@ 46fcbe30:6bd8ce4d

Opinion about Samourai Wallet (android)

Samourai has cost me many many hours due to their strong social media presence and constant ad hominem attacks. They blamed me for not being able to compile or reproduce their product instead of helping me to compile it. Given I compile wallets all the time as can be found on walletscrutiny, I doubt I lack the expertise to compile wallets but even if I did, why not show me? Not one developer other than their team themselves disagreed with my technical assessments of their product. Apart from proven scams, this is the product I trust least in the whole space.

But it's not only me. To quote Bitcoin Core developer and absolute genius Gregory Maxwell:

I have seen far too much outright dishonest and extremely incompetent behaviour from Samourai to ever trust it myself. Samourai has very poor privacy while bragging about having good privacy: It sends your addresses all back to their server. Their "trusted node" mode doesn't change this, it just exposes your Bitcoin node to attacks completely needlessly. (Needlessly because they only use it to relay transactions, which they could do via the public P2P ports of any node, and because since they've already sent your addresses back to their server sending your transactions via something else doesn't increase your privacy.) If you want strong privacy then as a start you need to run a full node (and use either Bitcoin Core wallet, or run your own electrum server), preferably via tor. I don't doubt that they want and intend to eventually have good privacy but it seems that they're just unable to stop lying about it, even after previously being caught.

You can find many more very competent people complaining about Samourai's dishonesity and aggressive behavior or outright incompetence if not malice here, here, here, and here. And yes, those links are to nopara, who is the founder of Wasabi wallet which targets the same audience of privacy focused users but that doesn't take away from the facts reported there.

Stay away from Scamourai!

WalletScrutiny #nostrOpinion

Join the conversation!

@ 20e17dd0:2ae504d7

In this article, we will learn how to create a bootable stick with only the commande line.

This is extremely useful for when you need to flash an image on a Stick.

This exemple will creat a bootable stick with the newest version of Ubuntu. I will be using this sitck in another article when I will upgrade my current laptop.

Prerequisite

• ubuntu-22.04.3-live-server-amd64.iso
• Any version of Linux
• USB Key

Let's Go!

The first step is to see what is the correct path of the USB Key. In order to do so, type the following commande without the USB Key

ls -1 /dev/sd?

I get this

/dev/sda /dev/sdb

Afer, insert the USB Key and repeat

ls -1 /dev/sd? I then get this

/dev/sda /dev/sdb /dev/sdc

The USB Key path is clearly /dev/sdc

Now, all you need to put is a one liner command:

sudo dd bs=4M if=/path/to/file.iso of=/dev/sdc status=progress oflag=sync

Here /path/to/file.iso is simply the path to your file and /dev/sdc is the path to your USB that we have earlier determined.

To make things easier, I often go into the folder in which I have the ISO. cd Downloads/Ubuntu

After, I am able to only write the image name

sudo dd bs=4M if=ubuntu-22.04.3-live-server-amd64.iso of=/dev/sdc status=progress oflag=sync

Et voila! No need for a special software! You can now create any bootable stick!

@ 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.

@ 947c8c3e:22e2d6ea

Welcome to the future of social networking—where your voice is uncensored, your identity is secure, and your connections are limitless. This tutorial will introduce you to Nostr, a groundbreaking protocol that promises to revolutionize how we interact online. By the end of this guide, you'll understand what Nostr is, how it works, and how you can start using it today.

What is Nostr?

Nostr stands for "Notes and Other Stuff Transmitted by Relays." It is a simple, open protocol designed to enable a global, decentralized, and censorship-resistant social network. Unlike traditional social media platforms, Nostr doesn't rely on centralized servers. Instead, it operates through a network of relays and clients, ensuring that your data remains in your control.

Key Features:

• Decentralization: No single entity controls the network, making it resilient against censorship and shutdowns.
• Simplicity: The protocol uses simple JSON objects for data and standard cryptographic methods for security.
• Openness: Nostr is an open standard, allowing anyone to build applications or services on top of it.

Getting Started with Nostr

Step 1: Understanding Keys

Every Nostr user has a pair of cryptographic keys: a public key and a private key. Think of your public key as your username and your private key as your password. However, your private key is irreplaceable—if lost, you cannot reset it.

• Public Key: Identifies you on the network (npub1...).
• Private Key: Secures your identity and data (nsec1...). Keep it secret! Keep it safe!

Step 2: Choosing a Client

To interact with Nostr, you'll need a client—a software application that connects to the Nostr network. Clients are available for web, desktop, iOS, and Android. Some recommended clients include: - Damus (iOS): The first Nostr client banned in China for its commitment to free speech. - Nostter (Web): A simple and popular choice for web users. - Amethyst (Android): Offers a comprehensive set of features.

Step 3: Connecting to Relays

Relays serve as the backbone of Nostr, storing and broadcasting messages across the network. When setting up your client, you'll choose relays to connect to. You can find a list of public relays on nostr.watch.

Step 4: Signing Events

Your activities on Nostr—whether posting a message or replying to someone—are called events. Each event is signed with your private key to verify its authenticity. For web clients, consider using a browser extension like nos2x or Alby to securely manage your keys.

Step 5: Finding Friends and Engaging

Start by following interesting profiles or importing contacts from other social networks where applicable. Engage with the community by posting messages, sharing insights, and participating in discussions.

Contributing to Nostr

The beauty of Nostr lies in its community-driven nature. Here are ways you can contribute: - Develop and Improve Clients: Enhance user experience or create new clients with unique features. - Run a Relay: Support the network's infrastructure by hosting your own relay. - Participate in the Community: Use Nostr, provide feedback, and share your experiences. - Contribute to Bounties: search for #bounty on Nostr for tasks that need help, ranging from development to community support. You could earn some Bitcoin by contributing!

Conclusion

Nostr is more than just a protocol; it's a movement towards a more open, secure, and user-driven internet. By joining Nostr, you're not only gaining access to a censorship-resistant network but also contributing to the future of digital communication. One online Identity for any Nostr capable website. Start exploring Nostr today and become part of a community that values freedom, privacy, and connection.

---

Remember, as Nostr evolves, so will its ecosystem of clients, relays, and community contributions. Stay engaged, and welcome to the decentralized web!

What to Earn the Badge?

Nostr Initiate Badge

As a bonus, if you successfully pass our optional quiz, you'll earn a special badge for your Nostr profile, showcasing your expertise and support for innovative communication technologies. It's a cool way to celebrate your understanding and contribution to the community.

Click here to take the quiz

@ 044b20cf:89e58620

Apple officially allows retro game emulators on the App Store

In addition to updating its developer guidelines to allow music streaming apps (https://www.engadget.com/ios-music-apps-in-the-eu-can-now-send-users-to-external-websites-for-purchase-111511085.html?fsig=mN.m4xTnunXxBYYqiyKN.Q--%7EA) to link to external website, Apple has also added new language that allows game emulators on the App Store. The updated guidelines (https://shopping.yahoo.com/rdlw?siteId=us-engadget&pageId=1p-autolink&featureId=text-link&custData=eyJzb3VyY2VOYW1lIjoiV2ViLURlc2t0b3AtVmVyaXpvbiIsImxhbmRpbmdVcmwiOiJodHRwczovL2RldmVsb3Blci5hcHBsZS5jb20vYXBwLXN0b3JlL3Jldmlldy9ndWlkZWxpbmVzLyIsImNvbnRlbnRVdWlkIjoiNWM3OTYyNjQtNjcwOS00YmMyLTllOTMtYWMzMmUwODE1Zjk4In0&signature=AQAAAXLqysX_SgHGrC4kKlcMxD9RY7VtLKyhrMTksTpV_43V&gcReferrer=https%3A%2F%2Fdeveloper.apple.com%2Fapp-store%2Freview%2Fguidelines%2F), first noticed by _9to5Mac (https://9to5mac.com/2024/04/05/app-store-guidelines-music-apps-game-emulators/), now say that retro gaming console emulator apps are welcome and can even offer downloadable games. Apple also reportedly confirmed to developers in an email that they can create and offer emulators on its marketplace.

Emulator software wasn't allowed on the App Store prior to this update, though developers have been finding ways to distribute them to iOS users. To be able to install them, users usually need to resort to jailbreaking and downloading sideloading tools or unsanctioned alternate app stores first. This rule update potentially eliminates the need for users to go through all those lengths and could bring more Android emulators to iOS.

Apple warns developers, however, that they "are responsible for all such software offered in [their] app, including ensuring that such software complies with these Guidelines and all applicable laws." Clearly, allowing emulators on the App Store doesn't mean that it's allowing pirated games, as well. Any app offering titles for download that the developer doesn't own the rights to is a no-no, so fans of specific consoles will just have to hope that their companies are planning to release official emulators for iOS. While these latest changes to Apple's developer guidelines seem to be motivated by the EU's Digital Markets Act regulation, which targets big tech companies' anti-competitive practices, the new rule on emulators applies to all developers worldwide.

This article originally appeared on Engadget at https://www.engadget.com/apple-officially-allows-retro-game-emulators-on-the-app-store-130044937.html?src=rss

https://www.engadget.com/apple-officially-allows-retro-game-emulators-on-the-app-store-130044937.html?src=rss

@ 473231ff:b499379a

Hi there!

I'm sharing with the international community a Lottery game we already had for the Spanish community for the Xmas Lottery. I'm the main coordinator of the Lottery which is been made trough a BTCPayServer and i would like to invite everyone around the world to participate so we can have an international Lottery game without borders thanks to Lightning Network so fell free to share the lottery and invite everyone you want!:

➤ Here you can read all the terms and conditions (https://hyper.media/d/b87NDGwSSnd7LHPJSW4YhU?b=a/z6MktrjxjkogjpGyGwuNKamUTTn8vBVKp7xLBjfVVWZSzMYg) ➤ SHOP: https://pagos.dinerosinreglas.com/apps/27MnRbHxi8PQKQMRe4ciQDsAVvKJ/pos

RULES:

There will be 1,000 unique entries from 000 to 999: each number is priced at 3,000 satoshis on the Lightning Network and prizes will be paid through the Lightning Network.

Each user can purchase any amount of numbers they wish and win the prizes corresponding to each number:

100% of the payments will go towards prizes as follows:

• 50% of the jackpot to be distributed to ONE 3-figure winner

• 50% of the jackpot, to be distributed among the winners of the last 2 figures (this could vary from 2 to 9 winners)

The winning number will be defined by the number of transactions included in BLOCK 840,000 corresponding to the first block with a halving of the mined block reward (known as a halving that occurs every 210,000 blocks, estimated between April 18-20th).

PS: to clear things in advance, I would love to automatize the payment of the prizes and that all this could be a completelly no trust service so nobody should trust on me to get the prizes but i don't know how to do this yet. On the other hand, I have a reputation on the Spanish community and I'm an active member in conferences and meetups so I've also put som skin in the game so people can trust the prizes will be given away in complete anonymity and that i won't get any benefit apart than the tips given while shopping the numbers. (As i said, Xmas lottery was the same format with almost 500 numbers sold and almost 3.000.000 satoshis given away in prizes). Any feedback is also welcome.

@ 0dde8796:14799cec

News Of The Week

Welcome to this week’s issue of the Books And Articles newsletter. Thanks again for all of the quality posts. This week I posted the Book Reviews Directory 11/23-3/24. You can find all of the book reviews that have been posted to this territory prior to March 31, 2024. I anticipate that SN will soon permit perpetual edits, so at that point I will keep that post updated with new reviews. I will also categorize the directory by genres as it grows.

Due to the sheer number of quality posts this week, I am sure I missed placing a few original content posts into the index sections of the newsletter. I simply ran out of time. I promise to try my best to catch up this week.

Thanks again to everyone for helping this territory grow into what we want it to be.

I hope everyone has a good week.

Top Five Posts Of The Week

The top post of the week will be forwarded 50% of the zaps earned on this week’s newsletter post. Rankings will be determined using the SN zaprank.

Here are this week’s top posts:

• “Fear Of A Black Flag” Alan Moore’s 2010 Essay On Anarchy by @StillStackinAfterAllTheseYears

• Discussing my writing process: Focus and feelings by @plebpoet

• Discuss this Quote- Miguel de Cervantes by @grayruby

• The Opposite Of A Good Idea by @kr

• What Is The Greatest Work Of Art You Have Stood In Front Of? by @CoffeeWithTheClassics

Siggy’s Suggestions

• From Shells To Satoshi: The Story Of Money by @Roll

This is a link post from @Roll announcing the release of a new bitcoin book. Like most here, a new bitcoin book always piques my interest. I hope someone does a book review soon so we can learn more about it.

• Blood Money: Meet the Top 20 Companies Profiting From Endless War by @DarthCoin

I found this article both informative and sad. I wasn’t aware of a few of the companies listed here. I am very aware of another. My wife’s family has a long tradition of working for one of these companies. It has put food on the table for three generations while building technological marvels and weapons of war.

Releasing Chronicles of the Code Guardians - A Bitcoin journey by @eddieoz

The author announced the publication of his latest book, a science fiction work about bitcoin. I am not much of a science fiction guy myself, but I know there are plenty of stackers here with the chops to give this book a look and post a review. I look forward to reading more about its post publication progress. Welcome, @eddieoz, to SN and to our territory!

• What book format do you prefer to read? by @Taft

This post was timely for me, since I was questioning the usefulness of poll posts recently. @Taft showed us here that they can be useful and engaging- 29 votes and 14 comments on an important topic.

Writing Contests

• Writing Contest #1

• Writing Contest #2

Stackers’ Blogs

• Fighting The Daily Grind by @cryotosensei

• Personal Blog, Got My First Job by @CyberCrypto

My Bitcoin Journey

Inspired by Writing Contest #1, this is where stacker’s bitcoin origin stories will be posted for easy reference.

• Grayruby’s Bitcoin story by @grayruby

• I Put ¼ Of A Bitcoin In A Landfill by @brandonsbytes

Book Clubs

• Stoic Book Club:Meditations by @Se7enZ

Books

• The Universal Good Deal by @cleophas

• Who Brought The Steak Tartare?, Chapter 1 by @cleophas

• Happy The Hippo, an absolutely wonderful children’s book written by @cryotosensei for his son.

• The Rogue Scholar by @jbschirtzinger

• Submersible by @johnbnevin

Book Reviews

• Some Thoughts On Re-Reading Bradbury’s “Fahrenheit 451” by @StillStackinAfterAllTheseYears

• The Last Policeman, by Ben H. Winters by @StillStackinAfterAllTheseYears

• Author Recommendation- Andrew Heaton by @Undisciplined

• The Things We Leave Unfinished, by Rebecca Yarros by @Tef

• Book Reviews Directory 11/23-3/24

Essays

Nihilism Wants Empire:Camus On Nietzsche by @jurraca

Poetry

• Poetry:unresolved between a thai lad and I by @cryotosensei

• plebpoet’s original poem + discussion by @plebpoet

• Churning Black Matter by @Nuttall

• If A Day Comes... by @Tef

Short Stories

• Neo’s Adventure In The Digital Realm: Discovering The Treasure Of Bitcoin by @VEINTIUNO

@ 044b20cf:89e58620

iOS music apps in the EU can now send users to external websites for purchase

Apple will make it easier for you to pay for music purchases and subscriptions outside of its payment system, if you're living in a European Union country. As first noticed by 9to5Mac (https://9to5mac.com/2024/04/05/app-store-guidelines-music-apps-game-emulators/), the company has updated its Apple Developer guidelines page (https://shopping.yahoo.com/rdlw?siteId=us-engadget&pageId=1p-autolink&featureId=text-link&custData=eyJzb3VyY2VOYW1lIjoiV2ViLURlc2t0b3AtVmVyaXpvbiIsImxhbmRpbmdVcmwiOiJodHRwczovL2RldmVsb3Blci5hcHBsZS5jb20vYXBwLXN0b3JlL3Jldmlldy9ndWlkZWxpbmVzLyIsImNvbnRlbnRVdWlkIjoiODljYjEzZmUtYzM5ZC00NDg0LWIzNjMtODVlY2RjNDk5OGM0In0&signature=AQAAAS-FI-CrV3lhLLaQIT2-rjH1KZrLCSeHpi2y6B-Hy4Qu&gcReferrer=https%3A%2F%2Fdeveloper.apple.com%2Fapp-store%2Freview%2Fguidelines%2F) to state that iOS and iPadOS music streaming apps "in specific regions" can now include a link to an external website where you can find alternative ways to pay for content and services. Developers can also ask you to provide your email address, so they could send you a link to that website.

In early March, the European Union slapped Apple with a €1.8 billion ($1.95 billion) fine (https://www.engadget.com/eu-fines-apple-nearly-2-billion-for-blocking-alternative-music-apps-134001372.html?_fsig=bQGKZXCo7hvtfpKV0PMQdA--%7EA) for preventing music streaming app developers from informing iOS users "about alternative and cheaper music subscription services available outside of the app and from providing any instructions about how to subscribe to such offers." This anti-steering practice, the European Commission said, is illegal under the bloc's new Digital Markets Act (DMA) rules, which became applicable in May 2023.

By the end of March, EU officials revealed that they were investigating (https://www.engadget.com/the-eu-is-investigating-apple-meta-and-google-over-fees-and-self-preferencing-124147179.html) Apple, Meta and Google over their compliance with the DMA. The commission wasn't happy with the changes the companies made in order to adhere to the law, and it was concerned that they were still constraining "developers' ability to freely communicate and promote offers and directly conclude contracts, including by imposing various charges."

With these recent changes, music apps can be more transparent about their pricing, so you can make an informed choice on whether to pay via Apple or use the other methods offered by the developers.

This article originally appeared on Engadget at https://www.engadget.com/ios-music-apps-in-the-eu-can-now-send-users-to-external-websites-for-purchase-111511085.html?src=rss

https://www.engadget.com/ios-music-apps-in-the-eu-can-now-send-users-to-external-websites-for-purchase-111511085.html?src=rss

@ 044b20cf:89e58620

Tesla will unveil a robotaxi on August 8, according to Musk

Tesla is introducing a robotaxi on August 8, Elon Musk has announced (https://twitter.com/elonmusk/status/1776351450542768368) on X a few hours after Reuters published a report that the automaker is scrapping its plans (https://www.engadget.com/tesla-is-reportedly-focusing-on-robotaxis-over-its-planned-budget-ev-190833687.html) to produce a low-cost EV. Reuters also said that Musk's directive was to "go all in" on robotaxis built on the company's small-vehicle platform. Tesla has been promising a more affordable EV with prices expected to start at $25,000 for years (https://www.engadget.com/2018-08-18-elon-musk-talks-25k-tesla.html?_fsig=SypsOlWc1PTRFEsV6quZow--%7EA), and Musk said as recently as this January that he's optimistic the model will arrive in the second half of 2025 (https://www.engadget.com/elon-musk-confirms-a-new-low-cost-tesla-model-is-coming-in-2025-103517158.html). In response to the report, the Tesla chief tweeted (https://twitter.com/elonmusk/status/1776272471324606778) that "Reuters is lying (again)."

He didn't clarify which part of the report was a lie, but considering he confirmed that Tesla is unveiling a robotaxi, he likely meant the news organization's claim that the company pulled the plug on a more affordable EV. At the moment, Tesla's cheapest vehicle is the Model 3, but its prices start at $39,000. It'll be interesting to see how the company will make a robotaxi work with its camera-only system — it dropped (https://www.engadget.com/tesla-losing-ultrasonic-sensors-camera-only-system-131503260.html?_fsig=C9GIyY3Y6hKDJwrC0.mT6Q--%7EA) radar and other sensors, which robotaxi companies like Waymo use extensively, from its driver assistance technologies a few years ago.

