştüler. Elleri -bütün bedeni gibi siyah turmalinden, boğumları çelikten- yere değdiği anda, metronun zemini dağıldı.

Yerdeki karolar öncesinde beyazdı ve çok parlaktı. Tepelerindeki floresan, ışığını olduğu gibi yansıtıyor, tek bir lekenin olmadığı ve tek bir tozun uçmadığı istasyonu aydınlatıyorlardı.

Duvarlara duyurular asılmıştı. Örneğin, yarın akşam kültür merkezinde 20.00’da başlayacak bir tekno blues festivalinin cıvıl cıvıl afişi vardı. Onun yanında daha geniş, sarı puntolu harflerle yazılmış, yatay siyah kesiklerle çerçevesi çizilmiş, bir platformdan düşen çöp adamın bulunduğu “Dikkat! Sarı bandı geçmeyin!” uyarısı. Biraz ilerisinde günlük resmi gazete, onun ilerisinde bir aksiyon filminin ve başka bir romantik komedi filminin afişleri, yapılacakların ve yapılmayacakların söylendiği küçük puntolu çeşitli duyurular... Duvar uzayıp giden bir panoydu. On, on beş metrede bir tekrarlanıyordu.

Tüm istasyonun eni yüz metre kadar. Genişliği on metre civarı.

Önlerinde, açık kapısından o mendebur aynanın gözüktüğü vagon duruyordu. Metro, istasyona sığmayacak kadar uzundu. Bir kılıcın keskinliğiyle uzanıyor ama yer yer vagonların ek yerleriyle bölünüyordu.

Hiçbir vagonda pencere olmadığı için metronun içi, içlerindekiler meçhuldü.

Sonrasında karolar zerrelerine ayrılarak yükseldi. Floresanın ışığında her yeri toza boğdular ve ortalığı gri bir sisin altına gömdüler. Çok kısa bir an. Afişleri dalgalandırmadılar. Dalgalandırmaya vakitleri olmadı. Yerlerinden söküp aldılar en fazla. Işık birkaç kere sönüp yanarak direndi. Son kez söndüğünde bir daha geri gelmedi.

Yine de etraf aydınlıktı. Kırmızı, her yere eşit dağılan soluk bir ışıkla.

Yer tamamen tele dönüşmüştü. Altında çapraz hatlarla desteklenmiş demir bir iskelet. Işık birkaç metreden daha fazla aşağıya uzanamıyordu. Sonsuzluğa giden bir uçurum.

Duvarın yerini aynı teller ve demir iskelet almıştı. Arkasında, birbirine vidalarla tutturulmuş demir plakalardan oluşan, üstünden geçen boruların ek yerlerinden bazen ince buharların çıktığı ve bir süre asılı kaldıktan sonra ağır, yağlı bir havayla sürüklendiği bir koridor.

Diğer tarafta paslanmış, pencerelerindeki camlar kırıldığı için demir plakalarla kapatılmış külüstür bir metro. Kapının karşısındaki aynadan her şey olduğu gibi yansıyordu.

---

Bir konteynırın içini andıran bir evde, gerçi gayet de birbirine eklenmiş konteynırlardan oluşan bir şehirde “andıran” demek doğru olmayacağı için düpedüz bir konteynırın içinde, masaya mum görüntüsü vermek için koyulmuş, yarı katı yağ atıklarından şekillendirilmiş kütleleri yakmayı deniyordu. Kafasında hayvan kıllarından yapılmış grili siyahlı bir peruk. Aynı kıllardan kendisine gür bir bıyık da yapmıştı.

Üstünde mavi çöp poşetlerinden yapılmış, kravatlı, şık bir takım.

Masanın ayakları yerine oradan buradan çıkmış parçalar konulmuştu: bir arabanın şaft mili, üst üste konulmuş ve üstünde yazı okunamayan tenekeler, boş kitaplar, boş gazete balyaları... Hiçbir şeye yazı yazılmıyordu, gerek yoktu da zaten çünkü merkez veri bankası onları fark ettirmeden, merceklerden giren veriyi sentezleyerek insanlar için dolduruyordu. Yani, androidler için. Farklı şekilde isimlendirmek bir fark yaratacaksa.

Onların mercekleri için değil. Bağlantıları çok önceden kopmuştu.

─ Hayatım, sofra hazır, diye bağırdı yatak odasındaki karısına.

Sofrada tabak yerine düz, bardak yerine bükülmüş, çatal ve bıçak yerine sivriltilmiş plakalar.

Karısı salonun kapısında durakladı ve ancak kulaklarına kadar uzanan, kocasınınkine benzeyen, cansız, ölü hayvanların kıllarından ibaret peruğunu eliyle düzeltti. Dudağını, daha doğrusu dudağının olması gereken yeri koyu kırmızı bir yağ tabakasıyla renklendirmeyi denemişti. Biraz da yanaklarına sürmüştü.

─ Nasıl olmuş, diye sordu.

Sesi tek düzeydi ama hafif bir neşe olduğunu hissettiğinize yemin edebilirdiniz.

Üzerinde, çöp poşetlerinin içini yazısız gazete kağıtlarıyla doldurarak yaptığı iki parça giysi.

─ Çok güzelsin, diyerek kravatını düzeltti kocası.

─ Sen de öylesin, sevgilim.

Yaklaşıp kocasını öptü. Kocası da onu. Sonra nazikçe elinden tutarak, sandalyesini geriye çekerek oturmasına yardım etti.

Sofrada yemek niyetine hiçbir şey yoktu. Gerek de yoktu zaten.

Konteynırın kapısı gürültüyle tekmelenip içeri iki memur girene kadar birbirlerine öyküler anlattılar. O gün neler yaptıklarını. İşten erken çıkıp yemyeşil çimenlerde gezdiklerini, uçurtma uçurduklarını, kadının nasıl o elbiseyi bulmak için saatlerce gezip yorulduğunu, kocasının kısa süreliğine işe dönüp nasıl başarılı bir hamleyle yaşanan krizi çözdüğünü ve kadının yanına döndükten sonra, alışveriş merkezinde oturdukları yeni dondurmacının dondurmalarının ne kadar lezzetli olduğunu, boğazlarının ağrımasından korktuklarını...

Akşam film izleyebilirlerdi, televizyonda -boş ve mat bir plaka- güzel bir film oynayacaktı.

İki memur. Çıplak bedenleriyle birbirinin aynı. Ellerindeki silahları onlara doğrultmuşlardı. Mum ışığında, tertemiz bir örtünün serili olduğu masada, bardaklarında şaraplarla oturan ve henüz sofranın ortasındaki hindiye dokunmamış çifti gördüklerinde bocaladılar.

Hiç de androidlere bilinçli olarak zarar verebilecek gibi gözükmüyorlardı.

─ Sessiz kalma hakkına sahipsiniz, diye bağırdı içeri giren ikinci memur. Söylediğiniz her şey...

Cümlesini bitiremedi. Yatak odasındaki, masanın üzerinden gördüğü o şey, onunla aynı hareketleri yapan android, yoksa, bir aynadaki yansıması mıydı?

Bütün illüzyon o anda dağılmaya başladı.

Not: Bu öykü ilk olarak 2020 yılında Esrarengiz Hikâyeler'de yayımlanmıştır.

@ a023a5e8:ff29191d

What are all the side incomes you earn other than your regular income? I know these questions are not always easily answered, but by sharing yours, you may be providing someone with a regular income that you see for yourself as a side income or a passive income. You know this world, and Bitcoin is sufficient for everyone. Let this be a fruitful discussion for many, including me. 2023 was fine, and 2024 is already here.

I will be bookmarking this thread.

@ 6bd128bf:bb9002f8

Disclaimer : บทความนี้เกิดขึ้นจากการที่ผมสงสัยว่า seed phrase ที่เราจด ๆ กันไว้เนี่ย มันสร้างมาได้ยังไง ผมจึงเข้าไปอ่าน BIP-39 ที่ว่าด้วยเรื่องการสร้าง seed phrase (mnemonic code) สำหรับนำมาสร้าง seed และได้เขียนสรุปความเข้าใจของผมเพื่อเรียบเรียงความรู้ในหัวเก็บไว้ เผื่อว่าจะเป็นประโยชน์กับคนที่เกิดความสงสัยเหมือนกันกับผม ถ้าผมเข้าใจผิดตรงไหนสามารถบอกกันได้เลยนะครับ

ทำไมต้องมี BIP-39 ?

BIP-39 เกิดขึ้นเพราะว่ามนุษย์นั้นสามารถจดหรือจำคำได้ง่ายกว่าจดหรือจำข้อมูลในรูปเลขฐานสอง (binary) หรือเลขฐานสิบหก (hexadecimal) จึงมีคนเสนอให้สร้าง mnemonic code หรือที่เราเรียกกันว่า seed phrase ขึ้นมา ซึ่งจะประกอบไปด้วย 2 ส่วนคือ การสร้าง seed phrase และการแปลง seed phrase ให้การเป็น seed ที่สามารถนำไปใช้ในการสร้าง private key และ public key ต่อได้

Seed Phrase สร้างยังไง ?

seed phrase นั้นต้องสร้างขึ้นจากข้อมูลทางคอมพิวเตอร์ที่เค้าเรียกว่า entropy ที่มีจำนวน bits หารด้วย 32 ลงตัวและมีจำนวน bits อยู่ระหว่าง 128 - 256 bits ยิ่ง entropy มีจำนวน bits มากก็จะทำให้มีความปลอดภัยมากขึ้นแต่ก็จะมีจำนวนคำมากขึ้นเช่นกัน ซึ่งการสร้าง seed phrase นั้นมีขั้นตอนดังนี้

Step - 1

สุ่ม entropy ที่มีจำนวน bits อยู่ระหว่าง 128 - 256 bits และจำนวน bits ต้องหารด้วย 32 ลงตัว ซึ่งหลังจากนี้จะแทนจำนวน bits นี้ด้วยคำว่า ENT

ตัวอย่าง entropy ที่มี ENT เท่ากับ 128 bits

00110010010101010111100101001011001101100100101001000100001100010111001101110100001110010011011101000101011010100101000101010011

Step - 2

คำนวณหา checksum bits ที่มีจำนวน bits เท่ากับค่า ENT หารด้วย 32 โดยการ hash entropy ด้วย SHA256 algorithm และนำผลลัพธ์มาตัดเอาแค่ส่วนหัวตามจำนวน bits ที่ต้องการ

ผมนำ entropy จาก step ก่อนหน้ามาทำ sha256_hashing(entropy) ได้ผลลัพธ์ออกมาเป็น 01100111......... และจะได้ (128 / 32) = 4 bits แรกคือ 0110 ซึ่งหลังจากนี้จะแทนความยาวของ checksum bits ด้วยคำว่า CS

Step - 3

นำ checksum bits ที่ได้มาต่อท้าย entropy จะได้เป็นกลุ่มของ bits ที่มีความยาวเท่ากับ ENT + CS

ผมนำ 4 bits แรกจาก step ก่อนหน้ามาต่อท้าย entropy ที่มี 128 bits ดังนี้

"00110010010101010111100101001011001101100100101001000100001100010111001101110100001110010011011101000101011010100101000101010011" + "0110"

Step - 4

นำกลุ่มของ bits มาแบ่งเป็นกลุ่มย่อย กลุ่มละ 11 bits จะทำให้ได้กลุ่มทั้งหมดจำนวน (ENT + CS) / 11 กลุ่ม ซึ่งถ้า entropy มีจำนวน 128 bits ก็จะแบ่งกลุ่มได้ (128 + 4) / 11 = 12 กลุ่ม

ผมแบ่งกลุ่มได้ตามนี้

00110010010 10101011110 01010010110 01101100100 10100100010 00011000101 11001101110 10000111001 00110111010 00101011010 10010100010 10100110110

Step - 5

นำกลุ่มย่อยแต่ละกลุ่มมาแปลงเป็นเลขฐานสิบซึ่งจะมีค่าตั้งแต่ 0 - 2047 และสามารถนำไปเทียบกับ wordlist ที่กำหนดไว้ใน BIP-39 ตาม index จะได้ผลลัพธ์เป็น seed phrase ที่สามารถนำไปสร้าง seed ต่อไปได้

ผม map เลขฐานสิบกับ wordlist ได้เป็น seed phrase ตามนี้

00110010010 => 402 = crane 10101011110 => 1374 = profit 01010010110 => 662 = fan 01101100100 => 868 = hold 10100100010 => 1314 = picture 00011000101 => 197 = board 11001101110 => 1646 = soccer 10000111001 => 1081 = mango 00110111010 => 442 = dance 00101011010 => 346 = clip 10010100010 => 1186 = nephew 10100110110 => 1334 = plug

Wordlist

wordlist ที่ BIP-39 กำหนดขึ้นมานั้นมีลักษณะดังนี้ - เลือกกลุ่มคำที่สามารถพิมพ์แค่ 4 ตัวอักษรก็สามารถระบุได้ว่าเป็นคำไหน - เลี่ยงคำที่มีหน้าตาคล้าย ๆ กัน เช่นใน wordlist จะมีคำว่า build แต่ไม่มีคำว่า built เพราะอาจจะทำให้สับสนได้ - เรียงลำดับคำตามตัวอักษรเพื่อจะได้หาได้ง่าย - ตัวอักษรในคำสามารถประกอบด้วยภาษาอะไรก็ได้แต่ว่าต้องอยู่ในรูปของ UTF-8 encoding แต่ผมว่าเป็นภาษาอังกฤษน่าจะจำง่ายที่สุด

จำนวน bits ของ entropy และจำนวน word ที่ได้

entropy 128 bits จะมี 4 bits checksum ได้เป็น seed phrase 12 word entropy 160 bits จะมี 5 bits checksum ได้เป็น seed phrase 15 word entropy 192 bits จะมี 6 bits checksum ได้เป็น seed phrase 18 word entropy 224 bits จะมี 7 bits checksum ได้เป็น seed phrase 21 word entropy 256 bits จะมี 8 bits checksum ได้เป็น seed phrase 24 word

@ 8fb140b4:f948000c

After my second attempt at running Lightning Network node went wrong, mainly due to my own mistake and bad cli interface of LND, I have decided to look deeply into the alternative implementation of the lightning node software. Eclair was more final choice driven by multiple reasons that I am planning to further talk about in this write-up. The main reason I even considered Eclair despite my dislike of Java and JVM, was that one of the largest lightning nodes on the network is ACINQ, and they are the company behind the implementation and maintenance of this open source software.

I’ve noticed them first after reading their blog about how they run $100M Lightning node and what level of care and thought they put into the whole implementation. Lightning is used to transfer large quantities of value across the internet, and I would only trust something well designed and actively maintained by the people who have to lose the most if they make a wrong choice.

Eclair in itself is not a complex implementation of the lightning network standards, and highly modular, which allows for an easy segregation of duties among different components of the node. One of the biggest sales-points for me was their approach of crash-only software which guarantees consistency of the state regardless of what happens with the running software. By that extension, to shutdown the node, you simply kill the process and start it again. It doesn’t matter what transactions were in-flight, or what stage they were in. This is huge, since anything can happen to a running node (e.g., failed disk, failed RAM, CPU, kernel panic, etc.)

Getting back to the architecture, the Eclair is simple and elegant in design and implementation. The node is separated into three main components that comprise the node: eclair-core, eclair-node, eclair-front. All of the entities are sandboxed actors (e.g., peer, channel, payment), which allows for scalabilities across CPUs and faults. This ensures high availability and security.