Tesla Robotaxi unveil on 8/8

— Elon Musk (@elonmusk) April 5, 2024 (https://twitter.com/elonmusk/status/1776351450542768368?ref_src=twsrc%5Etfw)

This article originally appeared on Engadget at https://www.engadget.com/tesla-will-unveil-a-robotaxi-on-april-8-according-to-musk-013853363.html?src=rss

https://www.engadget.com/tesla-will-unveil-a-robotaxi-on-april-8-according-to-musk-013853363.html?src=rss

@ 45057918:92db0561

🙂 NAND คืออะไร NAND คือแฟลชเมมโมรี่แบบไม่เลือนหายซึ่งสามารถเก็บรักษาข้อมูลได้แม้ว่าจะไม่ได้ต่ออยู่กับแหล่งจ่ายไฟ ความสามารถในการเก็บรักษาข้อมูลเมื่อตัดกระแสไฟฟ้าทำให้ NAND เป็นทางเลือกที่ดีอย่างยิ่งสำหรับใช้กับอุปกรณ์จัดเก็บข้อมูลติดตั้งภายใน ต่อพ่วง หรือแบบพกพา ไดรฟ์ USB, SSD และการ์ด SD ล้วนใช้เทคโนโลยีแฟลช โดยถือเป็นหน่วยความจำสำหรับอุปกรณ์ต่าง ๆ เช่น โทรศัพท์มือถือและกล้องดิจิตอลของคุณ . 😗 มี NAND ที่จำหน่ายในตลาดอยู่หลายประเภท ในเบื้องต้น ข้อแตกต่างที่สำคัญคือจำนวนบิตที่สามารถจัดเก็บต่อเซลล์ บิตคือประจุไฟฟ้าที่สามารถรองรับค่าได้สองค่าคือ 0 หรือ 1 หรือ เปิด/ปิด

. 🙂 ข้อแตกต่างที่สำคัญระหว่าง NAND แต่ละประเภทคือราคา ความจุ และความทนทาน ความทนทานจะพิจารณาจากจำนวนรอบการเขียนโปรแกรม-ลบข้อมูล (P/E) ที่เซลล์แฟลชรองรับก่อนจะเริ่มเสื่อมสภาพ รอบ P/E คือกระบวนการลบและเขียนข้อมูลไปที่เซลล์ สำหรับเทคโนโลยี NAND แล้ว หากมีรอบ P/E มากกว่า อุปกรณ์ก็ย่อมทนทานมากกว่า

. 😗 สื่อบันทึกข้อมูลแฟลช NAND ที่พบได้ทั่วไปได้แก่ SLC, MLC, TLC และ 3D NAND บทความนี้จะกล่าวถึงความแตกต่างของ NAND แต่ละประเภท . 📀📀 SLC NAND 👍 ข้อดี: ทนทานมากที่สุด - ข้อเสีย: ราคาแพงและความจุต่ำ NAND แบบ Single-Level Cell (SLC) จะจัดเก็บข้อมูลเพียง 1 บิตต่อเซลล์ เซลล์จะจัดเก็บข้อมูลเป็น 0 หรือ 1 เพื่อให้สามารถเขียนและเรียกค้นข้อมูลได้อย่างรวดเร็ว SLC มีประสิทธิภาพมากที่สุด และทนทานมากที่สุด โดยมีรอบ P/E สูงถึง 100,000 รอบ ทำให้ใช้งานได้ยาวนานกว่า NAND ประเภทอื่น อย่างไรก็ตาม ความหนาแน่นของข้อมูลที่ต่ำทำให้ SLC เป็น NAND ที่มีต้นทุนสูงที่สุด จึงมักไม่ใช้ในผลิตภัณฑ์ใช้งานทั่วไป ปกติจะใช้กับเซิร์ฟเวอร์และส่วนการใช้งานทางอุตสาหกรรมที่ต้องการความเร็วและความทนทานเป็นพิเศษ

. 💿💿 MLC NAND 👍 ข้อดี: ราคาถูกกว่า SLC - ข้อเสีย: ช้ากว่าและทนทานน้อยกว่า SLC NAND แบบ Multi-level cell (MLC) สามารถจัดเก็บข้อมูลได้หลายบิตต่อเซลล์ แม้ว่าอักษรย่อ MLC จะมักหมายถึงข้อมูล 2 บิตต่อเซลล์ก็ตาม MLC มีความหนาแน่นของข้อมูลที่สูงกว่า SLC ทำให้มีการผลิตที่ความจุสูงกว่า MLC มีข้อดีทั้งในด้านราคา ประสิทธิภาพ และความทนทาน อย่างไรก็ตาม MLC มักเกิดข้อผิดพลาดกับข้อมูลมากกว่าและรองรับรอบ P/E ที่ 10,000 รอบ ทำให้มีความทนทานน้อยกว่าเมื่อเทียบกับ SLC MLC มักใช้กับผลิตภัณฑ์ใช้งานทั่วไปที่ความทนทานอาจไม่ใช่ประเด็นสำคัญ

. 💾💾 TLC NAND 👍 ข้อดี: ราคาถูกที่สุดและความจุมากที่สุด - ข้อเสีย: ความทนทานต่ำ NAND แบบ Triple-level cell (TLC) สามารถจัดเก็บข้อมูลได้ 3 บิตต่อเซลล์ จำนวนบิตต่อเซลล์ที่เพิ่มขึ้นจะช่วยลดต้นทุนและทำให้รองรับความจุได้มากกว่าเดิม แต่ก็จะมีผลต่อประสิทธิภาพและความทนทาน โดยจะรองรับ P/E เพียง 3,000 รอบเท่านั้น ผลิตภัณฑ์ใช้งานทั่วไปส่วนใหญ่จะใช้ TLC ซึ่งเป็นทางเลือกที่ราคาประหยัดที่สุด . 💽💽 3D NAND ในช่วงไม่ถึงสิบปีที่ผ่านมา 3D NAND ได้กลายเป็นนวัตกรรมใหม่ที่สำคัญอย่างยิ่งในตลาดแฟลช ผู้ผลิตแฟลชได้พัฒนา 3D NAND ขึ้นเพื่อแก้ไขปัญหาที่พบกับ 2D NAND เพื่อให้รองรับความจุได้มากขึ้นโดยมีต้นทุนลดลง ใน 2D NAND เซลล์ที่จัดเก็บข้อมูลจะถูกจัดวางในแนวนอนเรียงต่อกัน ซึ่งหมายถึงพื้นที่ที่สามารถจัดวางเซลล์จะมีอยู่อย่างจำกัด และการทำให้เซลล์เล็กลงก็จะยิ่งมีผลต่อเสถียรภาพในการทำงาน

. ดังนั้นผู้ผลิต NAND จึงตัดสินใจวางซ้อนเซลล์ในรูปแบบใหม่ ทำให้เกิด 3D NAND ขึ้นโดยมีการจัดเรียงเซลล์ในแนวตั้ง ความหนาแน่นของหน่วยความจำที่มากกว่าทำให้รองรับพื้นที่จัดเก็บข้อมูลได้มากขึ้นโดยไม่เพิ่มภาระต้นทุน 3D NAND ยังมีความทนทานที่เหนือกว่าและใช้พลังงานน้อยกว่า

. โดยรวมแล้ว NAND เป็นเทคโนโลยีหน่วยความจำที่สำคัญอย่างยิ่ง เนื่องจากจะทำให้สามารถลบและเขียนข้อมูลได้อย่างรวดเร็วและมีต้นทุนต่อบิตที่ต่ำกว่า การเติบโตของอุตสาหกรรมเกมทำให้เทคโนโลยี NAND มีการพัฒนาอย่างต่อเนื่องเพื่อตอบสนองความต้องการด้านการจัดเก็บข้อมูลที่มากขึ้นเรื่อย ๆ ของผู้บริโภค . . สรุปแบบเข้าใจง่ายๆ ประเภทของ NAND แบ่งออกได้ : 📀 SLC (Single-Level Cell): เก็บข้อมูล 1 บิตต่อเซลล์ มีความเร็วสูง ทนทานสูง ราคาแพง เหมาะกับงานที่ต้องการความเร็วและความเสถียร 💿 MLC (Multi-Level Cell): เก็บข้อมูล 2 บิตต่อเซลล์ ความเร็วปานกลาง ทนทานปานกลาง ราคาปานกลาง เหมาะกับงานทั่วไป 💾 TLC (Triple-Level Cell): เก็บข้อมูล 3 บิตต่อเซลล์ ความเร็วช้า ทนทานต่ำ ราคาถูก เหมาะกับงานที่ต้องการพื้นที่เก็บข้อมูลขนาดใหญ่ 💽 3D NAND: เทคโนโลยีใหม่ที่เพิ่มชั้นของ NAND flash memory ช่วยให้เพิ่มความจุและลดต้นทุน . แหล่งที่มา : www.kingston.com/th/blog/pc-performance/difference-between-slc-mlc-tlc-3d-nandkingston

@ 18e3af1e:1d42e5df

Bid starts at 51K sats. Doesn't include shipping, US Only, comes in frame.

nostr #bitcoin #market #plebchain #plebmarket #agora

@ 044b20cf:89e58620

Meta asks a judge to throw out an FTC antitrust case

Meta (https://www.engadget.com/tag/meta/) has asked a judge (https://about.fb.com/news/2024/04/meta-files-motion-for-summary-judgment-in-ftc-lawsuit-relating-to-instagram-and-whatsapp/) to dismiss a Federal Trade Commission (https://www.engadget.com/tag/ftc/) antitrust case against the company before it goes to trial. Alongside 48 states and territories, the FTC sued Meta in 2020 (https://www.engadget.com/facebook-antitrust-ftc-48-states-194858668.html) in an attempt to force the company to divest Instagram and WhatsApp, which it bought in 2012 and 2014, respectively.

The agency and dozens of attorneys general claim that Meta (then known as Facebook) bought the two platforms to stifle competition. Meta CEO Mark Zuckerberg “recognized that by acquiring and controlling Instagram, Facebook would not only squelch the direct threat that Instagram posed, but also significantly hinder another firm from using photo-sharing on mobile phones to gain popularity as a provider of personal social networking,” the FTC asserted. “Just as with Instagram, WhatsApp presented a powerful threat to Facebook’s personal social networking monopoly, which Facebook targeted for acquisition rather than competition.”

Meta notes that not only did the FTC approve both acquisitions in the first place, but its initial complaint was dismissed for failing to to state a plausible claim. While a judge has allowed an amended complaint to move forward, Meta claims that "the agency has done nothing to build its case through the discovery process" to show that the company holds monopoly power in the “personal social networking services” market and that it caused harm to consumers and competition through the purchases.

In its motion for summary judgment, the company points out that Instagram, which accounted for nearly 30 percent of the company's total revenue in the first half of 2022 (https://www.bloomberg.com/news/articles/2024-04-05/instagram-generated-almost-30-of-meta-s-revenue-in-early-2022?sref=10lNAhZ9), wasn't making any money when it bought the service for $1 billion in 2012. Instagram had just two percent of the billion-plus users it has now, Meta says, adding that it introduced features such as direct messages, livestreaming, Stories and shopping. As for WhatsApp, Meta made the service free to use, added end-to-end encryption and implemented voice and video calling.

Meta argues that it has invested billions of dollars and millions of hours of work into the apps. It claims that both Instagram and WhatsApp are in a better place as a result, to the benefit of consumers and businesses.

Elsewhere, Meta argues that the FTC failed to establish a relevant antitrust market, claiming that the agency's definition of an “personal social networking services” market used "an artificially limited set of only four companies – Facebook, Instagram, Snapchat and MeWe – ignoring many of the most popular activities people engage in on Facebook and Instagram." For instance, Meta points out that YouTube and TikTok offer similar short-form video features (https://www.engadget.com/youtube-shorts-now-lets-you-chop-up-and-remix-music-videos-180655627.html) to Reels.

What's more, the FTC's allegation that Meta has a “dominant share” of the artificial “personal social networking services market” doesn't hold up, according to the company. Meta says that's because the FTC's "market share numbers are meaningless without a properly defined market."

Meta, which accused the FTC of wielding "structurally unconstitutional authority" against the company in a separate case last year (https://www.engadget.com/meta-sues-ftc-to-block-new-restrictions-on-monetizing-kids-data-185051764.html), also took the opportunity to take more potshots at the agency and antitrust rules. "The decision to revisit done deals is tantamount to announcing that no sale will ever be final," Jennifer Newstead, Meta’s Chief Legal Officer, wrote in a blog post (https://about.fb.com/news/2024/04/meta-files-motion-for-summary-judgment-in-ftc-lawsuit-relating-to-instagram-and-whatsapp/). Newstead claims the Instagram and WhatsApp "lawsuit not only sows doubt and uncertainty about the US government’s merger review process and whether acquiring businesses can actually rely on the outcomes of the regulatory review process, but it will also make companies think twice about investing in innovation, since they may be punished if that innovation leads to success."

This article originally appeared on Engadget at https://www.engadget.com/meta-asks-a-judge-to-throw-out-an-ftc-antitrust-case-203950108.html?src=rss

https://www.engadget.com/meta-asks-a-judge-to-throw-out-an-ftc-antitrust-case-203950108.html?src=rss

@ c4428155:a36de510

Trump’s Lawyers Told the Court That No One Would Give Him a Bond. Then He Got a Lifeline, but They Didn’t Tell the Judges.

by Robert Faturechi (https://www.propublica.org/people/robert-faturechi), Justin Elliott (https://www.propublica.org/people/justin-elliott) and Alex Mierjeski (https://www.propublica.org/people/alex-mierjeski)

ProPublica is a nonprofit newsroom that investigates abuses of power. Sign up to receive our biggest stories (https://www.propublica.org/newsletters/the-big-story?source=54G&placement=top-note®ion=national) as soon as they’re published.

Former President Donald Trump scored a victory last week when a New York court slashed the amount he had to put up while appealing his civil fraud case to $175 million.

His lawyers had told the appellate court it was a “practical impossibility” to get a bond for the full amount of the lower court’s judgment, $464 million. All of the 30 or so firms Trump had approached balked, either refusing to take the risk or not wanting to accept real estate as collateral, they said. That made raising the full amount “an impossible bond requirement.”

But before the judges ruled, the impossible became possible: A billionaire lender approached Trump about providing a bond for the full amount.

The lawyers never filed paperwork alerting the appeals court. That failure may have violated ethics rules, legal experts say.

In an interview with ProPublica, billionaire California financier Don Hankey said he reached out to Trump’s camp several days before the bond was lowered, expressing willingness to offer the full amount and to use real estate as collateral.

“I saw that they were rejected by everyone and I said, ‘Gee, that doesn’t seem like a difficult bond to post,’” Hankey said.

As negotiations between Hankey and Trump’s representatives were underway, the appellate court ruled in Trump’s favor, lowering the bond to $175 million. The court did not give an explanation for its ruling.

Hankey ended up giving Trump a bond for the lowered amount.

It’s unclear if Trump lawyer Alina Habba or the rest of his legal team were made aware that Hankey reached out about a deal for the full amount. Trump’s legal team did not respond to requests for comment.

After ProPublica reached out to Trump’s representatives, Hankey called back and revised his account. He said he had heard “indirectly” about ProPublica’s subsequent inquiries to Trump’s lawyers. In the second conversation, he said that accepting the real estate as collateral would have been complicated and that he wouldn’t have been able to “commit” to providing a bond in the full amount “until I evaluate the assets.”

Legal ethics experts said it would be troubling if Trump’s lawyers knew about Hankey’s approach and failed to notify the court.

New York state’s rules of professional conduct for lawyers forbid attorneys from knowingly making false statements to a court. At the time Trump’s lawyers told the court that meeting the bond would be impossible, Hankey said he had not yet reached out to the Trump team.

But the rules of conduct (https://www.documentcloud.org/documents/24533237-20240226-rules-of-professional-conduct-as-amended-6102022#document/p113) also dictate that lawyers must “correct a false statement of material fact or law previously made” to the court.

“If that deal was on the table for the taking, the representation from the earlier time would be untrue, and the lawyer would have an obligation to correct,” said Stephen Gillers, a legal ethics professor at New York University Law School.

In the rules of conduct for lawyers, the failure to update an important piece of evidence would fall under what’s referred to as the “duty of candor to a tribunal,” said Ellen Yaroshefsky, a professor of legal ethics at Hofstra Law.

“Any judge is going to be furious that this wasn’t corrected,” she said.

Scott Cummings, a legal ethics professor at UCLA’s law school, agreed that there was a potential ethical failure but said Trump’s lawyers could argue that they were not obligated to alert the court.

“A very narrow reading of this rule would be there is no obligation to report because it wasn’t a false statement at the time,” Cummings said.

The need for the bond arose from a case brought against Trump by the New York attorney general, who accused him of fraudulently inflating his net worth to get favorable loans and other benefits. A judge agreed and ordered Trump and the other defendants to pay $464 million.

Trump had a month to come up with the sum or risked having his properties seized.

When a defendant loses a civil case in New York, the creditor — in this case the attorney general — can immediately go after the defendant’s assets to collect the judgment. The defendant can protect his assets while pursuing an appeal by posting a bond. Typically obtained from an insurance company for a fee, the bond is essentially a promise that the company will guarantee payment of the judgment if the appeal fails.

In his first interview with ProPublica, Hankey said that when he heard Trump was having trouble getting a bond, he reached out to Trump’s camp, several days before the bond was reduced, with an offer to help.

Hankey, who took a break from a game of bocce to speak to ProPublica, is rated by Forbes (https://www.forbes.com/profile/don-hankey/?sh=194acba81783) as one of the 400 wealthiest people in the world with an estimated net worth of more than $7 billion. He made much of his fortune with high-interest car loans to risky borrowers, and he is chairman of a Los Angeles-based network of companies across a range of industries, including real estate, insurance and finance. He has said he supports Trump politically but would have wanted to make the deal no matter his politics.

Hankey told ProPublica that during the talks he came to the conclusion that Trump’s “got the liquidity” and was confused why others would have rejected him, speculating that some may have wanted to avoid political backlash: “If you’re a public company, maybe you don’t want to offend 45% of the population.”

Hankey said he informed Trump’s camp that he was willing to work with them, and “they said they had the collateral.” The two sides went over the assets that had to be pledged, and it was up to Trump “if they wanted to do it.” (In his second call, Hankey said making a deal would have been “difficult.”)

But, he said, the deal for the larger amount was dropped during a large Zoom call between the two sides, when Trump’s camp got a call informing them that the bond was reduced.

“They thanked us for trying to help: ‘Maybe next year, we’ll try to do business again,’” Hankey recalled them saying.

But several days later, Hankey said, they called back, hoping to make a deal for the reduced bond, and Hankey agreed.

The bond saga is not over. In a brief court filing on Thursday, the New York attorney general asked (https://www.nytimes.com/2024/04/04/nyregion/letitia-james-trump-bond-deal.html) Trump or Hankey’s company to show that the company has the financial means to fulfill the $175 million bond.