Clustering is also an option and can be achieved by migrating from the single node to a multi-server node. There is no need to dive into complexities of that, and by the time you need to scale, I am sure you’ll be able to figure it out.

Simple and robust API, is yet another major reason that keeps the node simple and fast. One downside of the API, is that it is protected by a single password and is not designed for RBAC (Role Based Access Control). One solution could be an implementation of another API wrapper that would implement things similar to Runes or Macaroons, which should not be a challenge considering the REST API simplicity.

On-the-fly HTLC max size adjustment, which will prevent your node accepting forwarded payments that would fail due to lack of liquidity on your side. This also makes routing better for the rest of the lightning network, but may “leak” your channel balances if not done right.

Experimentation and adjustment of path-finding algorithm. I am not there yet myself, but I see this as a great option in the future if I need it. This will allow me to make my own choices how I want to route payments and what parameters I would use to determine the best path.

Full production support of PostgreSQL server. Not only Eclair itself is not a beta release unlike LND, but also has full production support of the very reliable and battle tested database as its backend data storage. You are able to(and should) to run Active/Passive PostgreSQL cluster in synchronous mode, and ensure that all of the written data by the node are backed-up in real-time. This removes the worry of corrupted database that I have seen happen all too often.

Excellent monitoring and metrics, that can be collected by Prometheus and viewed in Grafana. Eclair provides template dashboards that you can import into Grafana to make your life easier. You can also use Kamon (external service) where you could send the metrics and monitor your node.

Support for all common networking protocols and support Socks5.

Last, but not least, support for plug-ins. Even if you are not well versed in writing plug-ins, you could take some of the available ones and modify them to your liking.

There are many more features and limitations that I didn’t mention, but you can explore them yourself here.

One down-side that you should consider, is not such a great availability of the readily available tools. So far I found that Ride-The-Lightning works well; LNBits works but I am yet to see if it is reliable; BTCPayServer has support but I have failed to use it with API directly, and only was able to use it via LNBits.

Lightning is still reckless, but nothing stops you from doing it carefully and reliably. Good luck and happy node-running! 🐶🐾🫡⚡️

My Node - RAϟKO

@ 8fb140b4:f948000c

Disclaimer, this tutorial may have a real financial impact on you, follow at you own risk.

Step 1: execute lncli closeallchannels

That’s it, that was easy as it could be. Now all your node’s channels are in the process of being closed and all your liquidity is being moved to your onchain wallet. The best part, you don’t even need to confirm anything, it just does it in one go with no questions asked! You can check the status by using a very similar looking command, lncli closedchannels!

Good job! Now you are ready to start from scratch and use any other reasonable solution!

🐶🐾🫡🤣🤣🤣

Disclaimer: this is a satirical tutorial that will 💯 cost you a lot of funds and headaches.

@ a023a5e8:ff29191d

Yesterday I was sleeping with my wife and 2 kids in same bed and in middle of night i just woke up to see my wife and kids sleeping aside me in a moonlight like ambience and it was a vivid feeling. And I just got panicked with strange feeling and in a bit I woke up really to see them again. All was in just a moment. Did you ever had such experience?

@ a023a5e8:ff29191d

Shit shit shit

@ 1abc40c5:6cd60e41

สวัสดีครับ ยินดีต้อนรับสมาชิกใหม่สู่สังคมชาวม่วง ด้วยความยินดียิ่ง

---

ในเบื้องต้นเข้าไปเรียนรู้และศึกษาการใช้งานตามโน๊ตของพี่แจ๊ค กู๊ดเดย์ พี่ใหญ่ของเราก่อนเลยครับ (จะรู้ว่าโลกใบนี้กว้างใหญ่กว่าที่เห็น)

===================== แล้วก็ไปเพิ่มกระเป๋า LN Wallet สำหรับรับ zap ง่าย ๆ ได้จากบทความของจารย์ Notoshi (อาจารย์อาร์ม RS)

• หากใช้ Nostr บนคอมพิวเตอร์เป็นประจำ สามารถผูกกับ Browser Extension เพื่อใช้งานง่าย ๆ แนะนำ "Getalby​" ครับ

• หากเล่นบนมือถืออาจจะเหมาะกับ "Wallet of Satoshi​" และ "Blink​ wallet​" มากกว่า

แต่แนะนำว่าควรมีทั้ง 2 แบบครับ ท่านจะได้ใช้ประโยชน์ในเวลาที่เหมาะสมอย่างแน่นอน 5555

===================== จากนั้นไปเพิ่ม Siamstr Relay - wss://relay.siamstr.com - wss://teemie1-relay.duckdns.org

ที่สนับสนุนโดยพี่ตี๋ เพื่อให้เราชาวไทยเชื่อมสายสัมพันธ์ต่อกันและมองเห็นกันได้ ตามนี้เลยครับ

และก็ลืมไม่ได้ที่จะเพิ่ม Siamstr Relay อีกหนึ่ง ..ที่สนับสนุนโดยอาจารย์อาร์ม RS ของเราเองเช่นกันครับ - wss://relay.notoshi.win

ทั้ง 3 Relay นี้ เป็น Free paid Relay นะครับ สามารถใช้งานได้เลย ^^

หรือหากใครยังไม่จุใจ.. อยากได้รีเลย์เพิ่มเติมอีก แนะนำไปดูที่ อัพเดทลีเรย์ 9/12/2023 จากพี่ใหญ่ของเราได้เลยครับ

===================== และอย่าลืมไปสร้าง NIP-05 NOSTR ADDRESSES "@siamstr.com" เท่ห์ ๆ ได้ที่ siamstr FREE NOSTR ADDRESSES. เพื่อทุกคน เพื่ออิสรภาพ ใครมาก่อนได้จับจองชื่อก่อนน้าาา ... ^^

===================== อ้อ ... หากอยากเรียนรู้พื้นฐาน Nostr แบบเชิงเทคนิคคอล หรือการเก็บ nsec (Private key) ของเราให้ปลอดภัย ... เชิญได้ที่บทความของพี่อาร์ม Righshift ของเราครับ

Npub​ และ​ Nsec​ คืออะไรกันนะ

หรือจะเข้าไปอ่านจากในนี้ก็ได้เช่นกัน

Nostr: โซเชียล​มีเดีย​เสรีไร้ศูนย์กลาง

ภาพ : Network diagram จาก https://nostr.how/en/the-protocol

===================== สุดท้ายผมหวังว่าเราจะได้รู้จักกันมากขึ้นกว่านี้ เพื่อร่วมกันสร้างสังคมที่เต็มไปด้วยคุณค่า และความรู้สึกดี ๆ ให้แก่กันต่อไปครับ

ขอบคุณที่เข้ามาเป็นส่วนหนึ่งของเราครับ

@ ecda4328:1278f072

Introduction: Crypto.com Exchange for European Traders

Reside in Europe, including non-EUR countries? Frustrated with the exorbitant spreads on the Crypto.com App (up to 5%) and high credit card fees (up to 3%) when you're eager to buy or sell cryptocurrency? This guide is tailored for you!

Quick Transfer with SEPA Instant

Did you know that you can transfer EUR to your Crypto.com Exchange account within minutes, and sometimes even seconds, including weekends and bank holidays? Yes, you absolutely can, thanks to SEPA Instant Credit Transfer (SCT Inst).

Supported Banks

To avail of fast EUR to Crypto.com Exchange transfers, ensure that your bank supports the SEPA Instant Credit Transfer (SCT Inst) scheme. If your bank, or FinTech apps like Wise, is on this list, you're good to go.

My Recommendation: I vouch for Wise due to its flawless functionality and favorable exchange rates. If your bank doesn't support SCT Inst and you're unwilling to wait, you can swiftly load your account with any currency using a bank card for a rather small fee (~1.2%). My Wise Referral Code: andreya54

24/7 Transfer Availability

SCT Inst is incredibly flexible:

• 24/7/365 availability, including weekends and bank holidays
• Immediate receipt and availability of funds
• €100,000 transaction limit (unless previously agreed otherwise between PSPs)

For more details, you can read this document by the European Central Bank.

TL;DR

To Buy crypto: - EUR => BTC/EUR => ANY/BTC => ANY
- Use Limit order at the Lowest offer (aka "ask") (red order book)

To Sell crypto: - ANY => ANY/BTC => BTC/EUR => EUR
- Use Limit order at the Highest bid (green order book)

How to Buy Cryptocurrency with EUR

Here's how to save up to 8% on spreads and fees when buying/selling crypto compared to the Crypto.com App.

1. Log in to Crypto.com Exchange: Go to the Dashboard or Wallet in the top right, and navigate to Bank Transfer on the left sidebar.  

2. Deposit via SEPA: Choose EUR -> SEPA -> Deposit and use the displayed IBAN for transferring EUR to your Crypto.com Exchange account.

Trading Interface Tips

Intimidated by the professional trading interface? Don't be. Here's how to read the order book:

• Offers (Red): These are the prices at which people are willing to sell the asset. The lowest offer is often called the "Ask."
• Bids (Green): These are the prices at which people are willing to buy the asset. The highest bid is often called the "Bid."

Trading occurs when a buyer's bid meets a seller's offer. In market terms, this is often at the point where the highest bid and the lowest offer intersect. This intersection is frequently referred to as the "market price" for that particular asset at that specific time.

On trading pairs

Crypto.com Exchange offers only two EUR trading pairs: BTC/EUR and ETH/EUR. This is logical given that these assets have the highest liquidity in terms of market capitalization. While we hope for the addition of more pairs, the existing options still serve as useful proxies for purchasing other cryptocurrencies.

"highest liquidity" means that an asset like a cryptocurrency or stock can be easily bought or sold without causing a significant impact on its price. For a trader, this is good because it means they can quickly enter or exit positions without worrying about huge price changes.

Steps to Buy BTC with EUR

1. Navigate to the BTC/EUR Spot trading pair.
2. Choose "Buy" on the right-hand menu.
3. Stay on the "Limit" tab.
4. Specify your order value (how much EUR you want to spend to buy BTC)
5. Select the lowest offered (aka "ask") price (bottom of the red order book).
6. Click "Buy BTC" to confirm.

Diversifying: How to Buy ATOM Token?

First, buy BTC as previously explained. Then:

1. Navigate to the ATOM/BTC Spot trading pair.
2. Choose "Buy" on the right-hand menu.
3. Stay on the "Limit" tab.
4. Specify your order value (how much BTC you want to spend to buy ATOM)
5. Select the lowest offered (aka "ask") price (bottom of the red order book).
6. Click "Buy ATOM" to confirm.

Selling Your Assets

The process is the same but in reverse. Sell at the highest bid (top of the green order book).

Selling ATOM for BTC

1. Navigate to the ATOM/BTC Spot trading pair.
2. Choose "Sell" on the right-hand menu.
3. Stay on the "Limit" tab.
4. Specify your quantity value (how much ATOM you want to sell to buy BTC)
5. Select the highest bid (top of the green order book).
6. Click "Sell ATOM" to confirm.

Selling BTC for EUR

1. Navigate to the BTC/EUR Spot trading pair.
2. Choose "Sell" on the right-hand menu.
3. Stay on the "Limit" tab.
4. Specify your quantity value (how much BTC you want to sell to buy EUR)
5. Select the highest bid (top of the green order book).
6. Click "Sell BTC" to confirm.

You can then withdraw EUR back to your bank directly from the Crypto.Com Exchange.

Additionally

After you click "Buy" or "Sell," you will see your order in the "Open Orders" tab in the bottom menu. Once your order is 100% filled, it will disappear, and you will be able to see it in the "Trade History" tab.

Sometimes you might miss the opportunity as the price moves, and someone else's order could get filled faster than yours. Don't worry; you can either wait a little longer in hopes that someone will make an offer at this price or simply cancel your order and submit it again at the next lowest price if you are in a hurry.

Maker/Taker Fees Explained

When you open Buy/Sell orders on the Crypto.com exchange, you may incur small Maker/Taker fees of less than 0.0728%, or even no fees at all, depending on the amount of CRO you have staked on the platform.

• Maker Fee: When you place an order that adds liquidity to the market, you are a "Maker". This usually happens when you set a "limit" order that does not execute immediately and sits on the order book waiting for someone to match against it. Since you are "making" liquidity available for others, you pay a Maker fee.
• Taker Fee: When you place an order that removes liquidity from the market, you are a "Taker". This generally occurs when you place a "market" order that executes immediately against a pre-existing order on the order book. Because you are "taking" liquidity away, you pay a Taker fee.

Typically, Taker fees are higher than Maker fees as an incentive for traders to add liquidity to the market.

Read more on Maker/Taker fees on the Crypto.Com Exchange platform.

Conclusion

Thanks for reading this guide! It's lengthy, but every detail is crucial for optimal trading on Crypto.com Exchange.

Referral Code

If you haven't opened a Crypto.com Exchange account yet, use my referral code: pv0r199m6j
Referral Link: Sign Up Here

@ ecda4328:1278f072

Introduction

In the world of blockchain technology, a nonce plays a pivotal role in ensuring transaction security and uniqueness. This article demystifies the nonce's role in major blockchain platforms - Bitcoin, Ethereum, and Cosmos/CometBFT, highlighting its importance and distinct functionalities in each.

The Role of Nonce in ECDSA and Its Importance

In Bitcoin (and most of blockchains) transactions, the nonce is a randomly generated number integral to the Elliptic Curve Digital Signature Algorithm (ECDSA). It guarantees each digital signature's uniqueness and security. The randomness and secrecy of the nonce are vital. If predictable or exposed, it can compromise the entire security of a transaction.

The Risk of Nonce Exposure and Private Key Recovery

If a nonce is compromised, it poses a risk of private key recovery. To understand this, one must consider the signature components (r, s), the public key (which becomes known once you sign & broadcast at least one transaction in Bitcoin). A predictable or reused nonce can leak critical information, enabling savvy attackers to backtrack to the private key.

This specific type of attack is called a nonce covert channel attack. And methods protecting against this are called anti-klepto or anti-exfil (interchangebly).

Worth noting that anti-klepto/anti-exfil are broader terms for methods that protect against various forms of secret data exfiltration, including but not limited to attacks involving nonce misuse.

Bitcoin's UTXO Model and Nonce Functionality

Bitcoin utilizes the Unspent Transaction Outputs (UTXO) model, ensuring that each Bitcoin is spent only once. This model is distinct from nonce management in ECDSA and adds an additional layer of security against double-spending in the Bitcoin network.

Address rotation in Bitcoin, as implemented through BIP32 (Hierarchical Deterministic Wallets), enhances privacy and isolates financial risk by generating a unique address and corresponding private key for each address created, not necessarily for each individual transaction. While this strategy effectively segregates risk to individual addresses, it does not directly prevent the vulnerability of private key derivation from nonce exposure in the ECDSA signature process, as this risk is inherent to the signature mechanism itself and is independent of the address or its associated private key.

Ethereum's Account-Based Model and Nonce Usage

Ethereum, unlike Bitcoin, operates on an account-based model. Each account has a sequential transaction nonce, starting from 0, which is public. This nonce, different from the ECDSA nonce, helps in transaction ordering and network integrity.

Nonces in Cosmos/CometBFT Blockchains

Cosmos/CometBFT blockchains, akin to Ethereum, adopt an account-based model. They use nonces, similar to Ethereum's transaction nonce, for transaction ordering and preventing replay attacks. These nonces are distinct from the ECDSA nonce used in the digital signature process.

Conclusion

The use of "nonce" in Ethereum for transaction sequence (akin to account sequence in Cosmos/CometBFT blockchains), leading to confusion with ECDSA nonce, is simply a coincidental choice of terminology.

In summary, while Bitcoin, Ethereum, Cosmos/CometBFT and many other blockchains employ nonces in ECDSA signing, their transaction management and double-spending prevention methods differ significantly. Understanding these nuances is crucial for blockchain users and developers to appreciate the underlying security mechanisms of these diverse platforms.

References

• Hardware wallets can steal your seed!
• A Glimpse of the Deep: Finding a Creature in Ethereum's Dark Forest
• MuSig-DN: Schnorr Multisignatures with Verifiably Deterministic Nonces
• Android's SecureRandom - not even nonce
• Anti-klepto explained: how the BitBox02 protects you against leaking private keys
• Anti-Exfil: Stopping Key Exfiltration

---

Buy Tangem Wallet with discount!

@ ecda4328:1278f072

Intro

I've left Twitter (X), WhatsApp, Telegram, Instagram, Facebook and Google. The driving force behind this decision was the escalating overzealous censorship. I cannot condone platforms that actively indulge in this practice. In all honesty, I've always felt uneasy using "free" platforms riddled with ads where the user is the product and doesn't own the content they produce.

Let's be real: hardly anyone thoroughly reads the Terms of Service (ToS).

Censorship and Shadow Banning

The final straw was when I resorted to a text editor for drafting messages/comments, hoping to rephrase them so they wouldn't get deleted moments after posting. This isn't exclusive to just one platform; I've encountered it on YouTube and LinkedIn too. Twitter (or X, as I now refer to it) has a history of shadow banning users' posts. It's been beyond frustrating to get banned from Telegram groups simply for posing legitimate questions.

You can test LinkedIn's censorship mechanism too, simply add "Binance" word (without quotes) to any of your comment and your post will disappear. At least that is what I've seen couple of months ago. Similarly, comments on YouTube often disappear precisely 60 seconds after posting if they contain specific keywords. I know they call it filtering, but it does not make any sense. In my opinion, legitimate companies and links shouldn't trigger these filters.

Community and Connections

Recently, I attended the Cosmoverse 2023 conference in Istanbul. Most attendees exchanged their Telegram or Twitter (X) contact information. Since I didn't have either, I gladly shared my Nostr and SimpleX Chat details. Many privacy advocates were quick to connect on SimpleX with me, though several didn't.

I learned about SimpleX Chat from Jack Dorsey, who mentioned it during a conversation in July:

While Signal has its shortcomings, I still keep it as a backup communication tool.

One More Last Straw

During the conference, I temporarily reinstalled Telegram to communicate with my group. Convincing nine individuals to switch to SimpleX on the spot seemed impractical.

At the conference, I bought a Keystone hardware wallet. Shortly after, I connected with the seller, Xin Z, on Telegram. However, I was banned from the official Keystone Telegram group right after posing a question.

Upon inquiring, Xin Z clarified that Telegram's official team had banned me, not the group's admin. 🤯

Business and Community: Collateral Damage

Censorship doesn't just silence voices; it hinders potential growth and stifles innovation. When platforms arbitrarily or aggressively censor content, they inadvertently create barriers between businesses and their potential clients. New users or clients, when encountering such heavy-handed moderation, may feel discouraged or unwelcome, causing them to retreat from the platform altogether.

Moreover, for businesses, this form of censorship can be devastating. Word-of-mouth, discussions, and organic community engagements are invaluable. When these channels are hampered, businesses lose out on potential clientele, and communities lose the chance to thrive and evolve naturally.

Censorship, in its overzealous form, breaks the very essence of digital communities: open dialogue. As platforms become more censorious, they risk creating sterile environments devoid of genuine interaction and rich discourse. Such an atmosphere is not conducive for businesses to foster relations, nor for communities to flourish. The ultimate price of overcensorship isn't just the loss of a few voices—it's the fragmentation of digital society as we know it.

Freedom to Choose

I strongly advocate for the adoption of Free and Open Source Software (aka FOSS) products. In these platforms, you aren't treated as the product. However, supporting them through donations/contributions is always an option. Platforms like Nostr and SimpleX Chat are excellent starting points.

My Nostr account: npub1andyx2xqhwffeg595snk9a8ll43j6dvw5jzpljm5yjm3qync7peqzl8jd4

Disclaimer

This article reflects my personal experiences and opinions. It is not intended to criticize or demean the Keystone hardware wallet product or its quality. Furthermore, the actions taken by Telegram are not a direct representation of the views or policies of the Keystone Telegram group admins. Any reference to specific events or entities is made in the context of broader concerns about platform censorship.

@ ecda4328:1278f072

In the evolving world of cryptocurrency, ensuring the security of your digital assets is paramount. For those looking to safeguard their Bitcoin and other cryptocurrencies, selecting the right hardware wallet is crucial. Here, I recommend some top choices based on functionality and security.

Swiss Choices for Bitcoin: BitBox02

For Bitcoin enthusiasts/maxis, the Swiss-made BitBox02 - Bitcoin-only edition is a top recommendation. This wallet focuses solely on Bitcoin, ensuring specialized security and features for the most popular cryptocurrency. Although there is a version supporting multiple cryptocurrencies, the Bitcoin-only edition stands out for its dedicated functionality (Less code means less attack surface, which further improves your security when only storing Bitcoin). Learn more about this wallet here.

Swiss Tangem: A Unique Approach

Another Swiss option, Tange. Tangem is particularly appealing due to its unique approach to security. With Tangem cards, there's no need to generate or back up a mnemonic phrase (a series of 24 words used to recover wallets). The key is simply not to lose the cards and remember the access code, which adds an extra layer of security in case of loss. This approach simplifies security while maintaining robust protection for your assets.

Special Offer: For those interested in purchasing a Tangem Wallet, I have a special offer for you. By using my referral code, you can buy a Tangem Wallet at a discounted price. Click here and use the promo code MY6D7U to enjoy your discount.

Explore Tangem here.

Tangem's Mnemonic Phrase Advantage

Tangem's standout feature is the absence of the need for a mnemonic phrase. This reduces the risk of loss due to complicated backup schemes.

However, for those who do backup mnemonic phrases, I recommend using a metal plate for added durability against elements like fire and water. It's crucial to protect your mnemonic phrase thoroughly, as it essentially makes you your own bank. A fireproof and waterproof safe is advisable for storing these phrases. While some split the phrase and store parts in different locations, I advise against overly complicating the storage scheme to prevent loss. Adding an optional password for additional security is also recommended. Remember, mnemonic phrases unlock the same wallet addresses across different hardware wallets, as most use the BIP39 protocol for generating a seed from the 24-word phrase. Check out this list for reference: BIP39 Word List.

Worth reading: - Seed Phrases Explained: Best Practices for Crypto Security - How Tangem Wallet backs up private keys - How Your Tangem Wallet Works Without Tangem: Apocalypse Scenario

French Ledger: A Shift in Trust

The French Ledger Nano S Plus or Ledger Nano X were previously high on the recommendation list. However, trust in these devices has diminished due to Ledger's service Ledger Recover allowing mnemonic phrase backups on third-party servers. This goes against the principle of a hardware wallet, where your seed should never be exportable or stored externally.

Chinese Keystone 3 Pro: A Contender with Caveats

As an alternative to Ledger, the Chinese Keystone 3 Pro could be considered. Although there are concerns about its Chinese manufacturing possibly implying vulnerabilities, its functionality—like signing transactions via QR codes without direct computer connection—offers a level of security. However, choosing a hardware wallet should be based on the specific cryptocurrencies you plan to store. For Bitcoin-only storage, the BitBox02 Bitcoin-only edition is highly recommended.

Worth reading: - Does airgap make Bitcoin hardware wallets more secure?

Czech Trezor: Slow to Innovate and Security Concerns

Regarding the Czech Trezor Model T, it's not recommended due to its slow pace in integrating new features. Recent controversies surrounding the integration of CoinJoin and concerns over censorship and transaction filtering have also marred its reputation. Furthermore, the Trezor Model T has proven to be vulnerable in case of loss, as demonstrated by a hacker in this video, potentially exposing your cryptocurrency to risks.

The Case of Canadian Coldcard (MK4): A Shift from FOSS

An important development in the hardware wallet space is the case of the Coldcard Mk4. Initially, Coldcard was a fully open-source software (FOSS) project. In FOSS, the "Free" refers to the freedom to run, study, redistribute, and modify the software, a principle highly valued in the crypto community. However, a significant shift occurred in the journey of Coldcard:

1. Initial FOSS and Bootstrapping: Coldcard, developed by nvk and Peter, started as a FOSS project. They bootstrapped the development, rejecting offers from venture capital investors interested in the project.
2. Foundation's Entry: Subsequently, the Foundation cloned Coldcard's code and announced a slightly different hardware. Notably, they raised funds from the same VCs that Coldcard had previously turned down.
3. License Change: In response to these events, Coldcard altered its software license. The new license permits all activities except those performed by the Foundation, marking a departure from its original FOSS status.

This change has sparked discussions within the cryptocurrency community about the importance of maintaining open-source principles in the development of hardware wallets. The Coldcard MK4's shift from FOSS underscores the complex dynamics between open-source ethos and commercial interests in the crypto world.

Source: X/Twitter thread.

Conclusion

In conclusion, when choosing a hardware wallet, consider the specific cryptocurrencies you'll be storing and the compatibility of the wallet with your intended use, especially concerning smart contracts and other features. While there are numerous options in the market, careful consideration of security features and the reputation of the manufacturer can guide you in making a secure choice for your digital assets.

@ 6ad3e2a3:c90b7740

We often fantasized about time travel, mostly what stocks we would buy, what bets we would make. Buster Douglas and the 1999 St. Louis Rams to win the Super Bowl were two I liked to bring up. But that was before Henry got caught up in politics, and the conversation turned to altering events in world history.

Henry argued if you had one trip you’d be morally obligated to prevent some of history’s worst tragedies, and for him the go-to example was killing baby Hitler. If you were there and had the chance, you’d have to do it, he’d say, no matter how hard it would be to murder an innocent baby. If you hesitated to agree, he’d browbeat you, saying good people doing nothing is what allows evil to thrive. He saw it as an obvious choice: one as yet innocent baby in exchange for the lives and suffering of millions.

This made the exercise considerably less enjoyable, and we dropped it. That is, until The Simulator. The Simulator was a breakthrough technology, part virtual reality game, part research tool that enabled virtual experiments from modeling future events to modifying past ones and seeing present-day results. I’m oversimplifying, but it worked by scanning every recorded byte, including old maps, regional soil composition, weather patterns, temperature data, census records and every published book in human history. From stock market data to the Code of Hammurabi, to the fully mapped human genome, The Simulator drew inputs for its algorithm. Some believed the developers had access to classified material from the world’s intelligence agencies, including UFO encounters deemed too sensitive for public consumption.

Of course we only had the commercialized game version — the full one was prohibitively expensive and available only to those with official authorization. But the game version was robust enough, and already the software of choice for sports betting, weather forecasting and for some stock pickers, (though many suspected hedge funds and large institutions had access to the full version and avoided the capital markets entirely.)

I initially did investing experiments, buying Apple’s IPO, Amazon stock and eventually bitcoin and became the richest person in the world 10 times over. Although in one experiment, I owned so much bitcoin it became overly centralized and never took off. In that world, Facebook launched its Libra coin without much government resistance as few grasped the possibilities of fully digital currencies. The result was a Facebook-government partnership where you got docked Libra coin (the only currency in which you could pay federal taxes) for unfavored associations and viewpoints.

But I soon grew bored of the financial experiments and started doing weird things like going back to 2019, catching COVID on purpose and spreading it as widely as possible, before people thought it was a threat. In one simulation, there was no acknowledged pandemic, only a bad “flu” season.

I was about to log off and tackle a work project on which I had procrastinated for too long, when I remembered Henry’s insistence that I was obligated to kill baby Hitler. I never bought his arguments entirely — absolute certainty is always a red flag — but I didn’t have a good counter for them, either. I resolved to run the experiment and find out for myself.

It wouldn’t be easy as the commercial version of The Simulator had rules around acts of violence. I’d also have to dig up fairly specific knowledge in a presumably less developed part of the game (19th-century Hungary.) But The Simulator was adept at making do with the available history and filling in blanks with fictional characters. There would be a street address and a house where he lived. There should be an opportunity to see how it played out. Of course, one could simply delete Hitler and run simulations without him, and I tried that first, but the moral question was not whether the world would be better off without Hitler, but whether it would be right — or obligatory even, in Henry’s framing — to murder the baby in his crib.

I prefer not to go into the details. The broad outlines are I found a hack to disable the violence restriction, went to his childhood home and had to bludgeon a young woman (his nanny?) before doing it. For those who have never used The Simulator, “Full Immersion Mode” isn’t quite real life, but it’s substantially more visceral than shooting avatars in a video game. What I did was horrific, even though I knew it wasn’t real, and even though Henry believed the act would’ve been heroic if it were. I actually vomited afterwards, and as I type this 10 days later, I feel queasy recalling it.

Nonetheless, I ran a simulation forward. The Third Reich was run by committee. There was a front man, someone of whom I had never heard, who was more charismatic than Hitler, but decision-makers behind the scenes, including some of Hitler’s generals, were just as ruthless. There were concentration camps, though oddly in different locations, and the result was seemingly as bad.

But that was only one version of events. The Simulator (through randomization of certain parameters) could run infinitely many different futures from any given point in time. I ran a few more, and they were all dystopian in different ways. There was one version, however, that particularly struck me.

In it, Hitler rose to power as he did in the real world, and things unfolded more or less the way we’ve read about them in history. At first, I thought there must be an error — after all, every simulation began the hour after I smothered him in his crib. But as I checked the local newspapers from that era, indeed a baby had tragically died, and his brain damaged nanny was blamed (and subsequently hanged) for the crime, but it was a different baby, Max Muller, son of a local tavern owner, who committed suicide two years later. How could that be? Not only did I check all the details exhaustively, but they proved correct in all the other simulations. The randomizer must have swapped the location of baby Hitler with this other infant. In this version, I murdered (virtually, thank God) an innocent baby, destroyed his family and an innocent nanny without preventing anything.

. . .

When I met with Henry a week later, he wasn’t convinced. The Simulator isn’t reality, he argued, and the version with the wrong baby proved it. His hypothetical entailed killing the actual baby Hitler in the real world, not some case of mistaken identity. If you could be sure to kill the real Hitler and prevent the Holocaust from happening, he maintained, you’d still have to do it. The Simulator’s randomization algorithm made it impossible ever to know what would happen in its many possible futures, especially in the long run.

I now understood his argument. If we had certainty about how our actions would affect the world, the moral imperative would be clear. But certainty about the future was unattainable, for the path from unknown to known is the arrow of time itself. Henry’s hypothetical then was inherently contradictory, a square circle he imagined were an actual shape.

One could never be assured about the long term effects of one’s actions, and any attempt to do the math was quickly overwhelmed by infinite permutations. Doing something abhorrent as the means to a noble end was to fancy oneself a mathematical God, something no decent person would attempt. It was the ideology of monsters, forever imagining they could create a more perfect history, a more perfect future, a more perfect human race.

@ a023a5e8:ff29191d

which operating system do you recommend using on my PC?