Do you have any information about this case that we should know? Robert Faturechi can be reached by email at robert.faturechi@propublica.org (mailto:robert.faturechi@propublica.org) and by Signal or WhatsApp at 213-271-7217. Justin Elliott can be reached by email at justin@propublica.org (mailto:justin@propublica.org) or by Signal or WhatsApp at 774-826-6240.

https://www.propublica.org/article/trump-bond-disclosure-appeals-court-hankey

@ 044b20cf:89e58620

Tesla is reportedly focusing on robotaxis over its planned budget EV

Tesla has scrapped plans to make an affordable electric vehicle (EV), according to (https://www.reuters.com/business/autos-transportation/tesla-scraps-low-cost-car-plans-amid-fierce-chinese-ev-competition-2024-04-05/) Reuters. CEO Elon Musk said as recently as January that he was “optimistic” the low-cost EV would arrive in the second half of 2025 (https://www.engadget.com/elon-musk-confirms-a-new-low-cost-tesla-model-is-coming-in-2025-103517158.html). The automaker will instead reportedly “go all in” on robotaxis (https://www.engadget.com/2023-was-the-year-cruises-robotaxi-dream-came-to-a-crashing-end-153002522.html), which Musk has described as the future of transportation.

The canceled entry-level EV project — often called “Model 2” — was reportedly codenamed “Redwood.” The automaker had predicted a weekly production volume of 10,000 vehicles (https://www.engadget.com/tesla-is-reportedly-building-a-compact-crossover-codenamed-redwood-103223757.html), and Musk said, “We’ll be sleeping on the line” to make it a reality. He had previously claimed Tesla was working on two new EV models expected to sell up to five million units annually.

For nearly two decades, the CEO has described his long-term goal as using luxury vehicles to build Tesla’s brand before using those profits to fund budget models. “When someone buys the Tesla Roadster sports car, they are actually helping pay for development of the low cost family car,” Musk wrote (https://www.tesla.com/blog/secret-tesla-motors-master-plan-just-between-you-and-me) in a 2006 “Secret Tesla Motors Master Plan” memo. In the following years, he often echoed those sentiments to customers and investors.

The cancellation would leave the $39,000 and up Model 3 sedan (https://www.engadget.com/teslas-redesigned-model-3-comes-with-a-new-interior-and-more-range-083832464.html) as Tesla’s cheapest vehicle. The scrapped budget model was expected to start at around $25,000.

Reuters’ sources told the outlet they were told about the cancellation in a late February meeting “attended by scores of employees.” The publication says it reviewed internal Tesla messages about the pivot, including one advising staff to hold off on telling suppliers “about program cancellation.” Other messages allegedly told staffers that “suppliers should halt all further activities related to H422/NV91,” referring to the budget model’s external and internal codenames.

Musk posted (https://twitter.com/elonmusk/status/1776272471324606778) on X (Twitter) on Friday, “ Reuters is lying (again)” in response to the story — without listing any points of contention.

Tesla has its work cut out for it. Not only has EV demand slowed (https://www.engadget.com/hertz-is-selling-20000-evs-and-replacing-them-with-gas-powered-vehicles-153302670.html) in the US, but competition in China is fierce, with the fast-growing BYD (https://www.engadget.com/chinas-emergence-as-an-ev-powerhouse-has-been-a-long-time-coming-145429852.html) leading the country’s entry-level market. The Chinese automaker said (https://electrek.co/2024/04/02/tesla-regains-bev-global-leader-crown-from-byd-amid-tough-quarter/) earlier this month that its sales increased 13 percent year over year. Meanwhile, Tesla said on Tuesday that its deliveries dropped eight percent annually while falling 20 percent from the previous quarter (https://www.engadget.com/tesla-sees-ev-deliveries-drop-year-over-year-for-the-first-time-since-2020-153020454.html).

This article originally appeared on Engadget at https://www.engadget.com/tesla-is-reportedly-focusing-on-robotaxis-over-its-planned-budget-ev-190833687.html?src=rss

https://www.engadget.com/tesla-is-reportedly-focusing-on-robotaxis-over-its-planned-budget-ev-190833687.html?src=rss

@ 000002de:c05780a7

I don't have much concern for the US attempting an outright ban any more. That ship has sailed unless the US gets very disparate. The issue that most concerns me is that there is a slow move away from self custody by bitcoiners.

@ 044b20cf:89e58620

Annual Max subscriptions are still 40 percent off, plus the rest of this week's best tech deals

As another week winds to a close, it's time for Engadget's roundup of the best deals we spotted this week. There's no giant sale happening right now, but we still found a few decent discounts on some of our recommended tech, including 40 percent off a year's subscription to Max's streaming service (https://shopping.yahoo.com/rdlw?merchantId=688578c2-f937-4e4e-ba49-28d7ac8f32c3&siteId=us-engadget&pageId=1p-autolink&featureId=text-link&merchantName=Max&custData=eyJzb3VyY2VOYW1lIjoiV2ViLURlc2t0b3AtVmVyaXpvbiIsImxhbmRpbmdVcmwiOiJodHRwczovL3d3dy5tYXguY29tLyIsImNvbnRlbnRVdWlkIjoiYzI4NTBlZGMtMzljYS00NzQwLWI0MjctZWU4YTUzODQ3YzA3In0&signature=AQAAAUlk_9nZoXZaM5qlp8joof5RZxN1bgODDYBvJL41pFdj&gcReferrer=https%3A%2F%2Fwww.max.com%2F), $130 off our favorite Android tablet (https://shopping.yahoo.com/rdlw?merchantId=66ea567a-c987-4c2e-a2ff-02904efde6ea&siteId=us-engadget&pageId=1p-autolink&featureId=text-link&merchantName=Amazon&custData=eyJzb3VyY2VOYW1lIjoiV2ViLURlc2t0b3AtVmVyaXpvbiIsImxhbmRpbmdVcmwiOiJodHRwczovL3d3dy5hbWF6b24uY29tL1NBTVNVTkctQW5kcm9pZC1TbmFwZHJhZ29uLVByb2Nlc3Nvci1HcmFwaGl0ZS9kcC9CMEM0QkM2Ujk1P3RhZz1nZGd0MGMtcC12LWQyLTIwIiwiY29udGVudFV1aWQiOiJjMjg1MGVkYy0zOWNhLTQ3NDAtYjQyNy1lZThhNTM4NDdjMDcifQ&signature=AQAAASWjdzNkkoqeT4l0D9rw6DmqnMfwQO1HMVAnIucQIr_9&gcReferrer=https%3A%2F%2Fwww.amazon.com%2FSAMSUNG-Android-Snapdragon-Processor-Graphite%2Fdp%2FB0C4BC6R95) and a new low price on ourtop mouse for gaming (https://shopping.yahoo.com/rdlw?merchantId=66ea567a-c987-4c2e-a2ff-02904efde6ea&siteId=us-engadget&pageId=1p-autolink&featureId=text-link&merchantName=Amazon&custData=eyJzb3VyY2VOYW1lIjoiV2ViLURlc2t0b3AtVmVyaXpvbiIsImxhbmRpbmdVcmwiOiJodHRwczovL3d3dy5hbWF6b24uY29tL2RwL0IwOUMxM1BaWDc_dGFnPWdkZ3QwYy1wLXYtZDItMjAiLCJjb250ZW50VXVpZCI6ImMyODUwZWRjLTM5Y2EtNDc0MC1iNDI3LWVlOGE1Mzg0N2MwNyJ9&signature=AQAAAfvdGrZHAOMTayzoFrrfDUyYWA0pTwxwwyZWdjoT7T48&gcReferrer=https%3A%2F%2Fwww.amazon.com%2Fdp%2FB09C13PZX7). If you've been considering a foldable phone but have been (understandably) turned off by the high prices, a both Samsung's Galaxy Z Fold 5 (https://shopping.yahoo.com/rdlw?merchantId=66ea567a-c987-4c2e-a2ff-02904efde6ea&siteId=us-engadget&pageId=1p-autolink&featureId=text-link&merchantName=Amazon&custData=eyJzb3VyY2VOYW1lIjoiV2ViLURlc2t0b3AtVmVyaXpvbiIsImxhbmRpbmdVcmwiOiJodHRwczovL3d3dy5hbWF6b24uY29tL1NBTVNVTkctVW5sb2NrZWQtU21hcnRwaG9uZS1TdHJlYW1pbmctSGFuZHMtRnJlZS9kcC9CMEM2M1QyOTVIP3RhZz1nZGd0MGMtcC12LWQyLTIwIiwiY29udGVudFV1aWQiOiJjMjg1MGVkYy0zOWNhLTQ3NDAtYjQyNy1lZThhNTM4NDdjMDcifQ&signature=AQAAAaL7c9eA5HxCskZX1BXGEHCa5sx5tdMbq-_F_5o5hHxo&gcReferrer=https%3A%2F%2Fwww.amazon.com%2FSAMSUNG-Unlocked-Smartphone-Streaming-Hands-Free%2Fdp%2FB0C63T295H) and Google's Pixel Fold (https://shopping.yahoo.com/rdlw?merchantId=66ea567a-c987-4c2e-a2ff-02904efde6ea&siteId=us-engadget&pageId=1p-autolink&featureId=text-link&merchantName=Amazon&custData=eyJzb3VyY2VOYW1lIjoiV2ViLURlc2t0b3AtVmVyaXpvbiIsImxhbmRpbmdVcmwiOiJodHRwczovL3d3dy5hbWF6b24uY29tL2dwL3Byb2R1Y3QvQjBDMzRETDZaNy9yZWY9ZXdjX3ByX2ltZ18xP3RhZz1nZGd0MGMtcC12LWQyLTIwIiwiY29udGVudFV1aWQiOiJjMjg1MGVkYy0zOWNhLTQ3NDAtYjQyNy1lZThhNTM4NDdjMDcifQ&signature=AQAAAcA8Ou2zPWiyJqUr2ami3HSE5BuB2HS7xSN-Kbz7FfOV&gcReferrer=https%3A%2F%2Fwww.amazon.com%2Fgp%2Fproduct%2FB0C34DL6Z7%2Fref%3Dewc_pr_img_1) are currently on sale and going for $400 and $500 off, respectively. Here are the best tech deals from this week that you can still get today.

Follow__@EngadgetDeals (https://twitter.com/EngadgetDeals) on Twitter and__subscribe to the Engadget Deals newsletter (https://subscription.yahoo.net/Newsletter/Preference/sub?b=engadgetdeals&src) for the latest tech deals and buying advice.

This article originally appeared on Engadget at https://www.engadget.com/annual-max-subscriptions-are-still-40-percent-off-plus-the-rest-of-this-weeks-best-tech-deals-172622166.html?src=rss

https://www.engadget.com/annual-max-subscriptions-are-still-40-percent-off-plus-the-rest-of-this-weeks-best-tech-deals-172622166.html?src=rss

@ c11cf5f8:4928464d

Let's hear some of your latest Bitcoin trades, feel free to include links to your shops or sites you sold it from or the pic of the sold item.

If you missed our last thread, here are some of the items stackers recently spent their sats on the ~AGORA territory.



@ 57d1a264:69f1fee1

The idea of being famous for simply being famous — à la the Kardashians — is no longer a novelty.

The craft of using a viral moment or scandal to one’s advantage and capitalizing on it for fame has become a form of art.

But this phenomenon is far from a social media age development.

One of the most successful examples of an entity leveraging virality for longstanding fame occurred over a century ago.

Her name was Mona Lisa.

---

One Heist Changes Everything

Before 1911, the Mona Lisa was appreciated but relatively unknown outside art circles. It wasn't the star attraction of the Louvre Museum, overshadowed by other works like the Venus de Milo or the Nike of Samothrace​​.

However, the painting's theft that year changed everything, causing the work of art to attain a cult-like status which catapulted it into the upper echelon of the art world.

And despite the clear cause and effect at play, this theft’s indelible mark remains largely forgotten today by most, who blindly accept that the Mona Lisa is, and always has been, the pinnacle of artistic achievement (just don’t ask them why).

Vincenzo Peruggia, the man behind the theft, wasn't a seasoned criminal but rather, a handyman who had been hired to install protective glass over the very painting he stole.

But Peruggia's crime was not just a theft but a statement, though perhaps a poorly-thought-out one.

In a dramatic courtroom moment after his capture, Peruggia, offended at being called a housepainter, stood up and proclaimed himself an artist​​.

This is incredibly illustrative of the mind of the thief — revealing him to be a bitter and (in his opinion) under-appreciated talent, sick of being ignored and intent on attracting the attention of the social class that rejected him by any means necessary.

The theft in 1911 ignited a media frenzy.

News of the Mona Lisa's disappearance spread rapidly, along with countless conspiracy theories.

The painting's absence created a void that was filled by public curiosity and speculation, making it more famous than it had ever been when it was actually present.

The arrest of Pablo Picasso, a rising star in the art world, on suspicion of involvement (though he was quickly exonerated)^1 only served to further sweeten the pot, incorporating the name of a man who would soon become a world-famous artist certainly assisted in the legend’s resilience through the years.

Upon its return to the Louvre in 1914, the Mona Lisa attracted an astounding 100,000 visitors in just two days​​ (today, 80% of visitors to the Louvre are there to see the Mona Lisa).

The transfer of the painting back to France after its recovery

The painting transcended its status as another work of art among a crowd; it had become a singular cultural icon, a source of intrigue, mystery, and a reminder of the powerful impact of a good story.

@ 044b20cf:89e58620

Samsung is doubling its semiconductor investment in Texas to $44 billion

It looks like President Biden’s CHIPS Act (https://www.engadget.com/senate-passes-chips-plus-chip-production-bill-185318688.html) is starting to pay off. Samsung is planning on doubling its investment in Texas, according to a report by The Wall Street Journal (https://shopping.yahoo.com/rdlw?merchantId=2f007401-3eaa-4237-b69b-54ccbe125502&siteId=us-engadget&pageId=1p-autolink&featureId=text-link&merchantName=The+Wall+Street+Journal&custData=eyJzb3VyY2VOYW1lIjoiV2ViLURlc2t0b3AtVmVyaXpvbiIsImxhbmRpbmdVcmwiOiJodHRwczovL3d3dy53c2ouY29tL3RlY2gvc2Ftc3VuZy10by1mb3J0aWZ5LXUtcy1jaGlwLXJldml2YWwtYnktc3dlbGxpbmctaXRzLXRleGFzLWludmVzdG1lbnQtdG8tNDQtYmlsbGlvbi02ZDJkMTc5OSIsImNvbnRlbnRVdWlkIjoiOTY5Njc5NzUtYjc0Yy00NDBmLWFlOWQtZjA3NzE3NWNkZjRjIn0&signature=AQAAAYyV_9-4bbFuVU3UieJ3MctnQF87yiB1rAIb8ukpkaF4&gcReferrer=https%3A%2F%2Fwww.wsj.com%2Ftech%2Fsamsung-to-fortify-u-s-chip-revival-by-swelling-its-texas-investment-to-44-billion-6d2d1799). This will bring the total investment in the state’s chip-manufacturing sector to $44 billion, as Samsung already spent nearly $20 billion to build a factory back in 2021 (https://www.engadget.com/samsung-17-billion-chip-factory-texas-054150875.html).

The ambitious expansion will reportedly take the form of a new chip manufacturing facility, a packaging site and a research and development space. It’ll all be located in or near Taylor, Texas, as that’s where the pre-existing semiconductor facility was built (https://semiconductor.samsung.com/us/sas/company/taylor/). The current manufacturing hub isn’t operational yet, but will begin building “crucial logic chips” later this year. For the geographically challenged, Taylor is around a 40 minute drive from Austin.

If this actually happens, it’ll be a huge win for the Biden administration. One of the main goals of the CHIPS Act, after all, is to lure global chipmakers to build on US soil. To that end, Washington plans on awarding more than $6 billion (https://www.bloomberg.com/news/articles/2024-03-15/samsung-poised-to-win-over-6-billion-for-expanded-us-investment?embedded-checkout=true) to Samsung as further incentive to keep things running in the good ole USA.

The CHIPS Act has allowed the federal government to award funding and offer loans to many tech companies to encourage domestic spending. Back in February, the multinational semiconductor company GlobalFoundries received a grant of $1.5 billion (https://www.engadget.com/globalfoundries-secures-15-billion-in-chips-act-funding-for-us-expansion-172754429.html) to help pay for a major US expansion, in addition to a $1.6 billion loan. It plans on building a new fabrication facility in Malta, New York, which will handle the manufacture of chips for the automotive, aerospace, defense and AI industries.

More recently, Intel received the largest CHIPS grant to date (https://www.engadget.com/intel-will-get-85-billion-in-chips-act-funding-to-support-its-us-manufacturing-efforts-090046810.html), snagging up to $8.5 billion to continue various US-based operations. The current plan is for Intel to use that money to manufacture plants that make leading-edge semiconductor chips meant for use in AI and other advanced applications. The company’s building two new fabrication facilities in Arizona and two in Ohio. Additionally, it’s going to use the money to modernize two pre-existing fabs in New Mexico and expand one location in Oregon. All told, Intel is going to invest $100 billion in US-based chip manufacturing. The various projects are expected to create 20,000 construction and 10,000 manufacturing jobs.

The Biden administration signed the CHIPS and Science Act into law back in 2022 to foster domestic semiconductor research and manufacturing and to lessen America’s reliance on Chinese suppliers. It sets aside $52 billion in tax credits and funding for firms to expand stateside production.

This article originally appeared on Engadget at https://www.engadget.com/samsung-is-doubling-its-semiconductor-investment-in-texas-to-44-billion-154322399.html?src=rss

https://www.engadget.com/samsung-is-doubling-its-semiconductor-investment-in-texas-to-44-billion-154322399.html?src=rss

@ 044b20cf:89e58620

Meta plans to more broadly label AI-generated content

Meta (https://www.engadget.com/tag/meta/) says that its current approach to labeling AI-generated content (https://www.engadget.com/meta-plans-to-ramp-up-labeling-of-ai-generated-images-across-its-platforms-160234038.html) is too narrow and that it will soon apply a "Made with AI" badge to a broader range of videos, audio and images. Starting in May, it will append the label to media when it detects industry-standard AI image indicators or when users acknowledge that they’re uploading AI-generated content. The company may also apply the label to posts that fact-checkers flag, though it's likely to downrank content that's been identified as false or altered.

The company announced the measure in the wake of an Oversight Board decision (https://www.engadget.com/maliciously-edited-joe-biden-video-can-stay-on-facebook-metas-oversight-board-says-110042024.html) regarding a video that was maliciously edited to depict President Joe Biden touching his granddaughter inappropriately. The Oversight Board agreed with Meta's decision not to take down the video from Facebook as it didn't violate the company's rules regarding manipulated media. However, the board suggested that Meta should “reconsider this policy quickly, given the number of elections in 2024.”

Meta says it agrees with the board's "recommendation that providing transparency and additional context is now the better way to address manipulated media and avoid the risk of unnecessarily restricting freedom of speech, so we’ll keep this content on our platforms so we can add labels and context." The company added that, in July, it will stop taking down content purely based on violations of its manipulated video policy. "This timeline gives people time to understand the self-disclosure process before we stop removing the smaller subset of manipulated media," Meta's vice president of content policy Monika Bickert wrote in a blog post (https://about.fb.com/news/2024/04/metas-approach-to-labeling-ai-generated-content-and-manipulated-media/).

Meta had been applying an “Imagined with AI” label to photorealistic images that users whip up using the Meta AI tool (https://www.engadget.com/metas-ai-image-generator-struggles-to-create-images-of-couples-of-different-races-231424476.html). The updated policy goes beyond the Oversight Board's labeling recommendations, Meta says. "If we determine that digitally-created or altered images, video or audio create a particularly high risk of materially deceiving the public on a matter of importance, we may add a more prominent label so people have more information and context," Bickert wrote.

While the company generally believes that transparency and allowing appropriately labeled AI-generated photos, images and audio to remain on its platforms is the best way forward, it will still delete material that breaks the rules. "We will remove content, regardless of whether it is created by AI or a person, if it violates our policies against voter interference, bullying and harassment, violence and incitement, or any other policy in our Community Standards," Bickert noted.

The Oversight Board told Engadget in a statement that it was pleased Meta took its recommendations (https://www.oversightboard.com/decision/FB-GW8BY1Y3) on board. It added that it would review the company's implementation of them in a transparency report down the line.

"While it is always important to find ways to preserve freedom of expression while protecting against demonstrable offline harm, it is especially critical to do so in the context of such an important year for elections," the board said. "As such, we are pleased that Meta will begin labeling a wider range of video, audio and image content as 'Made with AI' when they detect AI image indicators or when people indicate they have uploaded AI content. This will provide people with greater context and transparency for more types of manipulated media, while also removing posts which violate Meta’s rules in other ways."

Update 4/5 12:55PM ET: Added comment from The Oversight Board.

This article originally appeared on Engadget at https://www.engadget.com/meta-plans-to-more-broadly-label-ai-generated-content-152945787.html?src=rss

https://www.engadget.com/meta-plans-to-more-broadly-label-ai-generated-content-152945787.html?src=rss

@ 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!

@ 57d1a264:69f1fee1

Prompt: Media Player ===============

Design a player with all the functions needed: play, pause, volume, skip, fast forward, etc. Depending on the device you'll want to consider different needs such as inputs for a TV, YouTube or hover effects for a remote cursor. Could be a way to interact with it differently?

---

Flex your design muscles and join in. Most of all, keep this exercise loose and keep it stress-free. The FUC is about growing our design skills, together, as a community. We can't wait to see what you create!

Happy designing, Stackers!

---

Share Your Results When you finish the challenge, post your work on this thread! If you also share it on nostr, be sure to use the hashtag #FUCdesiger and tag Design_r@iris.to or @Design__r on X! We'll keep an eye out and repost good examples on a regular basis.

---

Curious to know WTF is a FUC? Read the ⚡️Flash Ui Challenges welcoming post.

Looking for more FUCs? Check the archive here!

@ a012dc82:6458a70d

Table Of Content

• Content

• Conclusion

• FAQ

• Meta Description

• External Links

For years, people have been talking about and debating this issue, but how exactly do you pronounce it, and what does it even refer to? Here is the information that you need:

How to pronounce Dogecoin

It is possible to trace the origin of the term "doge" all the way back to 2005, and its pronunciation changes depending on the country.

The variances tend to be different in nations that do not speak English compared to those that do.

This includes those who like pronouncing the first syllable as "dog" or "doggy," as well as others who favor pronouncing it as "dodge."

On the other hand, according to Billy Markus, one of the co-founders of the cryptocurrency, the word should be pronounced "dojh." "coin."

What is Dogecoin?

Dogecoin is a kind of cryptocurrency that was first created in 2013 as a joke.

The coin was named after a popular online joke that revolves around a picture of a Shiba Inu dog and makes fun of users' poor spelling skills by using the word "doge" instead of "dog."

Developers first created the currency as a spoof of Bitcoin; nevertheless, as the 2010s progressed, it started to gain appeal among users.

For instance, according to Investopedia, its value increased by 300 percent when China stopped banks from participating in cryptocurrencies roughly two weeks after its inception. This occurred after China banned banks from investing in cryptocurrencies.

CoinMarketCap, a company that compiles information on cryptocurrencies, reports that the price per coin peaked on April 13, 2021, at $0.09518.

Because of this, the Financial Conduct Authority (FCA) issued a warning to the general public about the dangers associated with investing in cryptocurrencies.

Who are Dogecoin's founders?

In 2013, Billy Markus and Jackson Palmer established the cryptocurrency known as "dogecoin."

Before coming together to establish the phenomenon of cryptocurrencies, the two individuals each worked as software engineers in their own right.

Markus was employed by IBM at the time and was based in Portland, Oregon. Palmer, on the other hand, was based in Sydney and worked in the marketing department for Adobe Systems.

After that, Markus contacted Jackson Palmer and jokedly tweeted, "Investing in Dogecoin; very confident it's the next big thing." Jackson Palmer responded positively to Markus's post.

However, none of them are working on the project at this time, with Mr. Markus informing the Wall Street Journal that he sold all of his dogecoin in 2015.

He said that the concept of dogecoin having a value of 8 cents is comparable to the assumption that GameStop has a value of $325.

"It doesn't make sense." It is really ridiculous. The design of the coin was ridiculous.

The decision to do so was made in spite of the widespread attention that was given to cryptocurrency as a result of Elon Musk's series of statements that were posted online.

Among them, the computer industry mogul shared a parody of a news piece titled "crazy fictitious internet money," coupled with a meme whose caption read "crazy imaginary internet money." "Dogecoin rulz."

Conclusion

The lesson to be learned from this is that it is impossible to standardize the way digital currencies like Dogecoin are pronounced across the board. Doing so would run counter to the collaborative nature of the Dogecoin project. The Dogecoin community, which sprung up spontaneously to promote the cryptocurrency, is known for being humorous and quirky. There is nothing that is less playful and humorous than trying to fix the pronunciation of another person.

FAQ

What is the current supply of Dogecoin in circulation? When it was first released, the maximum number of Dogecoins that could ever be created was set at 100 billion. However, not long after the DOGE cryptocurrency was first made available for purchase, the monetary policy of Dogecoin was altered, and an indefinitely inflated supply was introduced.

Where can I purchase Dogecoin? On cryptocurrency exchanges such as Binance, where you can sign up and establish an account as well as purchase Dogecoin without spending any money, it is possible to acquire DOGE.

How to Profit from Dogecoin You may make a profit from a change in the price of Dogecoin by selling it on crypto exchanges using the same exchange from which you purchased the cryptocurrency in the first place.

That's all for today, see ya tomorrow

If you want more, be sure to follow us on :

*NOSTR: croxroad@getalby.com*

X: @croxroadnews

Instagram: @croxroadnews.co

Youtube: @croxroadnews

Store: https://croxroad.store

Subscribe to CROX ROAD Bitcoin Only Daily Newsletter

https://www.croxroad.co/subscribe

DISCLAIMER: None of this is financial advice. This newsletter is strictly educational and is not investment advice or a solicitation to buy or sell any assets or to make any financial decisions. Please be careful and do your own research.

@ 57d1a264:69f1fee1

What have you designed this week?

Be proud of you and leave a comment below to let the SN ~Design community know what you're designing on this week. It doesn't matter if it's a sketch or a high resolution screen, nor how much progress you've made.

Just share what you're up to, and let the community know if you want any feedback or help. If you missed last week's thread, here are the updates stackers shared from all their latest work projects.

@ 1739d937:3e3136ef

"Gossip", "Outbox", "Inbox", "Blastr", "Small relays vs Big relays". You've probably seen most of these topics come up in conversations and memes recently. You might have even read nostr:nprofile1qqsf03c2gsmx5ef4c9zmxvlew04gdh7u94afnknp33qvv3c94kvwxgsm3u0w6's article (nostr:naddr1qq2hxenh2cchynnpdag4sepkx4gxyj2dt9nk6q3qjlrs53pkdfjnts29kveljul2sm0actt6n8dxrrzqcersttvcuv3qxpqqqp65wd3a9ny), or nostr:nprofile1qqswuyd9ml6qcxd92h6pleptfrcqucvvjy39vg4wx7mv9wm8kakyujgua442w's very technical article (nostr:naddr1qqxnzde3xycngdpjxg6nqdfsqgswuyd9ml6qcxd92h6pleptfrcqucvvjy39vg4wx7mv9wm8kakyujgrqsqqqa28906usv), or maybe even nostr:nprofile1qqsrhuxx8l9ex335q7he0f09aej04zpazpl0ne2cgukyawd24mayt8g2lcy6q's one with the clickbaity title (nostr:naddr1qvzqqqr4gupzqwlsccluhy6xxsr6l9a9uhhxf75g85g8a709tprjcn4e42h053vaqydhwumn8ghj7un9d3shjtnhv4ehgetjde38gcewvdhk6tcprfmhxue69uhhq7tjv9kkjepwve5kzar2v9nzucm0d5hsz9mhwden5te0wfjkccte9ehx7um5wghxyctwvshsqzpcxasnyvpcvsusgpcqx3).

These are all great, and you should go and read them too. But one thing that each of them is guilty of is assuming that the audience has enough context to jump into the middle of a very nuanced and technical discussion. I've yet to see a clear description of what Gossip or Outbox really are and certainly none that are written in a way that is approachable for a non-technical audience. I hope this article can give you that context and serve as a high-level overview of the discussion and the technologies involved so that you can go forth to create better, more informed memes (is there anything more important, really?) and join the discussion in a productive way.

The problems

Centralization is the default

First off, why are we even talking about relays? Most of know that nostr is a protocol which is designed to be decentralized from the ground up. That decentralization is due in large part to the fact that users read and write data to multiple relays by default. So instead of all your data going to a centralized database (usually owned and operated by a single company) with nostr you have the ability to send your data to as as many relays as you'd like (relays are just databases, after all). Likewise, you can read other people's data from as many relays as you'd like to. Decentralized design = decentralized system, right!? Well, turns out, no.

The problem with a design like this is that what can be done and what will be done are often very different things. Imagine the following scenario: You follow 1000 people; 700 of them post their notes to the Primal relay, the other 300 post their notes to the Damus relay. If you don't also write your content to those two relays, the people that you care about won't see your content, they won't see your replies to their notes, they won't even know you exist. So while; in practice, it's easy to read & write to many different relays, users and their content will tend to centralize because it's the path of least resistance to a good user experience. Network effects and economies of scale always apply, they just don't always lead to the outcomes that you want.

Before you start to panic, this sort of centralization isn't a huge issue just yet. We are still a nascent network and there are still hundreds of active relays out there. Almost all nostr clients make relay selection a first class citizen and don't default new users to a single relay. The fact that we're even having this conversation in a serious way at this stage is a great sign that the community cares enough to be proactive about maintaining (and improving) decentralization over time.

That said, this is not a issue that we can take lightly either. The top 5-10 relays do already have an outsized percentage of users and we have many examples of these centralizing tendencies across dozens of protocols and networks over the last 30 years, so the threat is real.

The status quo is wasteful

The other major issue is that currently most nostr clients are extremely wasteful in how they fetch data. The default is to simply get everything from all the relays a user wants to connect to. Because most of us are writing the same data to many relays, this leads to huge amounts of duplicated data being downloaded, having its signatures verified, and then (for the most part) thrown away. For those of us with latest generation smartphones, unlimited data, and a working power outlet nearby, this is fine. For everyone else, this is a major roadblock to adopting nostr.

A lightly technical aside

There are a few important features of nostr that make any sort of intelligent data fetching possible. To understand how any of the potential solutions to the aforementioned problems would actually work, it's important to have a baseline understanding of these technical details. I promise, I'll keep it high level.

Relay lists

Recently the concept of a Relay List Metadata has been introduced to the spec in NIP-65 (there are also other types of relay lists documented in NIP-51). This is a nostr list event where users publish their preferred relays with a marker that says whether the relay is for read-only, write-only, or read & write. This vastly simplifies the process of finding preferred user relays for clients and I imagine that this will become the de facto standard place to look for a user's preferred relays.

NIP-05

The NIP-05 spec also documents a way for users to signal their preferred relays. However, unlike the NIP-65 relay list, this is a simple list of relays without any details on whether the user reads or writes to those relays.

Tag markers

Tag markers are positional elements in tags that give the client publishing the event the ability to leave a hint as to which relay other clients can expect to find a given user or note that is being referenced.

For example, in a user's contact list (a kind: 3 event) you have many "p" tags to reference all the user's that are followed. These tags look like this:

{ "kind": 3, "tags": [ ["p", "91cf9..4e5ca", "wss://alicerelay.com/", "alice"], ["p", "14aeb..8dad4", "wss://bobrelay.com/nostr"], ["p", "612ae..e610f"] ], "content": "", ...other fields }

All three of these "p" tags are valid (only the "p" and the user's pubkey are required), in the first and second you can see the third item is a relay where the user's events can be found.