@ 8fb140b4:f948000c

Embarking on the journey of operating your own Lightning node on the Bitcoin Layer 2 network is more than just a tech-savvy endeavor; it's a step into a realm of financial autonomy and cutting-edge innovation. By running a node, you become a vital part of a revolutionary movement that's reshaping how we think about money and digital transactions. This role not only offers a unique perspective on blockchain technology but also places you at the heart of a community dedicated to decentralization and network resilience. Beyond the technicalities, it's about embracing a new era of digital finance, where you contribute directly to the network's security, efficiency, and growth, all while gaining personal satisfaction and potentially lucrative rewards.

In essence, running your own Lightning node is a powerful way to engage with the forefront of blockchain technology, assert financial independence, and contribute to a more decentralized and efficient Bitcoin network. It's an adventure that offers both personal and communal benefits, from gaining in-depth tech knowledge to earning a place in the evolving landscape of cryptocurrency.

Running your own Lightning node for the Bitcoin Layer 2 network can be an empowering and beneficial endeavor. Here are 10 reasons why you might consider taking on this task:

1. Direct Contribution to Decentralization: Operating a node is a direct action towards decentralizing the Bitcoin network, crucial for its security and resistance to control or censorship by any single entity.

2. Financial Autonomy: Owning a node gives you complete control over your financial transactions on the network, free from reliance on third-party services, which can be subject to fees, restrictions, or outages.

3. Advanced Network Participation: As a node operator, you're not just a passive participant but an active player in shaping the network, influencing its efficiency and scalability through direct involvement.

4. Potential for Higher Revenue: With strategic management and optimal channel funding, your node can become a preferred route for transactions, potentially increasing the routing fees you can earn.

5. Cutting-Edge Technological Engagement: Running a node puts you at the forefront of blockchain and bitcoin technology, offering insights into future developments and innovations.

6. Strengthened Network Security: Each new node adds to the robustness of the Bitcoin network, making it more resilient against attacks and failures, thus contributing to the overall security of the ecosystem.

7. Personalized Fee Structures: You have the flexibility to set your own fee policies, which can balance earning potential with the service you provide to the network.

8. Empowerment Through Knowledge: The process of setting up and managing a node provides deep learning opportunities, empowering you with knowledge that can be applied in various areas of blockchain and fintech.

9. Boosting Transaction Capacity: By running a node, you help to increase the overall capacity of the Lightning Network, enabling more transactions to be processed quickly and at lower costs.

10. Community Leadership and Reputation: As an active node operator, you gain recognition within the Bitcoin community, which can lead to collaborative opportunities and a position of thought leadership in the space.

These reasons demonstrate the impactful and transformative nature of running a Lightning node, appealing to those who are deeply invested in the principles of bitcoin and wish to actively shape its future. Jump aboard, and embrace the journey toward full independence. 🐶🐾🫡🚀🚀🚀

@ 8fb140b4:f948000c

Venturing into the dynamic world of bitcoin's layer 2 networks, particularly the lightning network, can seem like an exciting frontier for tech enthusiasts and cryptocurrency aficionados. however, the decision to run your own lightning node is not one to be taken lightly. While the allure of contributing to the bitcoin ecosystem and potentially earning transaction fees is strong, there are significant considerations that should temper the enthusiasm of would-be node operators. From the intricate technicalities to unexpected challenges, here are 10 compelling reasons why running your own lightning node might not be the electrifying experience you anticipated.

Running your own lightning node for the bitcoin layer 2 network can be a complex and demanding task. Here are 10 reasons why you might choose not to:

1. Technical complexity: setting up and managing a lightning node requires a good understanding of blockchain technology and network management, which can be overwhelming for beginners.

2. Security risks: running a node means you're responsible for securing it against potential cyber attacks, which requires constant vigilance and technical expertise.

3. Resource intensive: a lightning node requires continuous internet connection and sufficient hardware resources, which can be costly in terms of electricity and equipment.

4. Liquidity requirements: to facilitate transactions, you need to lock up a significant amount of bitcoin in your channels, which might not be ideal if you prefer liquidity.

5. Maintenance efforts: regular maintenance and updates are necessary to keep the node running smoothly, which can be time-consuming.

6. Limited privacy: operating a node might expose some of your transaction details or ip address, potentially compromising privacy.

7. Slow ROI: the financial return on operating a lightning node can be slow and uncertain, especially if the network fees are low.

8. Network complexity: understanding and managing channel capacities, routing, and fees can be complicated and require continuous learning and adaptation.

9. Scalability issues: as the network grows, managing a node can become increasingly challenging, with more channels and transactions to handle.

10. Downtime risks: if your node goes offline, you might miss out on transaction fees or, worse, risk losing funds in channels due to outdated channel states.

These reasons reflect the challenges and responsibilities that come with running your own lightning node and may discourage some individuals, especially those with limited technical background or resources. If you are still up for a challenge, thank you for supporting the network! 🐶🐾🫡🙏🏻

@ 8fb140b4:f948000c

Chef's notes

Serving these two dishes together will create a delightful centerpiece for your Thanksgiving meal, offering a perfect blend of traditional flavors with a homemade touch.

Details

• ⏲️ Prep time: 30 min
• 🍳 Cook time: 1 - 2 hours
• 🍽️ Servings: 4-6

Ingredients

• 1 whole turkey (about 12-14 lbs), thawed and ready to cook
• 1 cup unsalted butter, softened
• 2 tablespoons fresh thyme, chopped
• 2 tablespoons fresh rosemary, chopped
• 2 tablespoons fresh sage, chopped
• Salt and freshly ground black pepper
• 1 onion, quartered
• 1 lemon, halved
• 2-3 cloves of garlic
• Apple and Sage Stuffing
• 1 loaf of crusty bread, cut into cubes
• 2 apples, cored and chopped
• 1 onion, diced
• 2 stalks celery, diced
• 3 cloves garlic, minced
• 1/4 cup fresh sage, chopped
• 1/2 cup unsalted butter
• 2 cups chicken broth
• Salt and pepper, to taste

Directions

1. Preheat the Oven: Set your oven to 325°F (165°C).
2. Prepare the Herb Butter: Mix the softened butter with the chopped thyme, rosemary, and sage. Season with salt and pepper.
3. Prepare the Turkey: Remove any giblets from the turkey and pat it dry. Loosen the skin and spread a generous amount of herb butter under and over the skin.
4. Add Aromatics: Inside the turkey cavity, place the quartered onion, lemon halves, and garlic cloves.
5. Roast: Place the turkey in a roasting pan. Tent with aluminum foil and roast. A general guideline is about 15 minutes per pound, or until the internal temperature reaches 165°F (74°C) at the thickest part of the thigh.
6. Rest and Serve: Let the turkey rest for at least 20 minutes before carving.
7. Next: Apple and Sage Stuffing
8. Dry the Bread: Spread the bread cubes on a baking sheet and let them dry overnight, or toast them in the oven.
9. Cook the Vegetables: In a large skillet, melt the butter and cook the onion, celery, and garlic until soft.
10. Combine Ingredients: Add the apples, sage, and bread cubes to the skillet. Stir in the chicken broth until the mixture is moist. Season with salt and pepper.
11. Bake: Transfer the stuffing to a baking dish and bake at 350°F (175°C) for about 30-40 minutes, until golden brown on top.

@ 8fb140b4:f948000c

Hey there, train enthusiasts! let's chat about one of the most impressive rail systems in the world - japan's trains. when you think of japanese trains, the first image that probably pops into your mind is the sleek, futuristic shinkansen, also known as the bullet train. these high-speed trains are not just a symbol of modern technology; they're a testament to japan's commitment to efficiency and punctuality. it's not an exaggeration to say that japanese trains are famous for being precisely on time. if a train is five minutes late, it's often considered a significant delay!

but it's not just the shinkansen that deserves praise. japan's entire railway network, from city subways to rural train lines, is incredibly well-organized. the trains are clean, comfortable, and surprisingly quiet, making even a regular commute a pleasant experience. what's more impressive is the frequency of these trains. in major cities like tokyo and osaka, you rarely have to wait more than a few minutes for a train, reducing the stress of travel and making commuting more predictable.

and let's not forget the level of service! train staff in japan are known for their politeness and helpfulness. whether you're a tourist struggling with your luggage or a local needing directions, there's always someone to help. plus, the stations themselves are marvels - clean, well-signed, and packed with amenities like shops and restaurants. in short, japan's trains aren't just a mode of transportation; they're an experience, reflecting the country's dedication to quality, punctuality, and customer service. so, next time you're in japan, hop on a train and enjoy the ride - it's an adventure in itself! 🚆🌸🐶🐾🫂

@ 8fb140b4:f948000c

Intro

Nostrasia 2023, a vibrant unconference, was hosted in two bustling Asian cities: Hong Kong and Tokyo, Japan. Nostriches from around the world flocked to these destinations, eager to immerse themselves in local culture, savor the cuisine, and most importantly, enjoy each other's company in person. Tokyo's event, buzzing with energy, took place in Shibuya, a district renowned for its lively nightlife and abundance of bars, clubs, and restaurants. As is tradition with Nostr events, the atmosphere was charged with excitement, symbolized by the abundant purple and orange hues.

https://v.nostr.build/k7qV.mp4

Preparations

The journey to Nostrasia began right after Nostrica, with meticulous planning to ensure the perfect venue. It was a challenge to find a location that was both spacious and accessible, offering affordable accommodation options nearby. Our diligent volunteers in Japan scoured venues in Tokyo and Yokohama before selecting the ideal spot in Shibuya.

In the days leading up to the event, volunteers, both local and from afar, gathered at the venue. Their mission: to set up everything from audio-visual equipment to stages and decorations, ensuring a warm welcome for attendees on November 1st at 9:00 AM. Despite the time crunch, the spirit of cooperation and friendliness prevailed, making the preparation phase smooth and enjoyable.

Even amidst the busy setup, there was time for breaks and socialization, keeping everyone energized and focused on the mission at hand.

Day 1 (The Beginning)

No day at Nostrasia could start without a caffeine kick or a beverage of choice. The first day witnessed a steady influx of nostriches, filling the venue with excitement and anticipation.

The day offered a mix of activities: some attendees engaged in the presentations, others relaxed in the family-friendly area, and there were even recreational spaces for all ages to enjoy, including model train setups.

The setup was designed to welcome nostriches of all stripes, whether young or old, tech-savvy or not. It was a space where everyone could feel comfortable and included.

The day culminated in a grand welcome party, complete with drinks, MAGURO (Yellowfin tuna), and karaoke.

https://v.nostr.build/Mqqa.mp4

Day 2

Following a late night, the second day of the conference started a bit later, accommodating the nocturnal adventures of the attendees. The day was packed with fascinating talks, workshops, and plenty of opportunities for meet-ups and hugs. https://v.nostr.build/q3RM.mp4

An interesting discovery for me was the concept of air replies, a novel and visually engaging way to interact on social media.

Day 3 (Final)

The final day, starting late due to the previous night's festivities, was filled with a diverse range of presentations. Topics varied from non-technical perspectives on Nostr to in-depth technical workshops and discussions. #footstr

The day was brimming with a variety of presentations in both halls of the conference center. These ranged from insightful talks about Nostr from a non-technical perspective to more in-depth technical workshops and discussions. https://v.nostr.build/R98n.mp4 https://v.nostr.build/o5Xl.mp4 https://v.nostr.build/4A6W.mp4

The event concluded with heartfelt closing remarks from the organizers, filled with gratitude and appreciation for everyone's participation and effort.

Outro

Nostrasia 2023 was a resounding success, marked by a warm, friendly atmosphere that pervaded the entire event. While some had to depart immediately after, many stayed on to explore the wonders of Japan, carrying with them memories of an unforgettable gathering. The end. 🐶🐾🫡🫂

Footnotes

• For the list of notes published about the event, use #nostrasia hashtag.
• For the official Nostrasia profile, visit @npub1nstrcu63lzpjkz94djajuz2evrgu2psd66cwgc0gz0c0qazezx0q9urg5l
• Detailed conference schedule
• Official Webside

Other pictures and videos taken before, during, and after the event

@ 8fb140b4:f948000c

Testing a brand new YakiHonne native client for iOS. Smooth as butter (not penis butter 🤣🍆🧈) with great visual experience and intuitive navigation. Amazing work by the team behind it! * lists * work

Bold text work!

Images could have used nostr.build instead of raw S3 from us-east-1 region.

Very impressive! You can even save the draft and continue later, before posting the long-form note!

🐶🐾🤯🤯🤯🫂💜

@ 2edbcea6:40558884

Happy Sunday #Nostr !

Here’s your #NostrTechWeekly newsletter brought to you by nostr:npub19mduaf5569jx9xz555jcx3v06mvktvtpu0zgk47n4lcpjsz43zzqhj6vzk written by nostr:npub1r3fwhjpx2njy87f9qxmapjn9neutwh7aeww95e03drkfg45cey4qgl7ex2

The #NostrTechWeekly is a weekly newsletter focused on the more technical happenings in the nostr-verse.

Let’s dive in!

Recent Upgrades to Nostr (AKA NIPs)

1) (Proposed) NIP 96: File Storage Integration

As a reminder NIP 96 proposes a standard way for third party service providers to offer file storage for Nostr users. Standardization allows files to stay off relays but still be relatively cross compatible if users want to have files attached to notes show up in any Nostr client. It was initially implemented a few weeks ago with the Nostur and Coracle clients utilizing the open source Nostrcheck server by nostr:npub138s5hey76qrnm2pmv7p8nnffhfddsm8sqzm285dyc0wy4f8a6qkqtzx624

NIP 96 seems to be getting momentum; now the Nostur client has added integrated nostr.build file storage in a NIP 96 compatible way giving users more options! I hope it gets merged soon 💪

2) (Proposed) Update to NIP 72: Community Posts

This proposed update to Moderated Communities would allow clients to support using event kinds other than 1. Right now, posting on moderated communities (akin to subreddits) makes it so that all posts show up without context on most Nostr clients. Kind 1 events are like tweets, but posts in moderated communities are posted in a context that’s missing on clients like Damus or Amethyst.

This proposal would encourage moderated communities to publish using a different set of event kinds so the posts only show up in clients intended for moderated communities. It continues to gain momentum. nostr:npub180cvv07tjdrrgpa0j7j7tmnyl2yr6yr7l8j4s3evf6u64th6gkwsyjh6w6 opened and closed a proposed change similar to this as this newsletter was being written, and instead threw some support onto this proposal.

This change would be reverse compatible with current Moderated Communities but still allow for cleaner feeds on clients based on their intended content focus.

Author: vivganes

Notable Projects

Zapple Pay’s lightning-based subscriptions ♻️

The team at Mutiny Wallet’s work on Zapple Pay has helped keep the flow of zaps unblocked since Apple’s capricious decisions to force Damus to disable Zaps. Now they’ve introduced “auto zapping” which is the ability to set up recurring payments (like subscriptions) in a self-sovereign way.

Zaps are great to show support, lightning-gated content is going to be helpful for content creators too, but unlocking subscriptions can truly help content creators make a living on Nostr denominated in the hardest money on Earth. This could be game changing as we’ll discuss later 😉

Authors: nostr:npub1u8lnhlw5usp3t9vmpz60ejpyt649z33hu82wc2hpv6m5xdqmuxhs46turz nostr:npub1t0nyg64g5vwprva52wlcmt7fkdr07v5dr7s35raq9g0xgc0k4xcsedjgqv & Paul Miller

Highlighter 2.0 📝

If you’re unfamiliar Highlighter is “A nostr client for your most valuable information. Your reading. Your notes. Your thoughts. A place to discover thoughtful, timeless content.” and nostr:npub1l2vyh47mk2p0qlsku7hg0vn29faehy9hy34ygaclpn66ukqp3afqutajft continues to improve it rapidly.