These types of tag markers are repeated all throughout nostr. Here's a few more example references for an event (in this case a long-form article):

``` ["e", "b3e392b11f5d4f28321cedd09303a748acfd0487aea5a7450b3481c60b6e4f87", "wss://relay.example.com"],

["a", "30023:a695f6b60119d9521934a691347d9f78e8770b56da16bb255ee286ddf9fda919:ipsum", "wss://relay.nostr.org"] ```

As you can imagine, these hints can be very helpful but only if clients actually attempt to fetch the content from the referenced relay.

The solutions?

Now that you understand the problem space a bit better let's define those terms we started with.

Blastr

Blastr was created by nostr:nprofile1qqs9hejyd252x8q3kw6980ud4lymx3hlx2x3lgg6p7sz58nyv8m2nvgdswkeh and nostr:nprofile1qqswrlemlh2wgqc4jkds3d8ueqj9a2j3gcm7r48v9tskdd6rxsd7rtcpwpuwc from Mutiny and isn't a relay. Instead, Blastr is a proxy (i.e. it looks like a relay to clients) that ingests any event sent to it and, in turn, sends those events to EVERY online relay on the network. It's a mass re-broadcaster for events that can be helpful to get your data pushed out to as many relays (and thus users) as possible. The drawback, of course, is that this is tremendously wasteful from a bandwidth and storage perspective.

Gossip (in 3 flavors)

This is by far the most confusing part for most people when watching the memes of the last few weeks fly by and I've seen a lot of confused takes out there. Most of the confusion stems from the multiplicity of definitions of what the "gossip model" actually is. Let's go through the options. 1. Gossip protocols: This is a general concept more than a specific implementation. Gossip protocols are protocols that attempt to spread information around a network in a uniform way. For example, Bitcoin nodes use a variation of the gossip protocol to make sure that transactions end up in as many mempools as possible. This is important in computing when you want to reach consensus or when all nodes in a network need to have the same information in order to operate the network. Since nostr doesn't have any consensus rules or shared compute, it's somewhat pointless to try and make sure all events are propagated to all relays (hence the limited usefulness of Blastr). 2. The Gossip client from nostr:nprofile1qqswuyd9ml6qcxd92h6pleptfrcqucvvjy39vg4wx7mv9wm8kakyujgua442w : This is a nostr client that was built from the ground up to try and use relays and relay hints in events to the fullest to keep things as decentralized as possible while being efficient in how much data it was fetching. Mike has a great (slightly outdated and very technical) video that talks about his motivation behind building Gossip in the way he did. It's worth a watch. video link 3. Gossip model: This is what people are usually referring to when they are talking about relays on nostr. The Gossip model is a loose, catch-all term used to refer to all the ways in which clients attempt to understand which relays they should read & write to for a given user. Again, this isn't really a specific spec or implementation but encompasses many different strategies. This vagueness inherent in the term makes discussions about the "gossip model" pretty imprecise and prone to misunderstanding.

Don't gossip

To be clear: You really shoud not be thinking about or talking about any of this as the "gossip model" since that definition is so abstract as to be unusable. Which brings us finally to the real topic being discussed at the moment among devs; the Outbox model.

Outbox/Inbox model

This is the real topic of conversation right now: How should client developers build relay discovery and selection features into their apps. As we already talked about, if left alone, it's likely that we'd unintentionally centralize most of nostr onto a few huge relays. So making sure that we encourage (and build sensible defaults) to help client developers to treat relay discovery and selection properly is really critical.

Right now, the discussion centers around one main approach, called the "Outbox model". There is also an "Inbox model" which is a still just a high level idea which I'll mention below but it's not being implemented yet (as of late March 2024). 1. The "Outbox model": This strategy looks at what relays users are using to publish their events (from relay lists and tag markers) and then uses an algorithm to decide how to fetch all the needed events from the array of relays. Different implementations can use different algorithms to select relays. For example, one implementation might optimize fetching events from the smallest number of relays (favoring large relays), while another might optimize for fetching from the relays that have the smallest user overlap (favoring small relays). 2. The "Inbox model": As you can imagine, this strategy flips the outbox model on it's head. It's so far just an idea (proposed by nostr:nprofile1qqs8nsk2uy2w529fs8n4tx60u7z553e4yx5dy2nxhw4elgjgawpqlas9waufq) and a draft NIP but the idea is that when your client posts on your behalf, it will loop over your entire follow list, making a list of the relays that each of your followers uses to read events. Then the client will publish your event to all of those relays. If all clients followed this paradigm, then each of us would only have to read from a single relay. To quote nostr:nprofile1qqs8nsk2uy2w529fs8n4tx60u7z553e4yx5dy2nxhw4elgjgawpqlas9waufq 's original post, "This doesn't take away from the outbox approach, and maybe should even be used together instead of as a replacement. But my point is that clients should be trying harder to deliver posts instead of just fetch posts. Because it benefits users when their posts can be seen."

Why the Outbox model has broad support

To understand why implementing an Outbox model is so powerful at solveing the problems laid out at the beginning of this article, you can do two quick thought experiments:

A user banned from all other relays

Imagine a user who's content is banned from all public relays for some reason. Instead, they have to run their own relay and publish their events there. With a simple "follow the major relays model" (or even with Blastr attempting to copy and paste their events to every other relay) this user is completely invisible to the network. User's would have to know about the banned user's private relay and select that relay in each client they use. What's more, if that relay ever had to change URL (likely for a user that is banned so broadly), all user's would need to know what the new URL is in order to change relays and fetch events from the new location.

With Outbox however, clients will see that their user's follow this user, will then look up this user's relay list, and will know where they need to go to fetch their events. It becomes much more difficult for relays to censor or block users with an Outbox model in place

Duplicate event fetching

We talked earlier about how many nostr clients often fetch the same data many times, just to throw that data away. Even using the simplest algorithms with an Outbox model, you can significantly reduce the amount of duplicate data you're fetching from relays. We, as users, would all also need to specific many fewer relays in our relay lists but would still be quite sure our clients would be able to find all the content we want to see.

Wrapping up

Hopefully this has given you a better overall understanding of what folks are talking about when they refer to Gossip (remember: don't refer to it this way) or Outbox (outbox, yay!) and why we need to be proactive about maintaining the decentralization of nostr.

@ 1b443742:17f53392

• It is almost April!
• How about this external image ?
• Do something to your hair.
• Have you ever eaten a spoon full of peanut butter ?
• Have you ever eaten a spoon full of ketchup ?
• Do you like spiders ?
• How about this external image ?

@ 044b20cf:89e58620

Our favorite cheap Android tablet is on sale for $170

We highlight Samsung's Galaxy Tab A9+ (https://shopping.yahoo.com/rdlw?merchantId=66ea567a-c987-4c2e-a2ff-02904efde6ea&siteId=us-engadget&pageId=1p-autolink&featureId=text-link&merchantName=Amazon&custData=eyJzb3VyY2VOYW1lIjoiV2ViLURlc2t0b3AtVmVyaXpvbiIsImxhbmRpbmdVcmwiOiJodHRwczovL3d3dy5hbWF6b24uY29tL1NBTVNVTkctQW5kcm9pZC1TcGVha2Vycy1VcGdyYWRlZC1HcmFwaGl0ZS9kcC9CMENMRjNWUE1WP3RhZz1nZGd0MGMtcC12LWQwLTIwIiwiY29udGVudFV1aWQiOiJlY2RjMGY0OS1lMGI2LTRhZDQtYTE1My0wNGJiODlkMDQ5NTgifQ&signature=AQAAAblIesWqNWUoJBT9YNOCc-jS3gyB5gaQTrQoBhAubYF7&gcReferrer=https%3A%2F%2Fwww.amazon.com%2FSAMSUNG-Android-Speakers-Upgraded-Graphite%2Fdp%2FB0CLF3VPMV) in our Android tablet buying guide (https://www.engadget.com/best-android-tablet-120007530.html) for those who just want a competent slate for as little money as possible. If that describes you, take note: The 11-inch device is now on sale for $170 at several retailers, including Amazon, Walmart (https://shopping.yahoo.com/rdlw?merchantId=3719d8d4-5edd-4817-998a-91f3229e7323&siteId=us-engadget&pageId=1p-autolink&featureId=text-link&merchantName=Walmart&custData=eyJzb3VyY2VOYW1lIjoiV2ViLURlc2t0b3AtVmVyaXpvbiIsImxhbmRpbmdVcmwiOiJodHRwczovL3d3dy53YWxtYXJ0LmNvbS9pcC9TYW1zdW5nLUdhbGF4eS1UYWItQTktMTEtVGFibGV0LTY0R0ItQW5kcm9pZC1HcmFwaGl0ZS81MTY2NjY1NTQwIiwiY29udGVudFV1aWQiOiJlY2RjMGY0OS1lMGI2LTRhZDQtYTE1My0wNGJiODlkMDQ5NTgifQ&signature=AQAAAahy1EXU5xBQGla3m988_Iyegn4kLjlDKC0_jAzqHLvL&gcReferrer=https%3A%2F%2Fwww.walmart.com%2Fip%2FSamsung-Galaxy-Tab-A9-11-Tablet-64GB-Android-Graphite%2F5166665540) and Best Buy (https://sovrn.co/r0tidkr). This deal has technically been available for a couple of weeks, but it still represents the lowest price we've tracked. For reference, Samsung typically sells the tablet for $220. Both the Graphite and Silver finishes are discounted.

Do note, though, that this price applies the base model, which includes 4GB of RAM and 64GB of storage. The latter is expandable with a microSD card (https://www.engadget.com/best-microsd-card-130038282.html), but the limited memory can cause some stutters if you want to push the the tablet for anything beyond casual streaming and web browsing. Samsung sells a higher-spec model (https://shopping.yahoo.com/rdlw?merchantId=66ea567a-c987-4c2e-a2ff-02904efde6ea&siteId=us-engadget&pageId=1p-autolink&featureId=text-link&merchantName=Amazon&custData=eyJzb3VyY2VOYW1lIjoiV2ViLURlc2t0b3AtVmVyaXpvbiIsImxhbmRpbmdVcmwiOiJodHRwczovL3d3dy5hbWF6b24uY29tL1NBTVNVTkctQW5kcm9pZC1TcGVha2Vycy1VcGdyYWRlZC1HcmFwaGl0ZS9kcC9CMENMRjJETk1WP3RhZz1nZGd0MGMtcC12LWQwLTIwIiwiY29udGVudFV1aWQiOiJlY2RjMGY0OS1lMGI2LTRhZDQtYTE1My0wNGJiODlkMDQ5NTgifQ&signature=AQAAATaX0jH8LB2cfCZOU-n2MWRXu1WfUn0SSJqvo8Nxs4uq&gcReferrer=https%3A%2F%2Fwww.amazon.com%2FSAMSUNG-Android-Speakers-Upgraded-Graphite%2Fdp%2FB0CLF2DNMV) with 8GB of RAM and 128GB of storage: That one will be a better buy for gaming and more involved use, and it's also $50 off at $220, another all-time low.

As my colleague Sam Rutherford notes in our buying guide, the Galaxy Tab A9+ isn't likely to wow you in any one area, but it covers the basics well. Its 11-inch LCD display is well-sized and has a faster-than-usual 90Hz refresh rate, which helps the UI feel smooth to scroll through. The screen has a wide 16:10 aspect ratio, so it's better suited to landscape mode than the 4:3 display on an iPad. The metal and plastic frame is slick for the price, while the 7,040mAh battery should hold up for a day or two of casual use. And though no Android tablet really nails the software experience, most people should find Samsung's One UI to be cleaner than something like Amazon's Fire OS (https://www.engadget.com/amazon-fire-hd-8-review-130005977.html). The company says (https://www.samsungknox.com/en/knox-platform/supported-devices) it'll provide OS updates through the eventual Android 16 and security updates through October 2027.

That said, this is still a cheap tablet. The Galaxy Tab A9+'s Snapdragon 695 chip is speedy enough but no powerhouse, and its charging speed tops out at a relatively meager 15W. There's no fingerprint reader, included stylus or formal water-resistance rating, either. If you're not beholden to Android, one of Apple's iPads (https://www.engadget.com/best-ipads-how-to-pick-the-best-apple-tablet-for-you-150054066.html) will still be more well-rounded (though we expect to see (https://www.engadget.com/an-oled-ipad-pro-and-the-first-big-screen-ipad-air-will-reportedly-arrive-in-may-204056132.html) new models arrive in the coming weeks). Still, at these prices, the Galaxy Tab A9+ is a solid buy if you're on a tighter budget.

Follow__@EngadgetDeals (https://twitter.com/EngadgetDeals) on Twitter and__subscribe to the Engadget Deals newsletter (https://subscription.yahoo.net/Newsletter/Preference/sub?b=engadgetdeals&src) for the latest tech deals and buying advice.

This article originally appeared on Engadget at https://www.engadget.com/our-favorite-cheap-android-tablet-is-on-sale-for-170-151624727.html?src=rss

https://www.engadget.com/our-favorite-cheap-android-tablet-is-on-sale-for-170-151624727.html?src=rss

@ 044b20cf:89e58620

Apple Vision Pro owners now have more decent controller options

The Apple Vision Pro is an impressive piece of hardware (https://www.engadget.com/apple-vision-pro-review-beta-testing-the-future-201430272.html), and the eye-tracking/hand gesture input combo is fantastic for navigating menus and the like. It’s not so great for gaming. There haven't been many easy ways to connect a third-party controller for playing iPad or cloud games. This is changing, however, as accessory manufacturer 8BitDo just announced Vision Pro compatibility (https://analogueconsulting.campaigns.dmanalytics2.com/usr/c67af2da76977911f343cb91cbf5e8c3/eml/wR2uxvxkT2GuDekIzsh6QQ) for a number of its controllers.

These accessories are officially supported by Apple, so they should work as soon as you make a Bluetooth connection. No muss and no fuss. All told, eight devices got the Apple seal of approval here. One such gadget is the company’s Ultimate Bluetooth Controller, which we basically called the perfect gamepad for PC (https://www.engadget.com/what-we-bought-the-last-gamepad-ill-need-to-buy-for-switch-and-pc-140047518.html).

8BitDo

Other compatible devices include various iterations of the SN30 Pro controller (https://shopping.yahoo.com/rdlw?merchantId=66ea567a-c987-4c2e-a2ff-02904efde6ea&siteId=us-engadget&pageId=1p-autolink&featureId=text-link&merchantName=Amazon&custData=eyJzb3VyY2VOYW1lIjoiV2ViLURlc2t0b3AtVmVyaXpvbiIsImxhbmRpbmdVcmwiOiJodHRwczovL3d3dy5hbWF6b24uY29tLzhCaXRkby1TbjMwLVByby1CbHVldG9vdGgtR2FtZXBhZC1DbGFzc2ljL2RwL0IwN0dLTEczWlA_dGFnPWdkZ3QwYy1wLXYtY3otMjAiLCJjb250ZW50VXVpZCI6ImFjYmE5MjBlLTRmN2MtNDQ1Yi1hYmI3LTE5MjIwNzA0NWVhMCJ9&signature=AQAAAR5YTea_sDt5zDpcTLVt78BmfmJlJdsmlDJ1J7llhXJy&gcReferrer=https%3A%2F%2Fwww.amazon.com%2F8Bitdo-Sn30-Pro-Bluetooth-Gamepad-Classic%2Fdp%2FB07GKLG3ZP), the Lite 2 (https://shopping.yahoo.com/rdlw?merchantId=66ea567a-c987-4c2e-a2ff-02904efde6ea&siteId=us-engadget&pageId=1p-autolink&featureId=text-link&merchantName=Amazon&custData=eyJzb3VyY2VOYW1lIjoiV2ViLURlc2t0b3AtVmVyaXpvbiIsImxhbmRpbmdVcmwiOiJodHRwczovL3d3dy5hbWF6b24uY29tL0JsdWV0b290aC1Db250cm9sbGVyLVZpYnJhdGlvbi1Kb3lzdGlja3MtU3dpdGNoLU5pbnRlbmRvL2RwL0IwQlozV0Q3UTUvP3RhZz1nZGd0MGMtcC12LWN6LTIwIiwiY29udGVudFV1aWQiOiJhY2JhOTIwZS00ZjdjLTQ0NWItYWJiNy0xOTIyMDcwNDVlYTAifQ&signature=AQAAAYi5um1IHbxFmYCSo7LCgb9SaVjp-HRYQUvRp5AK1_Sq&gcReferrer=https%3A%2F%2Fwww.amazon.com%2FBluetooth-Controller-Vibration-Joysticks-Switch-Nintendo%2Fdp%2FB0BZ3WD7Q5%2F) and the NES-inspired N30 Pro 2. The integration isn’t just for game controllers, as 8BitDo also announced AVP compatibility for its Retro Mechanical Keyboard (https://www.engadget.com/8bitdos-nintendo-inspired-mechanical-keyboard-has-super-buttons-just-begging-to-be-mashed-150024778.html). Of course, the Vision Pro works out of the box with most Bluetooth keyboards.

This is pretty big news, however, as media consumption is one of the best parts of the Vision Pro experience. Video games fall squarely in that category. Just about every iPad title works on the device. If playing Cut the Rope on a giant virtual screen doesn’t do it for you, the headset also integrates with Xbox Cloud Gaming and Nvidia GeForce Now for access to AAA titles.

8BitDo announced official controller support for Apple devices (https://www.engadget.com/8bitdo-controllers-now-work-with-apple-devices-163657954.html) last year, though this was primarily for smartphones, tablets and Mac computers. The integration was thanks to new controller firmware and Apple's recent iOS 16.3, iPadOS 16.3, tvOS 16.3 and macOS 13.2 updates. It looks like all of the accessories that work with iPhones and iPads also work with the Vision Pro.

This article originally appeared on Engadget at https://www.engadget.com/apple-vision-pro-owners-now-have-more-decent-controller-options-150055872.html?src=rss

https://www.engadget.com/apple-vision-pro-owners-now-have-more-decent-controller-options-150055872.html?src=rss

@ 5d4b6c8d:8a1c1ee3

Somewhere along the way advice stopped being about the world that exists and became about the world upper middle class white liberals want to exist.

As should be clear to everyone, I'm super libertarian about all of this stuff. People should live their lives in pursuit of their own visions of happiness or flourishing or whatever term encapsulates what they find fulfilling. With that said, I'm often bothered by the directions young people are pushed in. I think it's leading to them having worse lives than they could have had and it's severely damaging our culture as a result.

@kepford had a great post along these lines that didn't get enough attention: https://stacker.news/items/478976/r/Undisciplined. However, please don't take that to mean he approves of the following message.

College for Everyone

This was my first taste of this bad advice phenomenon and I had many servings of it. I haven't been in a government school in over 10 years, so I don't know if this has gotten worse, but I have enough college contacts to know it hasn't gotten better.

High school kids with severe cognitive deficiencies are systematically pushed towards college. Everyone knows that these kids have no shot at completing college, but they're too "nice" to set realistic expectations. That is not kindness. It is in fact a very perverse type of cruelty to knowingly set mentally disabled kids up for failure like that. Out of sight, out of mind, I guess. The adults in these schools should be helping these kids develop attainable skills, so that they can actually know the joys of success.

Beyond kids with cognitive challenges, many young people are not going to get much out of college. To a first approximation, all of the returns to college accrue to the top handful of STEM students. For everyone else, it's a wash at best financially.

If people want to go to college, great, but most college students are decidedly less than enthusiastic. Given the extreme expenses involved, it seems like kids in high school should at least learn about alternatives.

Relationships vs College

This segues right into my next point. The prevailing "wisdom" is that long distance relationships are impossible, so high school couples should just break up before going to college. 1. If you're in love, you can absolutely manage a long distance relationship. 2. Finding the right partner is vastly more consequential than going away to college.

The single most important choice you make in life is who to spend it with. If you make that choice correctly, you can manage everything else in time. Sacrificing all these relationships on the alter of college is pretty sickening considering the point I just made about the returns to college in the previous section.

It was not long ago that people were getting married and starting families right around the age we now all leave for college. Why did our culture decide to radically devalue these relationships all of a sudden?

Putting off Having Kids

There will always be reasons to put off having kids and our cultural messaging doesn't help. There are real biological constraints at play here and many people find that they've run out of time to have the family they wanted. That's the rest of their lives spent wishing for something they could have had. Good thing they waited to start until after getting that promotion, right?

We have friends who started their family much younger than us. Their oldest is midway through high school. All the kids will be adults by the time our friends turn 50. They'll likely get to see all of their grandkids grow up and start families. They get to spend about a decade more with their kids than my wife and I get to, because we put it off. That's a pretty big deal.

Does anyone ever hear that simple perspective when they're young?

Romantic/Sexual Landscape

At least the alternative to maintaining those relationships and starting families is equally fulfilling, right?

Oh, wait, no, it's a complete disaster of empty hookups and loneliness. At least that seems to be the reporting on the ground. More and more, young people just aren't even trying to have meaningful romantic relationships.

Romantic bonds are how we propagate the species. It's our strongest preprogrammed urge and somehow it's been beaten out of us.

Maybe glorifying casual hookups wasn't a great idea. Young people probably don't need encouragement to be irresponsible, after all. Maybe teaching girls to see any attention from a boy as some sort of assault is not working out so well for either sex.

What do Happy Lives Look Like?

It's valuable to have a culturally expected path through life. People can use the same benchmarks as previous generations and know it at least sort of works: start dating in your teens, start a family in your 20's, support your family until they're grown, etc.

That doesn't mean people must follow the path. When you're innovating, it helps to have those benchmarks to know what you're building off of. The absence of those expectations leaves people rudderless. It's a form of the Paradox of Choice. Most people actually prefer to follow a plan than to have to create everything de novo.

Without that shared vision of the good life, people are vulnerable to adverse pressure. For instance, most people get more fulfillment from their families than from their jobs, yet the pressure is almost always to sacrifice family for career.

Gender Differences

Now for the potentially touchy point. Remember, I'm libertarian guy, live the life you want, I'm not trying to proscribe anything.

We have ample evidence from psychology, sociology, economics, anthropology, history, etc., to state simply that men and women tend to value different things.

It is not helping young people when we pretend that men and women are exactly the same and push them all into the same direction. It might help them to know things like husbands and wives both tend to prefer when the husband makes more money, for instance. Or to know that many women want to take extended time out of the labor force after having kids (this is actually normal in many places, gasp).

TL;DR

There are a ton of areas where the advice young people are receiving is unmoored from reality. It's doing them an extreme disservice.

I'd love to hear other people's thoughts on the subject, especially if you think I'm off my nut on some of this.

@ 52b4a076:e7fad8bd

Introduction

LNbits is a project plagued with poor code quality, potential security risks and bad management. What can be done about it?

The problems

Improper handling of vulnerability disclosures

Case 1

Two years ago (don't remember exactly when, Twitter account deleted), I discovered an SQL injection vulnerability in LNbits. This could be exploited very easily by setting by sending the injected data in keys in the payload of most requests. (anyone could create create wallets)

This was possible due to the query to insert/update was generated using the body of the request, with basically no sanitization.

When I contacted Ben Arc about this, the fix for this exploit was not implemented for several months, and when it was, I do not recall there being an advisory for people to update.

Case 2

A month or two ago, I had discovered an exploit that allows draining nodes completely under certain conditions. I had reported this to an active maintainer of the project, which had passed it on to the team. The exploit has not been fixed.

Case 3

Again, a month or two ago, a flaw was discovered in the SatsDice extension that allowed anyone to drain wallets. I had investigated this, and found that the extension allows invoice keys (instead of admin keys only) to create dice that have a guaranteed win rate and return more sats than put in, and then use it to drain balances.

I had reported this to the team, and while it was fixed a week or two later, there was no easily visible for people to update except an "update your SatsDice extension" message in the LNbits chat buried in a conversation about the exploit.

Bad security practices

"Don't do one thing, and don't do it well"

LNbits has over time expanded its scope, from being a wallet layer to an LN apps platform to a node management tool. While this may seem great for users, it has come at a significant security cost: - There is a larger attack surface for attackers to exploit. - The newly introduced node management and admin UI feature allows easy draining of nodes if the admin URL was leaked, whether by by the autocomplete on the search bar or the user's history. - All extensions run at the same privilege level as LNbits itself which has direct access to funds.

Developers can accidentally shoot themselves in the foot

The LNbits codebase encourages many harmful development patterns that allows developers to easily create vulnerabilities that put funds at risk

Example 1

Most LNbits extensions use the following system for handling object creation/deletion: - Take the body and convert it to a class - Overwrite/sanitize fields in that class, such as preventing overwrite of the wallet ID - Pass it to the DB to write

There is a slight problem: it can be easy to miss what to sanitize and what to not sanitize.

When you are doing an update request, you may accidentally forget to overwrite the wallet_id on the request sent by the user to update a withdraw link, and trust the user. You just created a bug to drain anyone's wallet given its ID, which LNbits does not consider sensitive information and sometimes requires you to share.

Example 2