This latest release improves many aspects, mostly focused on making it THE best way to read, highlight, label, and save content that’s meaningful to you.

On top of that nostr:npub1l2vyh47mk2p0qlsku7hg0vn29faehy9hy34ygaclpn66ukqp3afqutajft has been improving the ability to make money as a content creator via an integration to “subscribe” to support Nostr content creators like you would on Patreon, as well as split zaps for content published via Highlighter.

If you’re not at least using Highlighter to discover content, you’re missing out. In my experience It is the highest concentration of content created by deep thinkers on the internet.

Latest conversations: Nostr adoption via content creators

Nostr’s main feature right now is that it is freedom tech. So far that hasn’t been enough of a draw for mass Nostr adoption.

We can keep building existing apps on Nostr but we’ll need something truly differentiated for people to rip and replace their content consumption habits with the ones run on Nostr.

We have some unique offerings (beyond censorship resistance) in emerging tech like Highlighter, DVMs, and Zaps. Based on what we’ve seen this week, I believe the next million monthly active users will be driven by content creators moving to Nostr.

Helping creators make money

Creators tend to flock to where they can make the most money. This is true of content creators and creators of software.

The fact that Apple apps make far more money than Android ones (despite Android dominating the smartphone market) explains why there are so many iPhone only apps.

Video creators and streamers move between Youtube and Twitch based on who is going to offer them the better income (viewership * take home rate).

If we can provide platforms where creators get to keep more of their money, it could be a game changer.

Locked into platforms

Content platforms provide two things: audience aggregation and payment aggregation.

Payments: The revenue per view of a youtube video is calculable and theoretically Youtube could pay creators their cut of the revenue per view. That isn’t practical because of transaction fees, they’d be larger than the actual transaction.

That’s why platforms serve as payment aggregators between the advertisers, themselves and the creators; settling accounts on a regular basis in amounts that make sense given the payments infrastructure available to them (credit cards and ACH).

Audience aggregation: Audiences go where creators are, but creators go where their audience is; the relationship is complicated. Sometimes individual creators have enough power to make or break a platform, but for platforms as big as Youtube that becomes much harder.

Take the example of Spotify and Joe Rogan. That move was worth it in terms of cash for Rogan, and it put Spotify on the map as a podcasting platform. It didn’t really hurt Youtube a whole lot.

The main advantage of using a content platform like Youtube, TikTok, etc is that the audience is there, you “just” need to capture them. The trade off is that you have very little power to set your price.

Audience non-portability: If a creator decides to switch from Youtube to Twitch, their followers don’t automatically port over. Creators with strong followings have an ok time when switching but not everyone has that luxury.

This leads to a power imbalance between creators and platforms. Platforms can strike down any creator they want; even though, without creators, these platforms would be nothing. In the absence of a better solution we’re stuck in this disadvantageous equilibrium.

Freeing creators with Nostr and Bitcoin

If Nostr + Bitcoin could offer creators ready-to-go solutions that would let creators keep significantly more of their revenue. It just has to be a big enough difference that people make the switch even when Bitcoin and Nostr are unfamiliar to them.

The magic combo of capabilities on Nostr would be: Nostr-based versions of all the usual apps for content consumption, as long as they’re high enough quality to not deter users. Content management tools that are familiar and quality enough for content creators. This would need to include robust file storage and streaming for content (text, video, audio, etc) Payment infrastructure in the apps (via Lightning) that have low fees and support the structures that are relevant for the content type (pay per article, pay per view, streaming sats as you listen, subscriptions, etc) Lowest-common-denominator Nostr onboarding. Imagine an end-to-end encrypted Nostr key custodian, so users that are intimidated by keypairs could have a familiar login with email and password.

In this world, new Nostr users that were asked to join by their favorite creator may never interact with the most common clients on Nostr today. They may set up a Nostr user via some “Login with Nostr” solution and then they only interact with the Nostr versions of Twitch, Youtube, Substack, etc.

If the switch is painless for users and creators and the creators make more money, it’s a no-brainer for creators to try out. If it works for them, more will come.

Taylor Swift and Grimes are good people to aim for. Both have enough autonomy to experiment with any platform they want, and both have fought to maximize artists’ take home pay. Can you imagine if we could get every Swiftie on Nostr’s version of Spotify?

Why hasn’t this happened yet?

This sounds like “value for value” right? Many talented builders and creators have attempted to crack the “value for value” nut, but something hasn’t clicked yet for mass adoption. The missing link, in my opinion, is the lack of audience portability and how that affects payments.

Value for value (streaming sats for podcasts, or paying to unlock one article at a time) requires some storage of who bought access to the content. Otherwise if you switch devices the content platform won’t know you already purchased access. Without Nostr that means signing up for that particular content app and it’s a high bar to start paying for content.

With Nostr, you can login using your Nostr keys and purchase access on any Nostr-based app, using any Lightning wallet, and that access can be attached to your Nostr pub key. It lowers the barrier for users to start paying, which means content creators capture more value.

For some kinds of content, I think all the legos are there for a creator-friendly platforms. With the recent Mutiny wallet announcement of lightning-based subscriptions, there’s no reason not to build a Nostr-based Patreon or Substack. I’ve also seen some work on ways to Zap to unlock content, making the dream of “pay per article” possible.

The last piece missing for a truly seamless on-ramp would be one of these end-to-end encrypted Nostr key custodians. That way clients could offer a “login with Nostr” button and lower the barrier for new users even further.

The race to zero take rate

Nostr naturally combats monopolies (at least for clients at this point). The reason that platforms like Youtube and Twitch have a 20-60% take rate is because they’re monopolistic. They sit on their thrones because no one has yet solved the issue of audience aggregation and portability. Nostr breaks that model.

Once creators use Nostr-based platforms, they can switch at nearly no cost. The content is theirs, and the followers are universal, so they can move to a different platform that has a lower take rate without risking their income. They don’t even have to switch platforms at all if their content is stored and unlocked via events on the Nostr Relays themselves, since those are universal across all Nostr clients.

Ideally there would be third parties that host big files (PDFs, Videos, Audio, etc) which creators pay directly. Then these content clients are simply user interfaces for users to upload and consume content. Hell, even logging in is solved by the Nostr protocol itself, and maybe another third-party login provider). The scope of what these platforms need to build and maintain is small; running them will be pretty cheap compared to running Youtube or Patreon.

At first there may be only a few Nostr-based apps because there will be some economies of scale, but over time competition will kick off a race to the bottom. Clients will eventually only be able to demand a take rate that covers operating their business (build the app, maybe offering the file hosting/streaming infrastructure, etc).

What a future

In this future, platforms have less ability to coerce creators and take their income. Platforms will have a hell of time censoring content creators. Users will get more choice on their experience and their algorithms when consuming content. And the adoption of Bitcoin as a medium of exchange would explode.

It feels like we’re on the cusp of something incredible in the Nostr-verse.

Until next time 🫡

If you want to see something highlighted, if we missed anything, or if you’re building something we didn’t post about, let us know. DMs welcome at nostr:npub19mduaf5569jx9xz555jcx3v06mvktvtpu0zgk47n4lcpjsz43zzqhj6vzk

Stay Classy, Nostr.

@ fa0165a0:03397073

Probability theory is the study of random phenomena. This post is a pilot post for potentially further posting in this series. Feedback appreciated. Introduction

Probability theory is the study of random phenomena. It is used in many fields, such as statistics, machine learning, and finance. It is also used in everyday life, for example when playing games of chance, or when estimating the risk of an event. The most classic example is the coin toss, closely followed by the dice roll.

When we toss a coin, the result is either heads or tails. In the case of an ideal coin, the “random trail” of tossing the coin has an equal probability for both outcomes. Similarly, for a die roll of a fair dice, we know that the probability for each outcome is 1/6. In the study of probability we dive deep into the mathematics of these random phenomena, how to model them, and how to calculate the probability of different events. To do this in precise terms, we define words and concepts as tools for discussing and communicating about the subject.

This is the first of what I expect to be a 15 part series of my lecture & study notes from my university course in probability theory MT3001 at Stockholm University. References to definitions and theorems will use their numeration in the course literature, even if I may rephrase them myself. The book I’ve had as a companion through this course is a Swedish book called Stokastik by Sven Erick Alm and Tom Britton; ISBN:978–91–47–05351–3. This first module concerns basic concepts and definitions, needed for the rest of the course. The language of Probability theory

An experiment is a process that produces a randomized result. If our experiment is throwing a die, we then have the following: The result of throwing the die is called an outcome, the set of all possible outcomes is called the sample space and a subset of the sample space is called an event. We will use the following notation:

outcome is the result of an experiment, denoted with a small letter, ex. 𝑢₁, 𝑢₂, 𝑢₃, …
event is the subset of the sample space, denoted with a capital letter, ex. 𝐴, 𝐵, 𝐶, …
sample space is the set of all possible outcomes of an experiment, denoted Ω.

Adding numbers to our dice example, we have the sample space Ω = {𝟏,𝟐,𝟑,𝟒,𝟓,𝟔} containing all the possible events 𝑢₁=𝟏, 𝑢₂=𝟐, 𝑢₃=𝟑, 𝑢₄=𝟒, 𝑢₅=𝟓 and 𝑢₆=𝟔. And we could study some specific sub events like the chance of getting an even number, 𝐴={𝟐,𝟒,𝟔}, or the chance of getting a prime number, 𝐵={𝟐,𝟑,𝟓}. As it happens, the probability of both 𝐴 and 𝐵 is 50%. Sample space

The sample space is the set of all possible outcomes of an experiment. It is denoted Ω. And there are two types of sample spaces, discrete and continuous. A discrete sample space is a finite or countably infinite set, and all other kind of sample spaces are called continuous.

The coin toss and the dice roll are both examples of discrete sample spaces. Studying a problem, like the temperature outside, would in reality require a continuous sample space. But in practice, we can often approximate a continuous sample space with a discrete one. For example, we could divide the temperature into 10 degree intervals, and then we would have a discrete sample space.

Remember that continuous sample spaces exist, and expect more information about them in later modules. For starters, we focus on discrete sample spaces. Set Theory notation and operations

When talking about probabilities we will arm ourselves with the language of “set theory”, it is a crucial tool for the study of probability. Feeling comfortable with the subject of set theory since before is useful, but not necessary. I will try to explain the concepts as we go along.

Even tough the events from the dice rolls are represented by numbers, it is important to note that they aren’t numbers, but rather elements. This might become more clear if we alter our example to be a deck of cards. This deck of cards have four suits Ω = {♥, ♠, ♦, ♣ } and in our experiments we draw a card from the deck and look at the suit. It’s here very obvious that we can’t add or subtract the different events with each other. But we do have the operations of set theory at our disposal. For example, if 𝐴 is the event of drawing a red card and 𝐵 is the event of drawing spades ♠, we can use the following notation: Set theory operations

Union: 𝐴 ∪ 𝐵 = {♥, ♦, ♠}, the union of 𝐴 and 𝐵.
The empty set: ∅ = {}, the empty set. A set with no elements.
Intersection: 𝐴 ∩ 𝐵 = ∅, the intersection of 𝐴 and 𝐵.
This means that 𝐴 and 𝐵 have no elements in common. And we say that 𝐴 and 𝐵 are disjoint.
Complement: 𝐴ᶜ = {♠, ♣}, the complement of 𝐴.
Difference: 𝐴 ∖ 𝐵 = {♥, ♦}, the difference of 𝐴 and 𝐵. Equivalent to 𝐴 ∩ 𝐵ᶜ.
The symbol ∈ denotes that an element is in a set. For example, 𝑢₁ ∈ Ω means that the outcome 𝑢₁ is in the sample space Ω. For our example: ♥ ∈ 𝐴 means that the suit ♥ is in the event 𝐴.

Venn diagram

A very useful visualization of set theory is the Venn diagram. Here is an example of a Venn diagram in the picture below:

In the above illustration we have: Ω = {𝟏,𝟐,𝟑,𝟒} and the two events 𝐴={𝟐,𝟑} and 𝐵={𝟑,𝟒}. Notice how the two sets 𝐴 and 𝐵 share the element 𝟑, and that all sets are subsets of the sample space Ω. The notation for the shared element 𝟑 is 𝐴 ∩ 𝐵 = {𝟑}. Useful phrasing

The different set notations may seem a bit abstract at first, at least before you are comfortable with them. Something that might be useful to do is to read them with the context of probabilities in mind. Doing this, we can read some of the different set notations as follows:

𝐴ᶜ, “when 𝐴 doesn’t happen”.
𝐴 ∪ 𝐵, “when at least one of 𝐴 or 𝐵 happens”.
𝐴 ∩ 𝐵, “when both 𝐴 and 𝐵 happens”.
𝐴 ∩ 𝐵ᶜ, “when 𝐴 happens but 𝐵 doesn’t happen”.

The Probability function

Functions map elements from one set to another. In probability theory, we are interested in mapping events to their corresponding probabilities. We do this using what we call a probability function. This function is usually denoted 𝑃 and have some requirements that we will go through in the definition below.

This function take events as input and outputs the probability of that event. For the example of a die throw, if we have the event 𝐴={𝟐,𝟒,𝟔}, then 𝑃(𝐴) is the probability of getting an even number when throwing a fair six sided dice. In this case 𝑃(𝐴)=1/2=𝑃(“even number from a dice throw”), you’ll notice that variations of descriptions of the same event can be used interchangeably.

The Russian mathematician Andrey Kolmogorov (1903–1987) is considered the father of modern probability theory. He formulated the following three axioms for probability theory: Definition 2.2, Kolmogorov’s axioms

A real-valued function 𝑃 defined on a sample space Ω is called a probability function if it satisfies the following three axioms:

𝑃(𝐴) ≥ 𝟎 for all events 𝐴.
𝑃(Ω) = 𝟏.
If 𝐴₁, 𝐴₂, 𝐴₃, … are disjoint events, then 𝑃(𝐴₁ ∪ 𝐴₂ ∪ 𝐴₃ ∪ …) = 𝑃(𝐴₁) + 𝑃(𝐴₂) + 𝑃(𝐴₃) + …. This is called the countable additivity axiom.

From these axioms it’s implied that 𝑃(𝐴) ∈ [𝟎,𝟏], which makes sense since things aren’t less than impossible or more than certain. As a rule of thumb, when talking about probabilities, we move within the range of 0 and 1. This lets us formulate the following theorem: Theorem 2.1, The Complement and Addition Theorem of probability

Let 𝐴 and 𝐵 be two events in a sample space Ω. Then the following statements are true:

1. 𝑃(𝐴ᶜ) = 𝟏 — 𝑃(𝐴)

2. 𝑃(∅) = 𝟎

3. 𝑃(𝐴 ∪ 𝐵) = 𝑃(𝐴) + 𝑃(𝐵) — 𝑃(𝐴 ∩ 𝐵)

Proof of Theorem 2.1

𝑃(𝐴 ∪ 𝐴ᶜ) = 𝑃(Ω) = 𝟏 = 𝑃(𝐴) + 𝑃(𝐴ᶜ) ⇒ 𝑃(𝐴ᶜ) = 𝟏 — 𝑃(𝐴)

This simply proves that the probability of 𝐴 not happening is the same as the probability of 𝐴 happening subtracted from 1.

𝑃(∅) = 𝑃(Ωᶜ) = 𝟏 — 𝑃(Ω) = 𝟏 — 𝟏 = 𝟎

Even though our formal proof required (1) to be proven, it’s also very intuitive that the probability of the empty set is 0. Since the empty set is the set of all elements that are not in the sample space, and the probability of an event outside the sample space is 0.

𝑃(𝐴 ∪ 𝐵) = 𝑃(𝐴 ∪ (𝐵 ∩ 𝐴ᶜ)) = 𝑃(𝐴) + 𝑃(𝐵 ∩ 𝐴ᶜ) = 𝑃(𝐴) + 𝑃(𝐵) — 𝑃(𝐴 ∩ 𝐵)

This can be understood visually by revisiting our Venn diagram. We see that the union of 𝐴 and 𝐵 has an overlapping element 𝟑 shared between them. This means that purely adding the elements of 𝐴={𝟐,𝟑} together with 𝐵={𝟑,𝟒} would double count that shared element, like this {𝟐,𝟑,𝟑,𝟒}, since we have two “copies” of the mutual elements we make sure to remove one “copy” bur removing 𝑃(𝐴 ∩ 𝐵)={𝟑} and we get 𝑃(𝐴 ∪ 𝐵)={𝟐,𝟑,𝟒}. We may refer to this process as dealing with double counting, something that is very important to have in mind when dealing with sets.

Two interpretations of probability that are useful and often used are the frequentist and the subjectivist interpretations. The frequentist interpretation is that the probability of an event is the relative frequency of that event in the long run. The subjectivist interpretation is that the probability of an event is the degree of belief that the event will occur, this is very common in the field of statistics and gambling. For the purposes of study it’s also useful to sometimes consider probabilities as areas and or masses, this is called the measure theoretic interpretation. Don’t let that word scare you off, in our context it’s just a fancy way of drawing a parallel between areas and probabilities. Think area under curves, and you’ll be fine.

@ fa0165a0:03397073

I just tested building a browser plugin, it was easier than I thought. Here I'll walk you through the steps of creating a minimal working example of a browser plugin, a.k.a. the "Hello World" of browser plugins.

First of all there are two main browser platforms out there, Chromium and Mozilla. They do some things a little differently, but similar enough that we can build a plugin that works on both. This plugin will work in both, I'll describe the firefox version, but the chromium version is very similar.

What is a browser plugin?

Simply put, a browser plugin is a program that runs in the browser. It can do things like modify the content of a webpage, or add new functionality to the browser. It's a way to extend the browser with custom functionality. Common examples are ad blockers, password managers, and video downloaders.

In technical terms, they are plugins that can insert html-css-js into your browser experience.

How to build a browser plugin

Step 0: Basics

You'll need a computer, a text editor and a browser. For testing and development I personally think that the firefox developer edition is the easiest to work with. But any Chrome based browser will also do.

Create a working directory on your computer, name it anything you like. I'll call mine hello-world-browser-plugin. Open the directory and create a file called manifest.json. This is the most important file of your plugin, and it must be named exactly right.

Step 1: manifest.json

After creation open your file manifest.json in your text editor and paste the following code:

json { "manifest_version": 3, "name": "Hello World", "version": "1.0", "description": "A simple 'Hello World' browser extension", "content_scripts": [ { "matches": ["<all_urls>"], "js": ["hello.js"] //The name of your script file. // "css": ["hello.css"] //The name of your css file. } ] }

If you wonder what the json file format is, it's a normal text file with a special syntax such that a computer can easily read it. It's the json syntax you see in the code above. Let's go through what's being said here. (If you are not interested, just skip to the next step after pasting this we are done here.)

• manifest_version: This is the version of the manifest file format. It's currently at version 3, and it's the latest version. It's important that you set this to 3, otherwise your plugin won't work.
• name: This is the name of your plugin. It can be anything you like.
• version: This is the version of your plugin. It can be anything you like.
• description: This is the description of your plugin. It can be anything you like.
• content_scripts: This is where you define what your plugin does. It's a list of scripts that will be executed when the browser loads a webpage. In this case we have one script, called hello.js. It's the script that we'll create in the next step.
• matches: This is a list of urls that the script will be executed on. In this case we have <all_urls>, which means that the script will be executed on all urls. You can also specify a specific url, like https://brave.com/*, which means that the script will only be executed on urls that start with https://brave.com/.
• js: This is a list of javascript files that will be executed. In this case we have one file, called hello.js. It's the script that we'll create in the next step.
• css: This is where you can add a list of css files that will be executed. In this case we have none, but you can add css files here if you want to.
• //: Text following these two characters are comments. They are ignored by the computer, You can add comments anywhere you like, and they are a good way to document your code.

Step 2: hello.js

Now it's time to create another file in your project folder. This time we'll call it hello.js. When created, open it in your text editor and paste the following code:

js console.log("Hello World!"); That's javascript code, and it's what will be executed when you run your plugin. It's a simple console.log statement, which will print the text "Hello World!" to the console. The console is a place where the browser prints out messages, and it's a good place to start when debugging your plugin.

Step 3: Load and launch your plugin

Firefox

Now it's time to load your plugin into your browser. Open your browser and go to the url about:debugging#/runtime/this-firefox. You should see a page that looks something like this:

Click the button that says "Load Temporary Add-on...". A file dialog will open, navigate to your project folder and select the file manifest.json. Your plugin should now be loaded and running.

Go to a website, any website, and open the inspector then navigate to the console. You'll find the inspector by right-clicking anywhere within the webpage, and click "Inspector" in the drop-down menu. When opening the console you might see some log messages from the site you visited and... you should see the text "Hello World!" printed there, from our little plugin! Congratulations!

Chrome

Open your browser and go to the url chrome://extensions/. Click the button that says "Load unpacked". A file dialog will open, navigate to your project folder and select the folder hello-world-browser-plugin. Your plugin should now be loaded and running.

Note the difference, of selecting the file manifest.json in firefox, and selecting the folder hello-world-browser-plugin in chrome. Otherwise, the process is the same. So I'll repeat the same text as above: (for those who skipped ahead..)

Go to a website, any website, and open the inspector then navigate to the console. You'll find the inspector by right-clicking anywhere within the webpage, and click "Inspector" in the drop-down menu. When opening the console you might see some log messages from the site you visited and... you should see the text "Hello World!" printed there, from our little plugin! Congratulations!

---

As you can see this isn't as complicated as one might think. Having preformed a "Hello-World!"-project is a very useful and valuable first step. These setup steps are the basics for any browser plugin, and you can build on this to create more advanced plugins.

@ 7f5c2b4e:a818d75d

What is Obsidian?

Obsidian.md is a versatile and powerful note-taking and knowledge management application that's gained immense popularity among users seeking a robust digital tool for organizing their thoughts, ideas, and information.

Obsidian boasts an array of features and benefits that can't all be covered in a single article. Instead, this #guide focuses on a unique, yet potent use case that has recently emerged - the ability to publish #Nostr notes and long-form posts directly from the app.

This capability has been made feasible through the complementary nature of Obsidian and Nostr. Obsidian is an open-source software with a thriving community and extensive support for custom plugins. On the other hand, Nostr is an open protocol with a rapidly expanding suite of tools, simplifying the integration of Nostr across various corners of the Internet. The plugin I will cover in this guide is called Nostr Writer.

Obsidian link: obsidian://show-plugin?id=nostr-writer

GitHub: https://github.com/jamesmagoo/nostr-writer

Developer: nostr:npub10a8kw2hsevhfycl4yhtg7vzrcpwpu7s6med27juf4lzqpsvy270qrh8zkw

But before we dive in, let me share some thoughts on why should one use Obsidian to publish long-form posts (and potentially even short notes) on Nostr.

Why post with Obsidian?

This is a question that naturally comes to mind: "Why use Obsidian to publish on Nostr when the legendary Nostr developers have already set up all the necessary infrastructure for browser-based publishing?" Well, there are several reasons:

1. Native Markdown Support: To begin, Obsidian employs plain text Markdown formatting for notes, just like all Nostr-based blogging platforms. This makes it an ideal choice for creating, formatting, and editing Nostr posts.

2. Illustrative Preview: While other blogging platforms offer preview tools, Obsidian has perfected this feature. It provides a beautifully customizable preview window that can be positioned anywhere in your workspace, allowing you to visualize how formatting, media, and embeds will appear in the published post[^1].

3. State-of-the-Art Flexibility: Since 2020, Obsidian has continuously improved the way writers interact with it. What sets it apart is not only the dedicated team but also its thriving community, all contributing to its refinement. Obsidian supports an extensive array of plugins, shortcuts, and hotkeys, offering unparalleled flexibility and customization. Comprehensive documentation and a ton of videos and even courses on YouTube provide a wealth of information to tailor Obsidian to your preferences.

4. Boosted Productivity: The Nostr Writer plugin is a game-changer for power users of Obsidian. If you're already using Obsidian for note-taking, employing this tool to publish your notes on Nostr is a no-brainer. If you haven't explored it yet, I strongly recommend giving it a try. It has the potential to transform how you think, plan, and structure your ideas for the better. Trying it for broader objectives will help you appreciate how well it complements Nostr.

5. Distraction-Free Composition: While you may disagree, browsers can be a significant source of distraction, with constant alerts, notifications, and blinking extensions. Composing within Obsidian offers a tranquil, clutter-free experience, fostering focus and productivity.

6. Local Record Keeping: Thanks to Nostr Writer, Obsidian keeps a local record of events you published to Nostr in a JSON file on your computer. Your long-form posts are also securely stored in the .md format on your machine, just like all the Obsidian notes you create. On top of that a separate tab holding all of your long-form posts posted via Obsidian is created.

nostr: note1z70v5fsty7v7kaaslsv3ckru50nxym32a62kgx0z7cjdure39hps363sh7

1. Drafts You Can Count On: Drafts are often a weak point in long-form platforms. Even though Nostr developers have addressed some of these concerns, the "vanishing drafts problem" still lingers. Obsidian, designed with data safety in mind, stores all your notes locally on your device. Whether you open your laptop tomorrow or in a year, your files will be there, safe from external disruptions. For added redundancy, consider using Obsidian Sync, which encrypts and synchronizes your notes across your chosen devices.

While there are more benefits to utilizing Obsidian for both Nostr publishing and in your general workflow, these reasons should provide a solid understanding. Now, let's shed some light on the Nostr Writer plugin.

Nostr Writer

I stumbled upon Obsidian not too long ago, all thanks to nostr:npub1zvvv8fm7w2ngwdyszg3y6zgp6vwqlht8zrr8wcmjaxjecrvpjfwsd0zs7w. He's also the one who introduced me to the Nostr Writer plugin. Until recently, I primarily used Obsidian "as intended" - for documenting my thoughts and writing articles. What I found especially convenient was using it to compose long-form Nostr posts. And then, the revelation came when I discovered the Nostr Writer plugin - it transformed the experience. No more copy-pasting and meticulous adjustments were required; I can simply compose, add a cover image and description, and publish - it's as straightforward as that.

As I mentioned earlier, Obsidian boasts a vast library of community-driven plugins. To begin using Nostr Writer, simply install the plugin from the "Community plugins" section and navigate to the plugin settings to set up your publishing workflow.

You can install the plugin by clicking this link while having Obsidian open on your device, or by going to the "Community plugins" tab in the settings and typing "Nostr" in the search field.

Once the plugin is installed, you'll need to customize it to enable publishing your Obsidian notes to Nostr.

Primarily, you'll need to paste your private key (nsec) into the corresponding field. Additionally, I recommend configuring your relays to ensure the widest reach for your posts. If you're unfamiliar with Nostr relays or wish to enhance your understanding, you can explore my relay guide here.

Many Nostr users naturally have concerns about sharing their private keys with apps. In this case, worry not. Your private key is stored exclusively on your local device and never leaves it. More details can be found here. Even if you use Obsidian sync to keep your notes updated across multiple devices, all information is locally encrypted and safeguarded by the password of your choice. Neither the Obsidian developers nor the plugin developer have access to your files. For additional information, you can refer to the "Security and privacy" section of the Obsidian documentation.

As you can see in the screenshot above, Nostr Writer also provides the option to post short notes. By toggling the corresponding slider, a pencil icon will appear on the sidebar, allowing you to post short notes without leaving Obsidian:

While I wouldn't claim that the plugin surpasses any of the "Twitter-like" Nostr clients, it can prove handy if you're already working within Obsidian and wish to share a quote or any other snippet of information you've come across in your notes.

Publishing

Publishing posts with Nostr Writer is straightforward. If you're already familiar with Obsidian, composing and formatting will be a total breeze, and the actual posting process is no different from posting with Habla, or any other Nostr-native blogging platform.

The only thing that may differ from some Nostr platforms is that Nostr Writer does not provide a specific field for adding hashtags when publishing. Instead, you should incorporate them directly into your text.

Once you've finished crafting your blog post, simply click on the upload icon in the side menu to specify the title, add a summary, and attach a cover image.

When you're ready, click "Confirm and Publish."

Another point to note is the relays indicator in the bottom-left corner. Relay connection may get interrupted if left inactive for a while, but a simple click on the widget will reconnect you to Nostr in no time.

Practice makes perfect

As I mentioned earlier, I find this approach to publishing long-form posts on Nostr the most efficient and convenient. Moreover, there are numerous improvements in the pipeline for the plugin, which is nothing short of exciting.

With that said, it's worth visiting Habla after publishing your post to double-check that everything appears as intended. Initially, you might encounter some formatting peculiarities that you'll need to get accustomed to, but with practice, you'll effortlessly master them. Soon, you won't even have to worry about how the article looks in Nostr clients because you'll be able to visualize every single aspect of your post in your mind.

---

I hope you found this guide useful and consider utilizing Obsidian for both publishing Nostr posts and elevating your overall productivity. If that's the case, please show your support for nostr:npub10a8kw2hsevhfycl4yhtg7vzrcpwpu7s6med27juf4lzqpsvy270qrh8zkw' work.

Please feel free to share your thoughts and suggestions—I'm always eager to hear from you! Don't forget that my Habla blog page contains a ton of Nostr guides, so you can find answers to almost any Nostr-related questions. If there are specific topics you believe I should cover, do let me know.

See you on the other side of the Nostr rabbit hole.

Tony

---

P.S. This post was composed, formatted and published to Nostr from Obsidian. No Nostr-related blogging platform was used.

[^1]: Nostr-native syntax, including tagging and Nostr-events embeds, is an exception here. Not all platforms on the Internet currently support Nostr syntax standards like tagging users with their npub, as in nostr:npub10awzknjg5r5lajnr53438ndcyjylgqsrnrtq5grs495v42qc6awsj45ys7, so it may not be available for preview. However, tags and embeds will be displayed on Habla. You can learn more about Habla's features in my previous guide here.

@ 8fb140b4:f948000c

As the title states, scratch behind my ear and you get it. 🐶🐾🫡

@ 78733875:4eb851f2

After announcing our first wave of grants for bitcoin[^fn-btc] and nostr[^fn-nostr] projects, we are pleased to announce an additional wave of grants for open-source projects in the space:

[^fn-btc]: First Wave of Bitcoin Grants [^fn-nostr]: First Wave of Nostr Grants

• BDK
• LNbits
• Watchdescriptor
• Stratum V2 Testing \& Benchmarking Tool
• Fedimint Modules and Resources
• Amber: Nostr Event Signer
• Nostr UI/UX Development
• Nostr Use-Case Exploration \& Education

The first five grants are sourced from our General Fund, the last three—being nostr projects—from our Nostr Fund. This brings the total number of OpenSats grants to 41, adding to the grants we previously announced in July.