LNbits treats any error during a payment attempt an error. But errors don't always happen due to failures in your request. Network connectivity is flaky, nodes restart, and way more reasons for there to be an error while the payment actually may be going through.

If you can get a way to trigger an error during a payment call, but also have it succeed, you can easlly drain a node. I have reasons to believe this is possible in production deployments.

This could easily be fixed as attempting to check the status of a payment after an error, and if that also fails, consider the payment pending until it can be checked, but ths has not been implemented.

Bad project management

LNbits' current management suffers from many problems: - the project suffers from feature and scope creep, implementing things for the sake of it - bugs go unaddressed - security is not a top priority

This is problematic for a project that deals with funds, as it is everything that you shouldn't be doing for a project meant to deal with funds. Tens of thousands of dollars in some cases and thousands in others.

What can we do about it?

For me, I have disabled withdrawals on my LNbits instance. I am also working on a replacement project called LNLocker that will solely focus on the wallet layer bit.

I would encourage trying to replace LNbits, as hard and sometimes impossible as it may be, or if you can, modify the code or restricting access via LND macaroons so that withdrawals cannot be made.

I highly recommend not exposing LNbits to the internet if you cannot disable withdrawals.

@ 044b20cf:89e58620

Logitech’s Litra Beam key light is 10 percent off right now

Having a fancy webcam is all well and good, but another thing you might need to seriously upgrade the quality of your video calls and livestreams is a decent key light. It will illuminate your face to help you stand out from the background and help the camera discern your features more clearly. You don’t need to break the bank to get a decent key light either. Logitech’s Litra Beam (https://shopping.yahoo.com/rdlw?merchantId=66ea567a-c987-4c2e-a2ff-02904efde6ea&siteId=us-engadget&pageId=1p-autolink&featureId=text-link&merchantName=Amazon&custData=eyJzb3VyY2VOYW1lIjoiV2ViLURlc2t0b3AtVmVyaXpvbiIsImxhbmRpbmdVcmwiOiJodHRwczovL3d3dy5hbWF6b24uY29tL0xvZ2l0ZWNoLVRydWVTb2Z0LUFkanVzdGFibGUtQnJpZ2h0bmVzcy1TZXR0aW5ncy9kcC9CMEJTUVhEUzcxP3RhZz1nZGd0MGMtcC12LWN5LTIwIiwiY29udGVudFV1aWQiOiJjNTQwYzU5NS1kN2I1LTRhNGItYWViZi05Y2U2MzJkN2E0ZDIifQ&signature=AQAAAZPWK4wfXWjwJ9kGe88dWOIyz689ZmoA2rmUbGQ-gcbQ&gcReferrer=https%3A%2F%2Fwww.amazon.com%2FLogitech-TrueSoft-Adjustable-Brightness-Settings%2Fdp%2FB0BSQXDS71) is currently $10 off at $90. That’s only $5 more than the lowest price we’ve seen for it.

The Litra Beam (https://www.engadget.com/logitech-litra-beam-key-light-blue-sona-microphone-160043897.html) looks a bit like an LED reading lamp and it would be a fairly stylish addition to many setups. It has a three-way adjustable stand, allowing you to tweak the height, tilt and rotation as needed, while its ability to run on either USB or AC power gives you more placement options.

The device uses TrueSoft tech, which, according to Logitech, provides "balanced, full-spectrum LED light with cinematic color accuracy for a natural, radiant look across all skin tones." A frameless diffuser helps mitigate harsh shadows, according to the company.

You'll be able to adjust the Litra Beam's brightness, color temperature, presets and other settings through the Logitech G Hub desktop app, which also allows you to manage multiple lights at once. In addition, the key light has five physical buttons on the rear for quick switching between brightness and color temperature settings.

Follow__@EngadgetDeals (https://twitter.com/EngadgetDeals) on Twitter and__subscribe to the Engadget Deals newsletter (https://subscription.yahoo.net/Newsletter/Preference/sub?b=engadgetdeals&src) for the latest tech deals and buying advice.

This article originally appeared on Engadget at https://www.engadget.com/logitechs-litra-beam-key-light-is-10-percent-off-right-now-141839351.html?src=rss

https://www.engadget.com/logitechs-litra-beam-key-light-is-10-percent-off-right-now-141839351.html?src=rss

@ 947c8c3e:22e2d6ea

LoRa technology is being quickly adopted as a long-distance, low-power communication network, propelling a new wave of connectivity that significantly outstrips traditional methods like WiFi, Bluetooth, or ZigBee. Designed to transmit small amounts of data over vast distances, LoRa stands out as a great platform for the Ghost Grid Network and similar communities seeking to emergency preparedness and connectivity beyond conventional boundaries.

Understanding LoRa's Core

LoRa (Long Range) utilizes a wireless modulation strategy based on Chirp Spread Spectrum (CSS) technology, which encodes information across chirp pulses. This approach, inspired by the communication techniques of dolphins and bats, showcases remarkable resilience to interference, facilitating communication across extensive distances. LoRa's proficiency in handling small data packets across lengthy ranges, coupled with its operation on license-free sub-gigahertz frequency bands, makes it an obvious choice for a myriad of applications, from simple text communication, sensor networks to IoT (Internet of Things) ecosystems.

Distinctive Features of LoRa

LoRa distinguishes itself through several key attributes: - Extended Connectivity: It offers unparalleled range, enabling data transmission up to 20 km in rural settings and 5 km in urban environments, surpassing other wireless technologies. - Efficiency: LoRa devices boast extended battery life, operating for weeks on a single charge, which translates to sustainable and cost-efficient solutions. - High Capacity: Supporting a vast network of nodes, LoRa accommodates numerous messages per second, showcasing its scalability. - Security: End-to-end encryption guarantees secure data transmission, making LoRa an optimal choice for confidential communications.

LoRaWAN: Complementary Networks

You may hear of another network called LoRaWAN. LoRaWAN is a protocol that works with LoRa technology to manage how devices communicate over long distances. Think of LoRa as the way messages are sent, like speaking a language, and LoRaWAN as the rules of conversation—when to speak, how to reply, and making sure messages are understood and secure. It’s designed to ensure that devices using LoRa can connect efficiently, securely, and without using much power. Managed by the LoRa Alliance, this set of rules helps devices talk to each other and to the internet, making it easier to set up large networks of sensors and devices for things like monitoring weather or tracking assets.

Empowering the Ghost Grid Network with LoRa

The Ghost Grid Network is one example of how LoRa technology can be used for decentralized, autonomous communication systems. We leveraging LoRa's mesh protocol alongside tools like Meshtastic for effective, community-driven connectivity that benefits from each new user on the mesh. From emergency preparedness to environmental monitoring, each application benefiting from LoRa's robust, long-range, and low-power communication capabilities.

Venturing into LoRa

For enthusiasts eager to explore LoRa's potential, joining a community-focused network like Ghost Grid provides invaluable resources, tutorials, and collaboration opportunities. Starting with LoRa necessitates acquiring the appropriate hardware, such as modules and gateways, and delving into project development to contribute to the collective knowledge and application of this transformative technology.

Take Away

LoRa technology is not just a tool but as a base layer for sovereign communication, free speech and connectivity. Its long-range, low-power communication and resilient, interconnected mesh can enable us to do more without as much reliance on mega corporations and local city infrastructures. Join us as we grow the LoRa network into an awesome meshed up future!

What to Earn the Badge?

LoRa Learner Badge

As a bonus, if you successfully pass our optional quiz, you'll earn a special badge for your Nostr profile, showcasing your expertise and support for innovative communication technologies. It's a cool way to celebrate your understanding and contribution to the community.

Click here to take the quiz

@ 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

@ 3bf0c63f:aefa459d

Censorship-resistant relay discovery in Nostr

In Nostr is not decentralized nor censorship-resistant I said Nostr is centralized. Peter Todd thinks it is centralized by design, but I disagree.

Nostr wasn't designed to be centralized. The idea was always that clients would follow people in the relays they decided to publish to, even if it was a single-user relay hosted in an island in the middle of the Pacific ocean.

But the Nostr explanations never had any guidance about how to do this, and the protocol itself never had any enforcement mechanisms for any of this (because it would be impossible).

My original idea was that clients would use some undefined combination of relay hints in reply tags and the (now defunct) kind:2 relay-recommendation events plus some form of manual action ("it looks like Bob is publishing on relay X, do you want to follow him there?") to accomplish this. With the expectation that we would have a better idea of how to properly implement all this with more experience, Branle, my first working client didn't have any of that implemented, instead it used a stupid static list of relays with read/write toggle -- although it did publish relay hints and kept track of those internally and supported kind:2 events, these things were not really useful.

Gossip was the first client to implement a truly censorship-resistant relay discovery mechanism that used NIP-05 hints (originally proposed by Mike Dilger) relay hints and kind:3 relay lists, and then with the simple insight of NIP-65 that got much better. After seeing it in more concrete terms, it became simpler to reason about it and the approach got popularized as the "gossip model", then implemented in clients like Coracle and Snort.

Today when people mention the "gossip model" (or "outbox model") they simply think about NIP-65 though. Which I think is ok, but too restrictive. I still think there is a place for the NIP-05 hints, nprofile and nevent relay hints and specially relay hints in event tags. All these mechanisms are used together in ZBD Social, for example, but I believe also in the clients listed above.

I don't think we should stop here, though. I think there are other ways, perhaps drastically different ways, to approach content propagation and relay discovery. I think manual action by users is underrated and could go a long way if presented in a nice UX (not conceived by people that think users are dumb animals), and who knows what. Reliance on third-parties, hardcoded values, social graph, and specially a mix of multiple approaches, is what Nostr needs to be censorship-resistant and what I hope to see in the future.

@ 044b20cf:89e58620

NASA will be studying the total solar eclipse. Here's how you can help

On Monday, April 8, a total solar eclipse will be visible across a swath of North America, from Mexico’s Pacific coast to the easternmost reaches of Canada. And in those few minutes of daytime darkness, all sorts of interesting phenomena are known to occur — phenomena NASA would like our help measuring.

During a total solar eclipse, temperatures may drop and winds may slow down or change their course. Animals have been observed to behave unusually — you might hear crickets start their evening chatter a few hours early. Even radio communications can be disrupted due to changes in the ionosphere while the sun’s light is blocked. And, the sun’s corona — its outermost atmosphere — will come into view, presenting scientists (and those of us helping them) with a rare opportunity to study this layer that’s normally invisible to the naked eye.

NASA has lots of research efforts planned for the eclipse, and has sponsored a handful of citizen science campaigns that anyone can take part in if they’re in or near the path of totality, or the areas where people on the ground can watch (https://www.engadget.com/how-to-watch-and-record-the-2024-solar-eclipse-on-april-8-163035648.html) the sun become completely obscured by the moon. The path of totality crosses 13 US states, including parts of Texas, Oklahoma, Arkansas, Missouri, Illinois, Kentucky, Indiana, Ohio, Pennsylvania, New York, Vermont, New Hampshire and Maine. It’s an event of some significance; the next time a total solar eclipse passes over that much of the contiguous US won’t be until 2045.

All you’ll need to join in is equipment you already own, like a smartphone, and a few minutes set aside before the eclipse to go through the training materials.

NASA's Scientific Visualization Studio

Help measure the shape of the sun

One such citizen science project is SunSketcher (https://sunsketcher.org/index.php), a concerted effort to measure the true shape of the sun. While the sun is closer to being a perfect sphere than other celestial bodies that have been observed, it’s still technically an oblate spheroid, being a smidge wider along its equator. The SunSketcher team plans to get a more precise measurement by crowd-sourcing observations of Baily's Beads, or the little spots of sunlight that peek out from behind the moon at certain points in the eclipse.

The Baily’s Bead effect is “the last piece of the sun seen before totality and the first to appear after totality,” NASA explained in a blog post (https://science.nasa.gov/solar-system/skywatching/sketch-the-shape-of-the-sun-for-science-during-the-solar-eclipse/). “For a few seconds, these glimmers of light look like beads along the moon’s edge.” They’re visible thanks to the uneven topographical features on the lunar surface.

You’ll need to download the free SunSketcher app, which is available for iOS and Android on the App Store (https://apps.apple.com/us/app/sunsketcher/id6464665997) and Google Play Store (https://play.google.com/store/apps/details?id=com.wkuxr.eclipsetotality&pli=1). Then, a few minutes before totality (the exact time is location-dependent), put your phone on Do Not Disturb, hit “Start” in the app and prop up the phone in a place where it has a good view of the sun. After that, leave it be until the eclipse is over — the app will automatically take pictures of Baily’s Beads as they show up.

There’s a tutorial (https://sunsketcher.org/app-tutorial.php) on the SunSketcher website if you want to familiarize yourself with the process beforehand. When it’s all said and done, the pictures will be uploaded to SunSketcher’s server. They’ll eventually be combined with observations from all over to “create an evolving pattern of beads” that may be able to shed better light on the size and shape of the sun.

The SunSketcher images probably won’t blow you away, so if you’re hoping to get some great pictures of the eclipse, you’ll want to have another camera on hand for that (with the appropriate filters to protect your eyes and the device’s sensors).

NASA / Aubrey Gemignani

Record changes in your surroundings

Eclipse-watchers can also use their smartphones to record the environmental changes that take place when the sun dips behind the moon as part of a challenge run by Global Learning and Observations to Benefit the Environment (Globe). You’ll need an air temperature thermometer as well for this task, and can start logging observations in the days before the eclipse if you feel like being extra thorough.

Temperatures at the surface can, in some cases, drop as much as 10 degrees Fahrenheit during a total solar eclipse, according to NASA. And certain types of clouds have been observed to dissipate during these brief cooldowns, resulting in unexpectedly clear skies in the moments before totality. Data collected with the help of citizen scientists during the 2017 total solar eclipse showed that areas with heavier cloud cover (https://earthobservatory.nasa.gov/images/152590/the-best-places-to-view-the-total-solar-eclipse#:~:text=As%20the%20Moon%20blocks%20the,land%20surface%20cools%20during%20eclipses.) experienced a less extreme drop in surface temperatures.

To participate this time around, download the Globe Observer app from the App Store (https://apps.apple.com/us/app/globe-observer/id1090456751) or Google Play Store (https://play.google.com/store/apps/details?id=gov.nasa.globe.observer&hl=en&pcampaignid=MKT-Other-global-all-co-prtnr-py-PartBadge-Mar2515-1), and then open the Globe Eclipse tool from the in-app menu. There, you’ll be able to jot down your temperature measurements and take photos of the sky to record any changes in cloud cover, and make notes about the wind conditions. Plan to dedicate a few hours to this one — NASA asks that you include observations from 1-2 hours before and after the eclipse in addition to what you’ll record during. “You will measure temperature every 5-10 minutes and clouds every 15-30 minutes or whenever you see change,” NASA says.

You can keep using the Globe Observer app for citizen science beyond eclipse day, too. There are programs running all year round for recording observations of things like clouds, land use, mosquito habitats and tree heights. The eclipse tool, though, is only available when there’s an eclipse happening.

Listen to the sounds of wildlife

Observations going back nearly 100 years have added support to the idea that total solar eclipses temporarily throw some animals out of whack. Inspired by a 1935 study that gathered observations on animal behavior during an eclipse three years prior, the Eclipse Soundscapes Project (https://eclipsesoundscapes.org/) is inviting members of the public to take note of what they hear before, during and after totality, and share their findings.

To be an Observer (https://eclipsesoundscapes.org/observer/#training) for the project, it’s recommended that you first sign up on the website and go through the brief training materials so you can get a sense of what type of information the project is looking for. The website also has printable field notes pages you can use to record your observations on eclipse day. You should start taking notes down at least 10 minutes before totality. Only after the eclipse is over will you need to fill out the webform to submit your observations along with your latitude and longitude.

If you happen to have an AudioMoth acoustic monitoring device and a spare microSD card lying around, you can go a step further and record the actual sounds of the environment during the eclipse as a Data Collector (https://eclipsesoundscapes.org/data-collector-page/#kit). You’ll need to set everything up early — the project says to do it on Saturday, April 6 before noon — and let it record until at least 5PM local time on April 10. At that point, you can turn it off, submit your notes online and mail in the SD card. All of the details for submission can be found on the project’s website.

NASA

Take photos of the solar corona

The Eclipse Megamovie 2024 (https://eclipsemegamovie.org/) is an initiative designed to study the sun’s corona and plasma plumes from locations in the path of totality, building off of a previous campaign from the 2017 total solar eclipse. It’s already selected a team of 100 Science Team Alpha Recruits (STARs) who underwent training and were given 3D-printed tracking mounts for their cameras to shoot the best possible images. But, the project will still be accepting photo submissions from any enthusiasts who have a DSLR (and a solar filter) and want to participate.

The Photography Guide (https://drive.google.com/file/d/1HX2ZU0ZA_XemxvA7-lyiY8VndEOalXcH/view) is pretty exhaustive, so don’t wait until eclipse day to start figuring out your setup. You’ll be able to submit your photos after the eclipse through a form on the website.

However you choose to spend the eclipse, whether you’re collecting data for a citizen science mission or just planning to kick back and observe, make sure you have everything in place well ahead of the time. While the partial eclipse phases will last over an hour, totality will be over and done in about 3.5-4.5 minutes depending on where you’re watching from. You wouldn’t want to miss out on some of that time because you were fumbling with your camera.

Totality will start shortly after 11AM local time (2PM ET) for western Mexico, moving northeastward over the subsequent two-or-so hours before exiting land near Newfoundland, Canada around 5:30PM local time. There will still be something to see for people outside the path of totality, too. Most of the US will be treated to a partial eclipse that day. You can find out exactly when the eclipse will be visible from your location with this tool on NASA’s website (https://eclipse-explorer.smce.nasa.gov/), along with the percentage of sun coverage you can expect to witness.

This article originally appeared on Engadget at https://www.engadget.com/nasa-will-be-studying-the-total-solar-eclipse-heres-how-you-can-help-140011076.html?src=rss

https://www.engadget.com/nasa-will-be-studying-the-total-solar-eclipse-heres-how-you-can-help-140011076.html?src=rss

@ 947c8c3e:22e2d6ea

Bitcoin, emerging as the most decentralized and scarce currency, stands as the epitome of financial revolution in the digital age. It embodies the principles of autonomy, security, and innovation, paving the way for a new era of economic empowerment. This exploration delves into the fundamentals of Bitcoin, the pioneering innovation of the Lightning Network, and the unparalleled privacy and offline capabilities of eCash, illustrating the transformative power of these technologies in fostering a resilient and decentralized financial landscape.

Bitcoin for Individuals: Empowerment at Your Fingertips

Bitcoin revolutionizes the way we think about money, offering a secure, low-cost method for transactions. It simplifies mobile payments, allowing for effortless scan-and-pay transactions without the need for traditional banking hurdles. The security model of Bitcoin, underpinned by mathematical certainty and proof of work (PoW), provides unparalleled control and protection over your funds, ensuring that your transactions remain immutable and resistant to fraud.

The Universality of Bitcoin

Bitcoin operates on a global scale, unfettered by geographical boundaries or time zones. Its decentralized nature ensures that it is always operational, allowing for instantaneous international payments without the restrictions imposed by traditional financial institutions. This universality empowers users to transact with anyone, anywhere, at any time, with the freedom to set their own transaction fees.

Privacy and Anonymity

Bitcoin also champions financial privacy. Unlike conventional payment methods that are prone to security breaches, Bitcoin transactions do not reveal sensitive personal information. This feature, coupled with the potential for anonymity similar to physical cash transactions should you choose to do so, places a strong emphasis on user privacy, allowing individuals to transact securely and discreetly.

Lightning Network: The Path to Scalable Bitcoin Transactions

The Lightning Network represents a monumental stride towards the scalability of Bitcoin transactions. By facilitating instant, low-cost payments, the Lightning Network addresses the inherent limitations of blockchain confirmations, thereby enabling a vast throughput of transactions per second. This innovation not only enhances the efficiency of Bitcoin transactions but also opens up new avenues for microtransactions and cross-chain interactions without compromising on security or decentralization.

Payment Channel and Off-Chain Scalability

At its core, the Lightning Network leverages smart contracts called a multi-signature payment channel to conduct transactions off-chain, significantly reducing the burden on the Bitcoin blockchain. This approach ensures that transactions are both rapid and cost-effective, fostering a more dynamic and inclusive financial ecosystem.

Cashu: Reinventing Privacy for Bitcoin

One of the Lightning Networks disadvantages is that both parties need to be online to receive funds. Utilizing a Chaumian ecash system built specifically for Bitcoin and Lightning Network, Cashu emerges as a great solution to this issue, with its potential for partial offline transactions and near instant payments.

This system also ensures near-perfect anonymity for users, making it virtually impossible to trace transactions back to their participants. By integrating closely with the Lightning Network, eCash facilitates private, instant transactions, further solidifying Bitcoin's position as a leader in secure and decentralized financial transactions.

The Future of Bitcoin and Beyond

The synergy between Bitcoin, the Lightning Network, and eCash heralds a new era of financial sovereignty. These technologies collectively represent the cornerstone of a decentralized financial system, one that prioritizes privacy, security, and user autonomy. As we venture further into this digital frontier, Bitcoin continues to lead the charge, challenging the traditional paradigms of money and empowering individuals with the tools for true economic freedom.

In conclusion, the essence of Bitcoin and its complementary technologies lies in their ability to redefine our relationship with money. By championing decentralization, scarcity, and innovation, Bitcoin not only promises a future of financial autonomy but also invites us to partake in the ongoing evolution of digital prosperity.

@ 044b20cf:89e58620

Engadget Podcast: Why pay $10 a month to get away from Google search?

Google has gone from being the go-to search engine to something people are paying to avoid entirely. This week, Cherlynn and Devindra chat with 404 Media (https://www.404media.co/) co-founder Jason Koebler (https://twitter.com/jason_koebler?ref_src=twsrc%5Egoogle%7Ctwcamp%5Eserp%7Ctwgr%5Eauthor) about his experience moving away from Google and towards Kagi (https://www.404media.co/friendship-ended-with-google-now-kagi-is-my-best-friend/), a $10 a month search engine without ads or data tracking. Funny enough, Kagi is still relying on Google’s index, so it’s a lot like using that site before the onslaught of ads, sponsored posts and AI results. Also, we discuss the company’s lies around Chrome’s incognito mode, as well as the news that it would be deleting user data collected in that mode. (Be sure to check out the 404 Media podcast (https://www.404media.co/the-404-media-podcast/) too!)