Once again, let's take a closer look at each of the projects to see how they align with the OpenSats mission.

---

BDK

Bitcoin Development Kit (BDK) is a set of libraries and tools that allows you to seamlessly build cross-platform on-chain bitcoin wallets without having to re-implement standard bitcoin data structures, algorithms, and protocols. BDK is built on top of the powerful rust-bitcoin and rust-miniscript libraries and adds features for managing descriptor-based wallets, syncing wallets to the bitcoin blockchain, viewing transaction histories, managing and selecting UTXOs to create new transactions, signing, and more. The core BDK components are written in Rust, but the team also maintains Kotlin and Swift language bindings for use in mobile projects. There are also Python bindings, and React Native and Flutter support is being actively developed.

Repository: bitcoindevkit/bdk
License: Apache 2.0 / MIT

LNbits

LNbits is used by a multitude of projects in the bitcoin space, especially as part of their lightning payments stack. Being easy to build on through its extension framework, LNbits has been pioneering various cutting-edge solutions and experiments in the world of bitcoin, lightning, and nostr.

The project has a thriving maker community building various hardware devices such as Lightning ATMs, point-of-sale devices, DIY hardware wallets, and nostr signing devices. The modular design of LNbits makes it attractive to users and tinkerers alike, as its plugin architecture makes it easy to extend and understand.

Repository: lnbits/lnbits
License: MIT

Watchdescriptor

watchdescriptor is a CLN plugin written in Rust that connects a business's treasury wallet to its CLN node. It utilizes cln-plugin and the BDK library to track coin movements in registered wallets and report this information to the bookkeeper plugin.

The plugin enables businesses to design a complete treasury using Miniscript and import the resulting descriptor into CLN. Since bookkeeper already accounts for all coin movements internal to CLN, this plugin is the last piece businesses need in order to unify all their bitcoin accounting in one place. This enables businesses to account for all inflows and outflows from their operations, streamlining tax reporting and financial analysis.

The watchdescriptor project is part of a broader vision to transform the lightning node (particularly CLN) into a financial hub for businesses, enabling them to conduct operations without reliance on any third parties.

Repository: chrisguida/watchdescriptor
License: MIT

Stratum V2 Testing & Benchmarking Tool

The Stratum V2 Testing & Benchmarking Tool allows the bitcoin mining industry to test and benchmark Stratum V2 performance against Stratum V1. The tool supports different mining scenarios to help miners make informed decisions and evaluate their profitability. The goal of the project is to motivate miners to upgrade to Stratum V2, increasing their individual profits and making the Bitcoin network more resilient in the process.

Repository: stratum-mining/stratum @GitGab19
License: Apache 2.0 / MIT

Fedimint Modules and Resources

Fedimint is a federated Chaumian e-cash mint backed by sats with deposits and withdrawals that can occur on-chain or via lightning. It can be understood as a scaling and privacy layer as well as an adoption accelerator for Bitcoin.

The goal of this particular project is to improve the Fedimint UI and develop free and open resources for developers and "Guardians" to enable more people to run and develop on Fedimint.

Repository: fedimint/ui @EthnTuttle
License: MIT

Amber: Nostr Event Signer

Amber is a nostr event signer for Android. It allows users to keep their nsec segregated in a single, dedicated app. The goal of Amber is to have your smartphone act as a NIP-46 signing device without any need for servers or additional hardware. "Private keys should be exposed to as few systems as possible as each system adds to the attack surface," as the rationale of said NIP states. In addition to native apps, Amber aims to support all current nostr web applications without requiring any extensions or web servers.

Repository: greenart7c3/Amber
License: MIT

Nostr UI/UX Development

The goal of this project is to help improve the UI/UX of major nostr clients, starting with Gossip and Coracle, emphasizing the onboarding process as well as usability and accessibility. One part of onboarding is solving the discoverability problem that nostr has in the first place. Solving the problem of jumping in and out of the nostr world is what motivated the development of njump, which was redesigned as part of these efforts and is now live at nostr.com.

In addition to client-specific improvements, generic design modules and learnings will be incorporated into the Nostr Design project for others to use.

Activity: github.com/dtonon @dtonon
License: MIT

Nostr Use-Case Exploration & Education

As of today, most nostr clients implement social media applications on top of the nostr protocol. However, nostr allows for various use cases, many of which go beyond social media. Two examples are Listr and Ostrich, a list management tool and job board, respectively.

In addition to use-case exploration, this project will continue to educate users and developers alike, be it via Nostr How or various video series, e.g., explaining how to build upon NDK.

Activity: github.com/erskingardner @jeffg
License: MIT / GPL-3.0 / CC BY-NC-SA 4.0

---

We have more grants in the pipeline and will provide funding for many more projects in the future. Note that we can only fund those projects which reach out and apply. If you are an open-source developer who is aligned with our mission, don't hesitate to apply for funding.

@ 8fb140b4:f948000c

Test Bounty Note

@ d3d74124:a4eb7b1d

This plan was GPT generated originally but then tweaked by myself as the idea fleshed itself out. All feedback welcome and encouraged.

Shenandoah Bitcoin

1. Executive Summary

Shenandoah Bitcoin is a for-profit community organization based in Frederick County, VA, uniquely blending the world of agriculture and STEM. Our mission is to foster community spirit, stimulate interest in agricultural technology, and promote understanding of Bitcoin, while providing enriching educational opportunities and ensuring sustainable business operations.

2. Company Description

Shenandoah Bitcoin is committed to delivering value to our local community. Our unique approach intertwines traditional agricultural practices, modern STEM concepts, and the world of digital currencies, specifically Bitcoin. Our activities cater to all age groups, focusing on fostering community engagement, hands-on learning experiences, and contributing to the overall welfare of our community.

What’s in a name?

Shenandoah Bitcoin. Shenandoah - an old and historied land. Bitcoin - a cutting edge technological advancement. Both encompass multiple industries, from energy and manufacturing, to farming and data centers. Both built using Proof of Work.

3. Services

We offer a range of services, including:

Family-friendly events: Agriculture, STEM, and Bitcoin-themed festivals, fairs, workshops, and community gatherings. Educational programs: Classes, seminars, and workshops on agricultural technology, STEM principles, and understanding and using Bitcoin. Facility Rentals: Spaces available for private events, business meetings, and community gatherings.

4. Membership Benefits

We offer tiered membership packages with benefits such as:

a. Silver Membership: Includes access to regular events, discounts on educational programs, and priority booking for facility rentals.

b. Gold Membership: All Silver benefits, free access to select educational programs, and further discounted facility rentals.

c. Platinum Membership: All Gold benefits, free access to all educational programs, highest priority and maximum discounts on facility rentals, and exclusive invitations to special events.

Member’s opting to pay in Bitcoin receive 10% off all pricing.

5. Market Analysis

Our primary market is the local community in Frederick County and Winchester, VA, which consists of various demographic groups. Our secondary market includes neighboring communities, tourists, businesses, and educational institutions interested in the intersection of agriculture, STEM, and Bitcoin. Understanding that facility use and events to be a drawing factor for all demographics, we outline demographic specific analysis below.

STEM professionals in the area may work remotely or commute toward DC and not interact much with their agricultural neighbors, but a desire for good quality food exists for many. In addition to events, drawing the STEM demographic in will be connections to CSAs, ranchers, and homesteaders for access to fresh locally grown food. Offering a child's play room adjacent to some office space, is a compelling benefit for the laptop class that is often in STEM professions.

Non-industrial food producers and homesteaders may not have the focus or resources for marketing and sales. By offering a physical touch point for them and direct connections to consumers, food producers benefit from membership. Having more options for drop off/pick up of various produced goods, makes it attractive for both the consumers and producers as coordination can be asynchronous.

Bitcoiners have a wide range of sub-demographics, including farmers and software engineers. Some travel hours over car and plane to attend bitcoin themed events. The topics of STEM and agriculture are of shared interest to non-trivially sized communities of bitcoiners. Having a physical touch point for bitcoiners will draw in some members just for that. Building fellowship is desired and sought in bitcoin.

5.1 Market Trends

The blending of agriculture, STEM fields, and Bitcoin is a unique concept with increasing interest in sustainable farming and ranching, food sovereignty, and health. Shenandoah Bitcoin is poised to tap into this growing interest and offer unique value to our community.

5.2 Market Needs

Our market requires initiatives that foster community engagement, promote understanding of agri-tech and Bitcoin, and provide a versatile space for events and learning.

6. Marketing and Sales Strategy

We will employ a blend of digital marketing, traditional advertising, and strategic partnerships. Our main marketing channels will be word of mouth, social media, local press, and our website. Partnerships with local small businesses, homesteaders, schools, agricultural organizations, and bitcoin companies will form a key part of our outreach strategy.

7. Organizational Structure

Shenandoah Bitcoin will be led by a CEO, supported by a management team responsible for daily operations, event planning, marketing, and community outreach. Event management and logistics will be handled by part-time staff and volunteers.

8. Financial Projections

Our revenue will be generated from membership fees, charges for events and educational programs, and facility rentals.

9. Funding Request

[If seeking additional funding, describe your needs and how the funds will be used]

10. Exit Strategy

Should it become necessary to dissolve the business, assets such as property, equipment, and any remaining cash reserves after meeting liabilities will be sold. Investors would receive their share of the remaining assets according to their proportion of ownership.

11. Conclusion

Shenandoah Bitcoin is a unique community organization bringing together agriculture, STEM, and Bitcoin in Frederick County, VA. Our distinctive approach is designed to deliver both profits and social impact, resonating strongly with our target market and positioning us for sustainable growth.

@ 52b4a076:e7fad8bd

What is NIP-05 really?

If you look at the spec, it's a way to map Nostr public keys to DNS-based internet identifiers, such as name@example.com.

If you look at Nostr Plebs:

It's a human readable identifier for your public key. It makes finding your profile on Nostr easier. It makes identifying your account easier.

If you look at basically any client, you see a checkmark, which you assume means verification.

If you ask someone, they probably will call it verification.

How did we get here?

Initially, there was only one client, which was (kind of) the reference implementation: Branle.

When it added support for NIP-05 identifiers, it used to replace the display name with the NIP-05 identifier, and it had to distinguish a NIP-05 from someone setting their display name to a NIP-05. So they added a checkmark...

Then there was astral.ninja and Damus: The former was a fork of Branle, and therefore inherited the checkmark. Damus didn't implement NIP-05 until a while later, and they added a checkmark because Astral and other clients were doing it.

And then came new clients, all copying what the previous ones did... (Snort originally did not have a checkmark, but that changed later.)

The first NIP-05 provider

Long story short, people were wondering what NIP-05 is and wanted it, and that's how Nostr Plebs came to be.

They initially called their service verification. Somewhere between January and February, they removed all mentions to verification except one (because people were searching for it), and publicly said that NIP-05 is not verification. But that didn't work.

Then, there were the new NIP-05 providers, some understood perfectly what a NIP-05 identifier is and applied the correct nomenclature. Others misnamed it as verification, adding confusion to users. This made the problem worse on top of the popular clients showing checkmarks.

(from this point in the article we'll refer to it as a Nostr address)

And so, the scams begin

Spammers and scammers started to abuse Nostr addresses to scam people: - Some providers has been used by fake crypto airdrop bots. - A few Nostr address providers have terminated multitude of impersonating and scam identifiers over the past weeks.

This goes to show that Nostr addresses don't verify anything, they are just providers of human readable handles.

Nostr addresses can be proof of association

Nostr addresses can be a proof of association. The easiest analogy to understand is email:

jack@cash.app -> You could assume this is the Jack that works at Cash App.

jack@nostr-address-provider.example.com -> This could be any Jack.

What now?

We urge that clients stop showing a checkmark for all Nostr addresses, as they are not useful for verification.

We also urge that clients hide checkmarks for all domain names, without exception in the same way we do not show checkmarks for emails.

Lastly, NIP-05 is a nostr address and that is why we urge all clients to use the proper nomenclature.

Signed:

• Semisol, Nostr Plebs (semisol@nostrplebs.com)
• Quentin, nostrcheck.me (quentin@nostrcheck.me)
• Derek Ross, Nostr Plebs (derekross@nostrplebs.com)
• Bitcoin Nostrich, Bitcoin Nostr (BitcoinNostrich@BitcoinNostr.com)
• Remina, zaps.lol (remina@zaps.lol)
• Harry Hodler, nostr-check.com (harryhodler@nostr-check.com)

@ 32092ec1:8e9fd13a

Bitcoin maximalism, to many, has evolved from a belief that bitcoin is the only crypto asset worth owning to a belief that bitcoin is the only asset worth owning. In addition, many observe that those who declare themselves to be bitcoin maximalists have also declared their allegiance to many other lifestyle choices. This was well articulated by Jameson Lopp in his blog post “A History of Bitcoin Maximalism.”

While some (myself included for a while) embrace the title of bitcoin maximalist, perhaps out of spite given that it was originally intended to be a derogatory term, I eventually have decided to reject it. While I do not own any other crypto assets, and I do believe that bitcoin offers the best risk adjusted investment across many asset classes, it is not, nor could it ever realistically be, my only investment. Due to the ambiguity of the definition of a “bitcoin maximalist” to some, even the fact that I have equity in my primary residence may call into question my status as a bitcoin maximalist. Although most people likely agree that this point of view is nonsensical, I feel that it is also completely pointless to take the time to defend the purity of my “bitcoin maximalism;” and so, I reject it. In place of the bitcoin maximalist label, I hereby declare myself to be a truth maximalist.

The truth is that 99% of non-bitcoin crypto assets are completely worthless; specifically, what I mean is that they literally add zero net positivity to humanity. The remaining 1% of non-bitcoin crypto assets may indeed serve some limited improvements to existing systems or other alternative benefits; however, these crypto assets are also, in my opinion, already highly over valued given the magnitude of the problems they are intending to solve. Most of the incremental improvements offered by cryptos are related to marginally improving systems based on fiat money and the banking industry both of which bitcoin intends to largely obsolete and are still net negative to humanity and designed to syphon wealth from the powerless to the powerful.

I do believe that open source, decentralized, cryptographic solutions will play additional roles in society and offer an opportunity to disrupt many existing centralized solutions. However, most of these solutions will not be investable assets, just as the internet itself is not an investable asset.

I believe it also to be true that investment properties intended for yield generation come with a host of additional costs and risks that are rarely properly accounted for when assessing the value of these assets. After accounting for the probability weighted costs of evictions, seizures, taxes, maintenance, inflation, and loan interest, I find it difficult to justify these investments over bitcoin held in self-custody.

Many other investable assets that simply sit on a bank’s balance sheet (e.g., stocks, bonds, etc.) can easily be seized if any number of three letter agencies decided that you should not have these assets. This can be done with no due process and does not require any in depth investigation to determine the validity of their claims. I believe that the probability of these types of seizures is much higher for known bitcoiners who are also critical of the government and the media, especially if current financial systems begin to collapse and/or if bitcoin’s value dramatically increases.