---

Listen below or subscribe on your podcast app of choice. If you've got suggestions or topics you'd like covered on the show, be sure to email us (mailto:podcast@engadget.com?subject=Engadget%20Podcast%20Feedback) or drop a note in the comments! And be sure to check out our other podcast, Engadget News (https://www.engadget.com/2019-08-01-engadget-podcasts.html)!

Topics

• Why Jason Koebler moved from Google to Kagi's paid search engine – 0:45

• Google says it will destroy data collected from users using Incognito mode – 15:01

• Gurman report: Apple is working on personal home robots – 24:55

• Amazon just walked out on its self check-out tech – 30:43

• FCC set to vote to restore Net Neutrality – 43:00

• Apple adds Spatial Personas to make the Vision Pro experience less lonely – 45:09

• Proposed California state law would give tech workers the “right to disconnect” – 47:17

• Tekken director responds to fighting game fans’ request for a Waffle House stage – 49:57

• Around Engadget – 51:22

• Working on – 54:31

• Pop culture picks – 59:13

Subscribe!

• iTunes (https://shopping.yahoo.com/rdlw?siteId=us-engadget&pageId=1p-autolink&featureId=text-link&custData=eyJzb3VyY2VOYW1lIjoiV2ViLURlc2t0b3AtVmVyaXpvbiIsImxhbmRpbmdVcmwiOiJodHRwczovL2l0dW5lcy5hcHBsZS5jb20vdXMvcG9kY2FzdC90aGUtZW5nYWRnZXQtcG9kY2FzdC9pZDExNDI3OTA1MzA_bXQ9MiIsImNvbnRlbnRVdWlkIjoiNWUyMDMzNjEtZGQxMS00ODkwLWIxOTMtNGMwNmQ2MzI2MzU4In0&signature=AQAAAceZBn2I9QmWb1qCB9zGEf2ZqV_9Wr3aEp9zxpQw4pmY&gcReferrer=https%3A%2F%2Fitunes.apple.com%2Fus%2Fpodcast%2Fthe-engadget-podcast%2Fid1142790530%3Fmt%3D2)

• Spotify (https://shopping.yahoo.com/rdlw?siteId=us-engadget&pageId=1p-autolink&featureId=text-link&custData=eyJzb3VyY2VOYW1lIjoiV2ViLURlc2t0b3AtVmVyaXpvbiIsImxhbmRpbmdVcmwiOiJodHRwczovL29wZW4uc3BvdGlmeS5jb20vc2hvdy8zRUMzZE1JUkI5OWRrdm9TQmVTTzdHP3NpPWY3VUFMR0ttUkRXdE9yVThaNC11aVEiLCJjb250ZW50VXVpZCI6IjVlMjAzMzYxLWRkMTEtNDg5MC1iMTkzLTRjMDZkNjMyNjM1OCJ9&signature=AQAAAcb0Troo5AWdzur6W4Qm50rLcEckVQkHqSgT0PA6Tp_-&gcReferrer=https%3A%2F%2Fopen.spotify.com%2Fshow%2F3EC3dMIRB99dkvoSBeSO7G%3Fsi%3Df7UALGKmRDWtOrU8Z4-uiQ)

• Pocket Casts (http://pca.st/mlY3)

• Stitcher (http://www.stitcher.com/podcast/engadget/the-engadget-podcast)

• Google Podcasts (https://podcasts.google.com/?feed=aHR0cDovL2ZlZWRzLnNvdW5kY2xvdWQuY29tL3VzZXJzL3NvdW5kY2xvdWQ6dXNlcnM6MjQ1MjIwOTU4L3NvdW5kcy5yc3M&ep=14)

Credits

Hosts: Cherlynn Low and Devindra Hardawar

Guest:Jason Koebler (https://twitter.com/jason_koebler?ref_src=twsrc%5Egoogle%7Ctwcamp%5Eserp%7Ctwgr%5Eauthor)

Producer: Ben Ellman

Music: Dale North and Terrence O'Brien

This article originally appeared on Engadget at https://www.engadget.com/engadget-podcast-google-search-kagi-incognito-123049753.html?src=rss

https://www.engadget.com/engadget-podcast-google-search-kagi-incognito-123049753.html?src=rss

@ 664e070f:51cdb7aa

www.orangepillapp.com is a Bitcoin-only social network that lets you find local Bitcoiners, events, and merchants.

I look forward to engaging with all of you! 🤙

@ 044b20cf:89e58620

YouTube CEO warns OpenAI that training models on its videos is against the rules

AI models using individual's work without permission (or compensation) is nothing new, with entities like The New York Times (https://www.engadget.com/the-new-york-times-is-suing-openai-and-microsoft-for-copyright-infringement-181212615.html) and Getty Images (https://www.engadget.com/getty-images-sues-the-maker-of-ai-art-generator-stable-diffusion-over-data-scraping-allegations-184502897.html) initiating lawsuits against AI creators alongside artists and writers. In March, OpenAI CTO Mira Murati contributed to the ongoing uncertainty, telling The Wall Street Journal (https://www.wsj.com/tech/personal-tech/openai-cto-sora-generative-video-interview-b66320bb) she wasn't sure if Sora (https://www.engadget.com/openais-new-sora-model-can-generate-minute-long-videos-from-text-prompts-195717694.html), the company's new text-to-video AI tool, takes data from YouTube, Instagram or Facebook posts. Now, YouTube's CEO Neal Mohan has responded with a clear warning to OpenAI that using its videos to teach Sora would be a "clear violation" of the platform's terms of use.

In an interview with Bloomberg Originals (https://www.bloomberg.com/news/articles/2024-04-04/youtube-says-openai-training-sora-with-its-videos-would-break-the-rules?sref=10lNAhZ9&embedded-checkout=true) host Emily Chang, Mohan stated, "From a creator's perspective, when a creator uploads their hard work to our platform, they have certain expectations. One of those expectations is that the terms of service is going to be abided by. It does not allow for things like transcripts or video bits to be downloaded, and that is a clear violation of our terms of service. Those are the rules of the road in terms of content on our platform."

A lot of uncertainty and controversy still surrounds how OpenAI trains Sora, along with ChatGPT and DALL-E (https://www.engadget.com/chatgpt-will-digitally-tag-images-generated-by-dall-e-3-to-help-battle-misinformation-102514822.html), with The Wall Street Journal (https://www.wsj.com/tech/ai/ai-training-data-synthetic-openai-anthropic-9230f8d8) recently reporting the company plans to use YouTube video transcriptions to train GPT-5. On the other hand, OpenAI competitor Google is apparently respecting the rules — at least when it comes to YouTube (which it owns). Google's AI model Gemini (https://www.engadget.com/googles-gemini-15-pro-is-a-new-more-efficient-ai-model-181909354.html) requires similar data to learn but Mohan claims it only uses certain videos, depending on permissions are given in each creator's licensing contract.

This article originally appeared on Engadget at https://www.engadget.com/youtube-ceo-warns-openai-that-training-models-on-its-videos-is-against-the-rules-121547513.html?src=rss

https://www.engadget.com/youtube-ceo-warns-openai-that-training-models-on-its-videos-is-against-the-rules-121547513.html?src=rss

@ 75bf2353:e1bfa895

https://i.nostr.build/# Orange Pilling Merchants

On the Freedom Foot Print show, Brian DeMint said he’s friend’s with a coffee shop owner in Riverside, California--The place where I host my bi-monthly bitcoin meetup. For the last 12,960 blocks or so, I've held a plebwalk on the first Saturday of each month. This plebwalk has been a solo-trek each time. More people are interested in going to meetups where we sit down and drink drugs like beer, soda, or coffee. Therefore, I have decided to cancel my Pleb Walk and move the meetup to Arcade Coffee Bakehouse the coffee shop mentioned on my favorite bitcoin author's podcast. Not to brag, but I bought an autographed copy of Sovereignty Through Mathematics with bitcoin from Knut Svanholm about 8,000 blocks ago. Just kidding, I am trying to brag.

Plebwalks did not attract as many plebs as I had hoped. I suspect I might spark more interest if we went to a coffee house that accepted bitcoin. Arcade Coffee-The Bakehouse in Riverside California does not accept bitcoin yet but I hope to change that. Some of my first blogs were about me going to the Riverside Farmer's Market to ask people if they accept bitcoin. About one-in-a-hundred said yes. This taught me an important lesson. That shit doesn't work. Rather than go home and cry in my coffee, what if I try a different approach?

The main problem is social proof. People are social animals. They look to others to see what they should or should not do. My dad handed me green paper to buy ice-cream from a dude with a mustache selling sugar to kids out of a van. That's the paradigm of money for most people. That's what everyone used for money before we became a nation of credit card debtors. We don't pay people anymore. We pay debt off to banks. Should I buy a Mercedes, or a whole Bitcoin? If you're reading this, you are more likely to drive an old Toyota, but most people will buy a Mercedes because suits like to pick their nose in cars made by Mercedes-Benz, or the richest man in the world. They think, I should buy a Mercedes-Benz so I can pick my nose like the rest of the successful people. Picking my nose in a Tesla is the ultimate status symbol. You need to have a great job and a great debt score to pick your nose in a Tesla.

Bitcoin was declared dead more times than I could give a fuck to count, but you know what really died? Cash. According to Dave Ramsey, "Cash is King." I'm sorry to be the bearer of bad news Mr. Ramsey, but your king is dead. Almost nobody uses paper cash, let alone p2p cash. "This bill is legal tender and must be accepted for all debts both public and private." . Well...that's just about all you pay with it, debt. Cash not accepted at many places these days. I guess the legal tender mumbo-jumbo means your credit card must accept cash to pay off your debt. Besides you'll get "cash back" if you use your credit card. That's not cash. It's more like Weekend At Bernie's Cash. It's social engineering which created social proof that teaches everyone should pay with a credit card, not cash. Guess what fixes this. That's only used by drug dealers, and people who dry-clean money or whatever laundering it means.

It would be nice to pay for my coffee with bitcoin rather than pay credit card with bitcoin. To do this, I can't just be the one caffeine-crazed junkie, hopped up on orange pills, asking the poor barista, "Do you accept our lord and savior, bitcoin?" But what if ten people asked to pay for coffee with bitcoin? What if 21 people asked to pay for their coffee in bitcoin? 50? By the way, tell the credit card companies to go fuck themselves by shoving their fees up their ass. "Gradually...then suddenly," is a better catch phrase, but Parker Lewis already coined it and I digress. If I can bring enough customers, we will have social proof for p2p e-cash. That's the hard part, but we have to start somewhere.

How Businesses Can Accept Bitcoin.

People have been thinking about on-boarding businesses to accept payments for over a decade. NVK says that’s how Coinkite started, but the demand wasn’t there. It’s still not there. We need to create it. Strike has a Clover integration that works like this.

https://www.youtube.com/watch?v=yM4qfrywTew

Maybe you don’t want to spend your bitcoin because of the taxes or maybe the coffee house owner is a no-coiner. So what? Resist the urge to say “have fun staying poor.” Tell them the bitcoin can auto-magically convert to Trump’s favorite fiat currency.

strike Strike can’t pour a lot of resources into getting businesses to accept bitcoin as a payment when there’s no demand, but they have given us the tools to do it. Brian Tracy said, "if it’s to be, it’s up to me." He's right. Making bitcoin peer-to-peer cash is up to me and up to you. Some meetups have already integrated payments at their meetups. It's one of the best ways to grow bitcoin as peer 2 peer electronic cash. Many of the people who have signed up for my meetup are not aware of the lightning network. Some of them think video on a blockchain is the next way to pick their nose in a Lambo on the moon. They like “BTC” too. I say why video game on a blockchain NGMI and show them the lightning network.

After I give my spiel, I say, "so show me how this video game on a blockchain works." I might as well ask them to unify the theory of gravity. They don't know what a blockchain is.

"Wallet, you mean like my Coinbase wallet?"

Coinbase is good at marketing. They convinced the ETF's to let Coinbase HODL their bitcoin. They don't know how to accept payments. They think lightning addresses are for email. They sell SHIBullshit and send nasty letters to people playing online poker. Bitcoin doesn't fix this. We fix this, but I need some help. Like I said, it won't work if it's just me.

Note: I called the coffee house mentioned on the podcast. They have another location that does use clover down the road, but they use Square at the location the author from the Freedom Footprint show likes to frequent. Thank Zeus we can use Square anyway.

₿logging₿itcoin 830,051 Debt Clock NGU

🧡Support this blog by using the [Value] 4 Value model](https://value4value.info/). ⚡Zap Me

🍐Join my Keet Room 🛒Shop my Nostr Store 🛒Shop The Elliptic Curve Economy

Book Bitcoin Coaching

Note: Pablo asked me to set up tiers on highlighter.com, so I did. I am also interested in FOSS AI and decided to use elevenlabs to create audio-versions of my blog after listening to this episode of AI U unchained I highly encourage you to listen to this episode even though it's not technically a bitcoin podcast--I think it is. The idea is to create a podcast feed for subscribers, but I don't have all the details worked out yet so I put this first audio recording on Spotify.

https://open.spotify.com/episode/271nHQEPxvqxVSSXHsbZM1?si=IocbUhgxTJSbBGi8oQaxGwnznq.jpg

@ 044b20cf:89e58620

Roku looks into serving you ads on whatever you plug into its TVs

Roku already serves ads (https://www.engadget.com/roku-shoppable-ads-walmart-113552825.html) through its platform, but it's also apparently exploring the idea of showing you ads while you're using third-party devices connected to its TVs. Based on a recent patent filing (https://patents.google.com/patent/US20230388589A1/en) unearthed by Lowpass (https://www.lowpass.cc/p/roku-hdmi-ad-insertion-patent), the company is looking to develop a system or a method "for ad insertion by a display device coupled to a media device via a high-definition media interface (HDMI) connection." That means if you've connected another streaming device or console — say, an Apple TV, a Chromecast or a PlayStation — to a Roku TV via HDMI, the company would still be able to serve you advertisements.

In particular, Roku is hoping to show you commercials while whatever you're watching or playing on the third-party device attached to it is on pause. In its patent, it described several methods on how it can detect whether the show or game on screen is paused, such as receiving a pause signal from the remote control, detecting a pause icon, looking at several video frames and determining that the image on screen hasn't changed for some time and getting a silent audio signal from the HDMI connection.

If it works as intended, those ads wouldn't impact your viewing or playing experience ( much), assuming you're truly stepping away or doing something else in the meantime. While you'd probably prefer those experiences to be free of ads altogether, Roku is at least looking to make sure that it's serving you relevant ads. It could analyze frozen video or audio frames and use automatic content recognition (ACR) technology to identify what's on screen. Or it could analyze metadata to show ads connected to what you're playing or watching. It could also serve commercials based on what third-party device is attached to your TV.

As Lowpass notes, the company could have conjured the idea because manufacturers typically don't make a lot of money from hardware sales. For the fiscal year of 2023, Roku lost $44 million on smart TVs. Similarly, Samsung's visual display and digital appliances division posted $37.5 million in operating losses (https://www.engadget.com/samsungs-annual-profits-continued-to-decline-in-2023-090500640.html) for last year's fourth quarter. Meanwhile, ads and services generated $1.6 billion in profit for Roku. This idea could potentially make it more money... if the prospect of watching commercials while your show or game is paused doesn't turn you off buying Roku TV, of course. This is just a patent at this point in time, though, and Roku may very well end up scrapping it and not implementing it at all.

This article originally appeared on Engadget at https://www.engadget.com/roku-looks-into-serving-you-ads-on-whatever-you-plug-into-its-tvs-120016754.html?src=rss

https://www.engadget.com/roku-looks-into-serving-you-ads-on-whatever-you-plug-into-its-tvs-120016754.html?src=rss

@ 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!

@ 044b20cf:89e58620

The Morning After: 80 percent of global carbon dioxide emissions comes from just 57 companies

A new Carbon Majors Database report, which examines carbon dioxide emissions, found that just 57 companies were responsible for 80 percent of the global carbon dioxide emissions (https://www.engadget.com/only-57-companies-produced-80-percent-of-global-carbon-dioxide-130752291.html) between 2016 and 2022. ExxonMobil, which topped the list of United States companies, contributed 1.4 percent of all global carbon dioxide emissions. It has net zero emissions targets.

Nearly 200 parties adopted the 2015 Paris Agreement, committing to reduce greenhouse gas emissions. However, 58 of the 100 state- and investor-owned companies in the Carbon Majors Database have since increased their production.

The International Energy Agency found coal consumption increased by eight percent over the seven years to 8.3 billion tons — a record high. State-owned Coal India is one of the top three carbon dioxide producers. Russia’s state-owned energy company Gazprom and state-owned oil firm Saudi Aramco rounded out the group.

— Mat Smith

The biggest stories you might have missed

X is giving blue checks to people with more than 2,500 Premium followers (https://www.engadget.com/x-is-giving-blue-checks-to-people-with-more-than-2500-premium-followers-090922311.html)

Hatsune Miku in Crypt of the Necrodancer feels like the perfect crossover (https://www.engadget.com/hatsune-miku-in-crypt-of-the-necrodancer-feels-like-the-perfect-crossover-203138973.html)

The best multi-device wireless charging pads for 2024 (https://www.engadget.com/best-multi-device-wireless-charging-pads-120557582.html)

​​ You can get these reports delivered daily direct to your inbox.__Subscribe right here! (https://www.engadget.com/about/newsletter/)

The chaos of YouTube’s multicam Coachella stream (https://www.engadget.com/who-exactly-is-youtubes-multicam-coachella-stream-for-183744741.html)When you apply sports logic to a music festival.\ \ YouTube (https://www.engadget.com/who-exactly-is-youtubes-multicam-coachella-stream-for-183744741.html)

YouTube is hyping its exclusive Coachella streaming coverage, which starts next week. The headlining feature is the platform’s multiview experience (already familiar to sports fans) — but who wants to watch up to four stages simultaneously, with audio for one of them. It’s… a music festival. Coachella runs from April 12 to 14 and April 19 to 21.

Continue reading. (https://www.engadget.com/who-exactly-is-youtubes-multicam-coachella-stream-for-183744741.html)

The latest Razer Blade 18 is now available to order (https://www.engadget.com/the-latest-razer-blade-18-is-now-available-to-order-180330999.html)If you want 4K 200Hz display, you’ll need an extra $1,700 and a bit of time.\ \ Razer (https://www.engadget.com/the-latest-razer-blade-18-is-now-available-to-order-180330999.html)

Finally, after a reveal at CES, the 2024 edition of the Razor Blade 18 arrives for $3,099. The base system has an i9-14900HX processor, 32GB of RAM, 1TB of SSD storage, Wi-Fi 7, a triple-fan cooling system and a six-speaker array with THX spatial audio support. You can equip the laptop with up to an NVIDIA GeForce RTX 4090 (the base model has a 4070 graphics card). In what Razer claims is a first for a laptop, there’s Thunderbolt 5 connectivity, but only if you opt for a 4080 or 4090 GPU.

Continue reading. (https://www.engadget.com/the-latest-razer-blade-18-is-now-available-to-order-180330999.html)

Apple cuts over 700 jobs as it closes car and display projects (https://www.engadget.com/apple-cuts-over-700-jobs-following-its-car-and-display-project-closures-061524777.html)Eight offices in Santa Clara, California were affected by the layoffs.

Over 700 people at Apple have recently lost their jobs, mostly from offices in Santa Clara. The location that dealt with the company’s electric vehicle projects has lost 371 people. There may not be enough space at thatnew home robot project. (https://www.engadget.com/apple-is-developing-personal-robots-for-your-home-bloomberg-says-044254029.html)

Continue reading. (https://www.engadget.com/apple-cuts-over-700-jobs-following-its-car-and-display-project-closures-061524777.html)

This article originally appeared on Engadget at https://www.engadget.com/the-morning-after-80-percent-of-global-carbon-dioxide-emissions-comes-from-just-57-companies-111514748.html?src=rss

https://www.engadget.com/the-morning-after-80-percent-of-global-carbon-dioxide-emissions-comes-from-just-57-companies-111514748.html?src=rss

@ 1e52c554:21771908

Posthumous work of the Colombian poet born in Don Matias on January 20, 1948.

Welcome to this blog dedicated to the Posthumous work of the Colombian poet Francisco Luis Arroyave Tabares (my father), born in Don Matias on January 20, 1948-2010. Where I will be publishing each of the 175 sonnets from his unpublished collection 'Sonnets For The Twenty-First Century And A Circadian Musical (1984-1987).' Analyzed with GPT4 artificial intelligence and illustrated with AI tools... I hope you enjoy this garden of words snatched from the solitude of a locked room.

Likewise, any enthusiast of the sonnet form is invited to conduct their personal studies of Arroyave Tabares' work, as it is a collection that, although registered since 1989, has not yet been published.

Frank Duna

---

Analysis "Thinking Of Love"

Introduction

This sonnet beautifully captures the essence of love - its transformative power, its ability to bring hope and joy, and its potential to fulfill dreams.

Thematic Analysis

In the octave, the speaker expresses the transformative power of love, describing how the arrival of the beloved has brought joy and light into their life. The octave uses vivid imagery to convey the depth of the speaker’s feelings, such as “One thousand or more worlds behind my mind / Since you arrived have been happily born”. The octave ends with a sense of unity and understanding between the lovers, despite the darkness that surrounds them.

The sestet shifts the focus to the physical and intimate aspects of their relationship. The speaker describes the act of kissing the beloved’s lips and reading in silence what they have done, suggesting a deep connection and understanding between them. The sestet ends with a sense of completeness and a hint of transience, acknowledging that their beautiful dreams may one day come to an end.

Overall, the sonnet explores the themes of love, unity, intimacy, and transience, using rich imagery and emotional language to convey the depth and complexity of these feelings. The structure of the sonnet, with its division into an octave and a sestet, allows the poet to explore different aspects of these themes and to create a sense of progression and development in the speaker’s reflections on love.

Rhyme Scheme

The sonnet “Thinking Of Love” by Francisco Luis Arroyave Tabares follows the rhyme scheme ABBA ABBA CDC DCD. Let’s break it down:

The octave (the first eight lines) has the rhyme scheme ABBA ABBA:

A: One thousand or more worlds behind my mind B: Since you arrived have been happily born B: With cheer our souls have killed all drear and scorn A: And night sings with lights of many a kind. A: This eve, thinking of love, our thoughts we bind B: And our hearts have accepted our return B: After the many things that we have sworn A: And since, even at dark, our eyes we find.

The sestet (the last six lines) has the rhyme scheme CDC DCD:

C: I slowly kiss your lips to see you smile D: As I read in silence what you have done C: And almost smell your blood that has no guile. D: While we feel complete and no more lone C: Beautiful dreans have been by for a while D: In one of them, for sure, we will be gone.

This rhyme scheme is a variation of the Petrarchan sonnet form, which typically follows the ABBA ABBA CDE CDE rhyme scheme. The variation in the sestet’s rhyme scheme allows for a more complex exploration of the poem’s themes and adds a unique rhythm and flow to the poem. It also creates a sense of progression and development in the speaker’s reflections on love. The change in rhyme scheme from the octave to the sestet often signals a shift in theme or tone, which is evident in this sonnet. The octave focuses on the transformative power of love, while the sestet explores the physical and intimate aspects of their relationship. The rhyme scheme helps to highlight these shifts and adds depth and complexity to the poem.

Additional Aspects

Let’s delve deeper into the analysis of “Thinking Of Love” by Francisco Luis Arroyave Tabares:

Language and Imagery: The language used in the sonnet is rich and evocative, creating vivid images that engage the senses. For instance, “One thousand or more worlds behind my mind / Since you arrived have been happily born” uses cosmic imagery to convey the transformative power of love. Similarly, “And night sings with lights of many a kind” uses auditory and visual imagery to depict a scene of joy and brightness. The language is also deeply emotional, reflecting the speaker’s profound feelings for the beloved.

Themes: The sonnet explores several themes, including love, unity, intimacy, and transience. Love is depicted as a powerful and transformative force that brings joy, light, and understanding. The theme of unity is expressed through the speaker’s sense of connection and intimacy with the beloved, while the theme of transience is hinted at in the final lines of the sestet, acknowledging the fleeting nature of their beautiful dreams.

Meter: The sonnet appears to follow the iambic pentameter, which is the most common meter in English poetry and is often used in sonnets. This means each line consists of five metrical feet, each foot being made up of two syllables, the first unstressed and the second stressed. This creates a rhythmic pattern that adds a musical quality to the poem.

Overall: The sonnet is a beautiful exploration of love and its various facets. The use of rich language and vivid imagery enhances the emotional depth of the poem, while the themes of love, unity, intimacy, and transience add layers of meaning. The structure of the sonnet, with its division into an octave and a sestet, allows the poet to explore different aspects of these themes and to create a sense of progression and development in the speaker’s reflections on love. The meter adds a rhythmic and musical quality to the poem, enhancing its aesthetic appeal. Overall, the sonnet is a powerful and moving expression of love and its transformative power.

(GPT4)

---

Syllable count for each line.