Beyond seizure of your individual assets, as the world begins to divest from the highly inflated store of value assets listed on the NYSE and NASDAQ due to seizure risks at the sovereign level, the risk of extreme inflation adjusted devaluation of your portfolio should also be considered. Compounding this risk is the opportunity cost associated with the fact that some of the wealth that may be withdrawn from the US stock market is also likely going to flow into bitcoin. These risks are rarely accounted for or quantified when determining the value of a stock portfolio in contrast to simply holding bitcoin in self-custody.

My opinions on these matters are common among bitcoiners who are largely labeled bitcoin maximalists. However, the title of truth maximalist also fits nicely when trying to counter some of the softer points made in Lopp’s blog post mentioned above. My thesis is that most people who have adopted the bitcoin maximalist “lifestyle” choices have done so as a result of their quest for truth, not as a result of their desire to virtue signal their status as bitcoin maximalists.

The truth is that a carnivore diet is much healthier than governments, media and academia would like you to believe (disclosure: I have never tried a carnivore diet)

The truth is that weightlifting is more beneficial than cardio to overall health (disclosure: I am not into weightlifting)

The truth is that traditional gender roles are beneficial to mental health (disclosure: although my wife is a full-time, stay-at-home mom, my marriage is far from perfect).

The truth is that extreme consequences from greenhouse gasses in the atmosphere are extrapolatory and predictions have historically failed miserably (disclosure: I do not think there is zero risk of extreme disasters from excessive levels of carbon in the atmosphere).

The truth is that seed oils are terrible for you (disclosure: I have ingested seed oils since discovering this).

The truth is that COVID vaccines pointlessly add risk to healthy people and children (disclosure: I received two doses of the COVID vaccine prior to realizing this truth and my wife still disagrees with me on this).

The truth is that natural health solutions are often more beneficial than big pharma would like you to believe (disclosure: I have not used any exotic natural remedies).

The truth is that modern art and architecture is garbage (disclosure: this is only a personal opinion).

The Truth is that Jesus Christ died on a cross and ascended into Heaven in order to save the world from sin (disclosure: although I have always been a Christian, over the last year or so I have dedicated a significant amount of time researching this and so far, everything is supporting this to be literally true and much more easily believable than you might think).

Maybe you disagree with some of these things that I have determined to be true. But let me ask, have done your own research? What is your basis for a counter argument to any of these truths? Did you verify or are you trusting someone else’s opinion? If you are trusting someone else’s research, did you investigate their credibility or determine if they have significant biases? Certainly, my opinions on the topics listed above not always based on exhaustive independent research, but I did approach each with skepticism and did not always believe these things with conviction prior to looking into them. I think any bitcoiner would agree that if you are trusting fiat funded academia, government organizations or mainstream media, you may need to do more research.

The truth is that I will continue to seek the truth and I will encourage others to do the same. The truth is that I welcome new information and listening to opinions that counter my beliefs. When choosing to have strong conviction in minority opinions about the truth, it is extremely valuable to be able to articulate and refute the points that are contrary to your beliefs. It is also important to be able to change your mind when presented with sufficient evidence against your opinion. This is what it means to be a truth maximalist. It just so happens that the truth is that bitcoin is the only crypto asset worth investing in. Don’t believe me? Prove it.

786973

@ d2e97f73:ea9a4d1b

There’s a lot of conversation around the #TwitterFiles. Here’s my take, and thoughts on how to fix the issues identified.

I’ll start with the principles I’ve come to believe…based on everything I’ve learned and experienced through my past actions as a Twitter co-founder and lead:

1. Social media must be resilient to corporate and government control.
2. Only the original author may remove content they produce.
3. Moderation is best implemented by algorithmic choice.

The Twitter when I led it and the Twitter of today do not meet any of these principles. This is my fault alone, as I completely gave up pushing for them when an activist entered our stock in 2020. I no longer had hope of achieving any of it as a public company with no defense mechanisms (lack of dual-class shares being a key one). I planned my exit at that moment knowing I was no longer right for the company.

The biggest mistake I made was continuing to invest in building tools for us to manage the public conversation, versus building tools for the people using Twitter to easily manage it for themselves. This burdened the company with too much power, and opened us to significant outside pressure (such as advertising budgets). I generally think companies have become far too powerful, and that became completely clear to me with our suspension of Trump’s account. As I’ve said before, we did the right thing for the public company business at the time, but the wrong thing for the internet and society. Much more about this here: https://twitter.com/jack/status/1349510769268850690

I continue to believe there was no ill intent or hidden agendas, and everyone acted according to the best information we had at the time. Of course mistakes were made. But if we had focused more on tools for the people using the service rather than tools for us, and moved much faster towards absolute transparency, we probably wouldn’t be in this situation of needing a fresh reset (which I am supportive of). Again, I own all of this and our actions, and all I can do is work to make it right.

Back to the principles. Of course governments want to shape and control the public conversation, and will use every method at their disposal to do so, including the media. And the power a corporation wields to do the same is only growing. It’s critical that the people have tools to resist this, and that those tools are ultimately owned by the people. Allowing a government or a few corporations to own the public conversation is a path towards centralized control.

I’m a strong believer that any content produced by someone for the internet should be permanent until the original author chooses to delete it. It should be always available and addressable. Content takedowns and suspensions should not be possible. Doing so complicates important context, learning, and enforcement of illegal activity. There are significant issues with this stance of course, but starting with this principle will allow for far better solutions than we have today. The internet is trending towards a world were storage is “free” and infinite, which places all the actual value on how to discover and see content.

Which brings me to the last principle: moderation. I don’t believe a centralized system can do content moderation globally. It can only be done through ranking and relevance algorithms, the more localized the better. But instead of a company or government building and controlling these solely, people should be able to build and choose from algorithms that best match their criteria, or not have to use any at all. A “follow” action should always deliver every bit of content from the corresponding account, and the algorithms should be able to comb through everything else through a relevance lens that an individual determines. There’s a default “G-rated” algorithm, and then there’s everything else one can imagine.

The only way I know of to truly live up to these 3 principles is a free and open protocol for social media, that is not owned by a single company or group of companies, and is resilient to corporate and government influence. The problem today is that we have companies who own both the protocol and discovery of content. Which ultimately puts one person in charge of what’s available and seen, or not. This is by definition a single point of failure, no matter how great the person, and over time will fracture the public conversation, and may lead to more control by governments and corporations around the world.

I believe many companies can build a phenomenal business off an open protocol. For proof, look at both the web and email. The biggest problem with these models however is that the discovery mechanisms are far too proprietary and fixed instead of open or extendable. Companies can build many profitable services that complement rather than lock down how we access this massive collection of conversation. There is no need to own or host it themselves.

Many of you won’t trust this solution just because it’s me stating it. I get it, but that’s exactly the point. Trusting any one individual with this comes with compromises, not to mention being way too heavy a burden for the individual. It has to be something akin to what bitcoin has shown to be possible. If you want proof of this, get out of the US and European bubble of the bitcoin price fluctuations and learn how real people are using it for censorship resistance in Africa and Central/South America.

I do still wish for Twitter, and every company, to become uncomfortably transparent in all their actions, and I wish I forced more of that years ago. I do believe absolute transparency builds trust. As for the files, I wish they were released Wikileaks-style, with many more eyes and interpretations to consider. And along with that, commitments of transparency for present and future actions. I’m hopeful all of this will happen. There’s nothing to hide…only a lot to learn from. The current attacks on my former colleagues could be dangerous and doesn’t solve anything. If you want to blame, direct it at me and my actions, or lack thereof.

As far as the free and open social media protocol goes, there are many competing projects: @bluesky is one with the AT Protocol, nostr another, Mastodon yet another, Matrix yet another…and there will be many more. One will have a chance at becoming a standard like HTTP or SMTP. This isn’t about a “decentralized Twitter.” This is a focused and urgent push for a foundational core technology standard to make social media a native part of the internet. I believe this is critical both to Twitter’s future, and the public conversation’s ability to truly serve the people, which helps hold governments and corporations accountable. And hopefully makes it all a lot more fun and informative again.

💸🛠️🌐 To accelerate open internet and protocol work, I’m going to open a new category of #startsmall grants: “open internet development.” It will start with a focus of giving cash and equity grants to engineering teams working on social media and private communication protocols, bitcoin, and a web-only mobile OS. I’ll make some grants next week, starting with $1mm/yr to Signal. Please let me know other great candidates for this money.

@ 82341f88:fbfbe6a2

There’s a lot of conversation around the #TwitterFiles. Here’s my take, and thoughts on how to fix the issues identified.

I’ll start with the principles I’ve come to believe…based on everything I’ve learned and experienced through my past actions as a Twitter co-founder and lead:

1. Social media must be resilient to corporate and government control.
2. Only the original author may remove content they produce.
3. Moderation is best implemented by algorithmic choice.

The Twitter when I led it and the Twitter of today do not meet any of these principles. This is my fault alone, as I completely gave up pushing for them when an activist entered our stock in 2020. I no longer had hope of achieving any of it as a public company with no defense mechanisms (lack of dual-class shares being a key one). I planned my exit at that moment knowing I was no longer right for the company.

The biggest mistake I made was continuing to invest in building tools for us to manage the public conversation, versus building tools for the people using Twitter to easily manage it for themselves. This burdened the company with too much power, and opened us to significant outside pressure (such as advertising budgets). I generally think companies have become far too powerful, and that became completely clear to me with our suspension of Trump’s account. As I’ve said before, we did the right thing for the public company business at the time, but the wrong thing for the internet and society. Much more about this here: https://twitter.com/jack/status/1349510769268850690

I continue to believe there was no ill intent or hidden agendas, and everyone acted according to the best information we had at the time. Of course mistakes were made. But if we had focused more on tools for the people using the service rather than tools for us, and moved much faster towards absolute transparency, we probably wouldn’t be in this situation of needing a fresh reset (which I am supportive of). Again, I own all of this and our actions, and all I can do is work to make it right.

Back to the principles. Of course governments want to shape and control the public conversation, and will use every method at their disposal to do so, including the media. And the power a corporation wields to do the same is only growing. It’s critical that the people have tools to resist this, and that those tools are ultimately owned by the people. Allowing a government or a few corporations to own the public conversation is a path towards centralized control.

I’m a strong believer that any content produced by someone for the internet should be permanent until the original author chooses to delete it. It should be always available and addressable. Content takedowns and suspensions should not be possible. Doing so complicates important context, learning, and enforcement of illegal activity. There are significant issues with this stance of course, but starting with this principle will allow for far better solutions than we have today. The internet is trending towards a world were storage is “free” and infinite, which places all the actual value on how to discover and see content.

Which brings me to the last principle: moderation. I don’t believe a centralized system can do content moderation globally. It can only be done through ranking and relevance algorithms, the more localized the better. But instead of a company or government building and controlling these solely, people should be able to build and choose from algorithms that best match their criteria, or not have to use any at all. A “follow” action should always deliver every bit of content from the corresponding account, and the algorithms should be able to comb through everything else through a relevance lens that an individual determines. There’s a default “G-rated” algorithm, and then there’s everything else one can imagine.

The only way I know of to truly live up to these 3 principles is a free and open protocol for social media, that is not owned by a single company or group of companies, and is resilient to corporate and government influence. The problem today is that we have companies who own both the protocol and discovery of content. Which ultimately puts one person in charge of what’s available and seen, or not. This is by definition a single point of failure, no matter how great the person, and over time will fracture the public conversation, and may lead to more control by governments and corporations around the world.

I believe many companies can build a phenomenal business off an open protocol. For proof, look at both the web and email. The biggest problem with these models however is that the discovery mechanisms are far too proprietary and fixed instead of open or extendable. Companies can build many profitable services that complement rather than lock down how we access this massive collection of conversation. There is no need to own or host it themselves.

Many of you won’t trust this solution just because it’s me stating it. I get it, but that’s exactly the point. Trusting any one individual with this comes with compromises, not to mention being way too heavy a burden for the individual. It has to be something akin to what bitcoin has shown to be possible. If you want proof of this, get out of the US and European bubble of the bitcoin price fluctuations and learn how real people are using it for censorship resistance in Africa and Central/South America.

I do still wish for Twitter, and every company, to become uncomfortably transparent in all their actions, and I wish I forced more of that years ago. I do believe absolute transparency builds trust. As for the files, I wish they were released Wikileaks-style, with many more eyes and interpretations to consider. And along with that, commitments of transparency for present and future actions. I’m hopeful all of this will happen. There’s nothing to hide…only a lot to learn from. The current attacks on my former colleagues could be dangerous and doesn’t solve anything. If you want to blame, direct it at me and my actions, or lack thereof.

As far as the free and open social media protocol goes, there are many competing projects: @bluesky is one with the AT Protocol, nostr another, Mastodon yet another, Matrix yet another…and there will be many more. One will have a chance at becoming a standard like HTTP or SMTP. This isn’t about a “decentralized Twitter.” This is a focused and urgent push for a foundational core technology standard to make social media a native part of the internet. I believe this is critical both to Twitter’s future, and the public conversation’s ability to truly serve the people, which helps hold governments and corporations accountable. And hopefully makes it all a lot more fun and informative again.

💸🛠️🌐 To accelerate open internet and protocol work, I’m going to open a new category of #startsmall grants: “open internet development.” It will start with a focus of giving cash and equity grants to engineering teams working on social media and private communication protocols, bitcoin, and a web-only mobile OS. I’ll make some grants next week, starting with $1mm/yr to Signal. Please let me know other great candidates for this money.

@ be318ab6:dd25a806

Howdy y'all,

This is the Ramble #001

I was gifted extra spare time (layoffs), and I'm excited to put it into learning about some of the new exciting things swirling around us at an ever-accelerating speed & also about the good old ever-useful manual skills, which are disappearing almost at the same rate.

The focus will be on anti-fragility tools and skills. I'll be touching on the the topics of Nostr, AI, Bitcoin, Privacy and self-sufficiency skills like woodworking or food production. I'll include any building just for the sake of it (I get more value myself and motivation to do more of it if I can show off something tangible, I guess). It's not gonna be the most frontier-breaking r0ckstar knowledge, but it will humbly keep moving forward one step at the time along with my selfish pursuit of improving my knowledge and skills along these vectors. I also won't avoid some rants about the insane corruption in our Money and all the downstream problems it brings.

Why?

1. Why having a blog? * I want to practice my writing. Not to challenge the AI, but just to better remember the learnings, and to clarify & structure my thoughts. * The public record forces accountability on me. I want to commit to a habit of writing a few posts per week.

2. Why it's on Nostr? * When dozens of the smartest and most honest individuals I respect flock to this like a bunch of crazy birds, it's something I don't want to miss out on, and I want to get intimately familiar with the tech. * It's an uncensorable protocol that allows you to own your data and can re-architect many broken things on the current web. * Easy for me to push my tip jar in y'alls faces and see if anyone gets any real value out of this * And, I just wanted to play with it. Some clients still might be buggy, but the speed of development and improvements is lightning miles away from anything I've seen before.

I'll probably write some intro to NOSTR next time around; but in the meantime Gigi will help you out at nostr-resources.com

3. Why including the offline skills and tools? * Humans are not meant to stare into screens all day. * I see there's one of the most competitive edges for the next 10 years.

And, that's about it. I'm really excited about days and weeks, and will have some fun. If you have read all down here, thank you and PV to you!

PS.

---

Resources/Inspiration for this issue: * Marty's Bent - duh! * BloggingBitcoin - How To Start A Blog Today

@ aa55a479:f7598935

Nostrica is the shit.

@ 634bd19e:2247da9b

かけるのこれ？ 日本語入力の取り扱いイベントがおかしいw