``` Thinking Of Love

10 One thousand or more worlds behind my mind 10 Since you arrived have been happily born 10 With cheer our souls have killed all drear and scorn 10 And night sings with lights of many a kind.

10 This eve, thinking of love, our thoughts we bind 10 And our hearts have accepted our return 10 After the many things that we have sworn 10 And since, even at dark, our eyes we find.

10 I slowly kiss your lips to see you smile 10 As I read in silence what you have done 10 And almost smell your blood that has no guile. 9 While we feel complete and no more lone 10 Beautiful dreans have been by for a while 10 In one of them, for sure, we will be gone. *** ```

---

Sonnets For The Twenty First Century And A Circadian Musical Written By Francisco Luis Arroyave Tabares (1984-1987)

---

Analyzed by GPT4; Image by leonardo.ai First published on Nostr Protocol by franciscoarroyavet@nostrplebs.com Thinking Of Love

@ f72e682e:c51af867

Spaniards already dedicate more than 75% of their salary to taxes: Indirect taxes, the 69 tax increases this year, and 50% of the salary for social security make Spaniards the people in Europe whose tax pressure has increased the most since 2019. Tax experts already talk about “modern tax slavery”. The video in the link is in Spanish but I believe you may be able to translate the subtitles. A psychologist analyze this new modern version of slavery.

(ES) Los españoles dedican ya más del 75% de su sueldo a impuestos: Los impuestos indirectos, las 69 subidas del fisco, y el 50% del sueldo para cotizaciones y varios hacen de los españoles el pueblo de europa al que más suben la presión fiscal desde 2019. Expertos fiscales hablan ya de “esclavismo fiscal moderno”

https://www.youtube.com/watch?v=63zP9XlLg4k

@ 1e52c554:21771908

Posthumous work of the Colombian poet born in Don Matias on January 20, 1948.

Welcome to this blog dedicated to the Posthumous work of the Colombian poet Francisco Luis Arroyave Tabares (my father), born in Don Matias on January 20, 1948-2010. Where I will be publishing each of the 175 sonnets from his unpublished collection 'Sonnets For The Twenty-First Century And A Circadian Musical (1984-1987).' Analyzed with GPT4 artificial intelligence and illustrated with AI tools... I hope you enjoy this garden of words snatched from the solitude of a locked room.

Likewise, any enthusiast of the sonnet form is invited to conduct their personal studies of Arroyave Tabares' work, as it is a collection that, although registered since 1989, has not yet been published.

Frank Duna

---

Analysis "More Than Welcome"

Introduction

“More Than Welcome” by Francisco Luis Arroyave Tabares is a beautiful sonnet that explores themes of love, longing, and the passage of time.

Thematic Analysis

In the octave, the speaker invites the addressee to stay with him, expressing a deep emotional connection. The speaker reflects on their shared past, their hopes, and the growth they’ve experienced together. The octave ends with a powerful image of their worlds joined by a shared love.

The sestet shifts the focus to the present and future. The speaker expresses gratitude for the care shown by the addressee and the hope it has instilled in him. The speaker then invites the addressee to explore the depths of his solitude and to fill the silence with their presence.

Overall, the sonnet explores themes of love, longing, and the passage of time. It beautifully captures the depth of the speaker’s emotions and the profound impact of the addressee on his life. The use of natural imagery (gardens, fruits, harvest) adds a layer of richness to the poem, symbolizing growth, change, and renewal. The sonnet ends on a note of hope and anticipation, leaving the reader with a sense of longing and expectation.

Rhyme Scheme

The rhyme scheme ABBA ABBA CDE CDE, is a common one for sonnets, particularly those in the Petrarchan or Italian style.

In this sonnet “More Than Welcome” by Francisco Luis Arroyave Tabares, let’s analyze the rhyme scheme:

Octave:

My dear, please come and stay beyond my need (A) Since our oaths have grown and flowers no blink (B) In gardens where you used to sit and think (B) About how futures would your children feed. (A) Witness the ripening of fruits from seed (A) That in the depth of night we felt once sink (B) And became in our mind a well known link (B) To join our worlds that pined a same love deed. (A)

Sestet:

The harvest of your care after the bloom (C) Has risen in my valleys a new hope, (D) Be more than welcome to my silent kiss. (E) You can search the skies from my empty room (C) To chase those solitudes so hard to cope (D) And fill up voices that your name still miss. (E)

As you can see, the sonnet follows the ABBA ABBA CDE CDE rhyme scheme perfectly. This structure allows for a clear thematic shift between the octave and the sestet, which is a characteristic feature of Petrarchan sonnets. The rhyme scheme also adds a musical quality to the poem, enhancing its emotional impact.

Additional Aspects

Let’s delve deeper into the sonnet’s use of language, imagery, themes, meter, and overall impact.

Language and Imagery: The language used in the sonnet is rich and evocative, with a strong emphasis on natural imagery. The poet uses images of gardens, fruits, seeds, and harvest to symbolize the growth and development of their relationship. These images create a vivid picture in the reader’s mind and add depth to the emotional content of the poem.

Themes: The main themes of the sonnet are love, longing, and the passage of time. The speaker expresses a deep emotional connection with the addressee and invites them to stay. The speaker reflects on their shared past, their hopes, and the growth they’ve experienced together. The sonnet ends on a note of hope and anticipation, leaving the reader with a sense of longing and expectation.

Meter: The sonnet appears to be written in iambic pentameter, which is a common meter for sonnets. In iambic pentameter, each line consists of five iambs - pairs of syllables where the first syllable is unstressed and the second is stressed. This gives the poem a rhythmic quality and enhances its musicality.

Overall: The sonnet is a beautiful exploration of love and longing. The use of natural imagery adds a layer of richness to the poem, symbolizing growth, change, and renewal. The sonnet is well-structured, adhering to the traditional sonnet form, and the language is evocative and emotive. The sonnet leaves a lasting impression on the reader, evoking a sense of deep emotion and longing.

(GPT4)

---

Syllable count for each line.

``` More Than Welcome

10 My dear, please come and stay beyond my need 10 Since our oaths have grown and flowers no blink 10 In gardens where you used to sit and think 10 About how futures would your children feed.

10 Vitness the ripening of fruits from seed 10 That in the depth of night we felt once sink 10 And became in our mind a well known link 10 To join our worlds that pined a same love deed.

10 The harvest of your care after the bloom 10 Has risen in my valleys a new hope, 10 Be more than welcome to my silent kiss. 10 You can search the skies from my empty room 10 To chase those solitudes so hard to cope 10 And fill up voices that your name still miss. *** ```

---

Sonnets For The Twenty First Century And A Circadian Musical Written By Francisco Luis Arroyave Tabares (1984-1987)

---

Analyzed by GPT4; Image by leonardo.ai; First published on Nostr Protocol by franciscoarroyavet@nostrplebs.com More Than Welcome

@ 044b20cf:89e58620

Disney+ is also cracking down on password sharing

Say goodbye to your best friend's neighbor's great aunt's Disney+ account. Disney CEO Bob Iger said in an interview with CNBC (https://www.youtube.com/watch?v=srDb6vj3w-Q) that the streamer is cracking down on password sharing worldwide this summer. The company enacted the same restrictions for Canadian subscribers (https://www.engadget.com/disney-is-getting-strict-about-password-sharing-starting-in-canada-194038029.html) last fall.

The move is hardly a surprise, as Disney's CFO Hugh Johnston shared the plan during an earnings call in February. "Paid sharing is an opportunity for us. It's one that our competitor is obviously taking advantage of, and one that sits in front of us. We've got some very specific actions (https://www.engadget.com/disney-has-started-cracking-down-on-password-sharing-in-the-us-070317512.html) that we're taking in the next couple of months." Disney-owned Hulu started its own crackdown (https://www.engadget.com/hulu-is-the-latest-streaming-service-to-crack-down-on-password-sharing-161957187.html) on password sharing on March 14, and both streamers' terms of service explicitly ban people from using other customers' login information (Though its latest announcement indicates Disney is actually ready to enforce it).

Streamers across the lineup are restricting password sharing, and it seems to be working — for them, not us. According to analytics firm Antenna, Netflix's United States signups increased (https://www.engadget.com/netflixs-password-sharing-crackdown-seems-to-be-working-151023478.html) by 102 percent during the first four days after the rule went into effect, compared to the 60 days prior. There were an average of 73,000 new signups daily, far outpacing cancelations. Max will also start restricting sharing this year, fully cracking down in 2025.

Disney+ will start its clampdown in some countries come June, expanding to a second wave of countries in September. It's unclear as of now which group the US is in, but Disney will likely provide a breakdown when the dates get closer. Disney+ currently costs $8 monthly with ads (https://www.engadget.com/disney-plus-ad-supported-plan-live-premium-price-increase-162818934.html) and $14 monthly for ad-free viewing.

This article originally appeared on Engadget at https://www.engadget.com/disney-is-also-cracking-down-on-password-sharing-103010857.html?src=rss

https://www.engadget.com/disney-is-also-cracking-down-on-password-sharing-103010857.html?src=rss

@ 044b20cf:89e58620

An old SEO scam has a new AI-generated face

Over the years, Engadget has been the target of a common SEO scam, wherein someone claims ownership of an image and demands a link back to a particular website. A lot of other websites would tell you the same thing, but now the scammers are making their fake DMCA takedown notices and threats of legal action look more legit with the help of easily accessible AI tools.

According to a report by 404Media (https://www.404media.co/a-law-firm-of-ai-generated-lawyers-is-sending-fake-threats-as-an-seo-scam/), the publisher of the website Tedium (https://tedium.co/) received a "copyright infringement notice" via email from a law firm called Commonwealth Legal last week. Like older, similar attempts at duping the recipient, the sender said they're reaching out "in relation to an image" connected to their client. In this case, the sender demanded the addition of a "visible and clickable link" to a website called "tech4gods" underneath the photo that was allegedly stolen.

Since Tedium actually used a photo from a royalty-free provider, the publisher looked into the demand, found the law firm's website, and upon closer inspection, realized that the images of its lawyers were generated by AI. As 404Media notes, the images of the lawyers had vacant looks in the eyes that's commonly seen in photos created by AI tools. If you do a reverse image search on them, you'll get results from a website with the URL generated.photos, which uses artificial intelligence to make "unique, worry-free model photos... from scratch." The publisher also found that the law firm's listed address that's supposed to be on the fourth floor of a building points to a one-floor structure on Google Street View. The owner of tech4gods said he had nothing to do with the scam but admitted that he used to buy backlinks for his website.

This is but one example of how bad actors can use AI tools to fool and scam people, and we have to be more vigilant as instances like this will just likely keep on growing. Reverse image search engines are your friend, but they may not be infallible (https://www.engadget.com/deepfake-detectors-can-be-duped-083601148.html) and may not always help. Deepfakes, for instance, have become a big problem in recent years, as bad actors continue to use them to create convincing videos and audio not just to scam people (https://www.engadget.com/scammers-use-deepfakes-to-steal-256-million-from-a-multinational-firm-034033977.html?_fsig=fGOUqdW63FrvjmvinRrY.A--%7EA), but also to spread misinformation (https://www.engadget.com/tiktok-bans-deepfakes-misinformation-173314446.html) online.

This article originally appeared on Engadget at https://www.engadget.com/an-old-seo-scam-has-a-new-ai-generated-face-100045758.html?src=rss

https://www.engadget.com/an-old-seo-scam-has-a-new-ai-generated-face-100045758.html?src=rss

@ 044b20cf:89e58620

The best VR headsets for 2024

Virtual reality is interesting again. After a few years of stagnation, it’s worth considering an immersive VR headset. The Meta Quest 3 delivers excellent standalone virtual reality for $500, while Apple has thrown down the gauntlet with the Vision Pro (https://www.engadget.com/apple-vision-pro-review-beta-testing-the-future-201430272.html), a $3,500 stab at combining VR and augmented reality (AR). Those who have an original Quest should consider upgrading, and while it’s not really feasible for most people, the Vision Pro provides a glimpse at where the entire category might be headed. We’ve tested and reviewed all of the big players in the VR game; this buyer’s guide will help you decide which is the best VR headset for you.

How we test VR headsets

I tend to judge VR headsets on a few basic criteria: Ergonomics, immersion and controls. It's not that hard to shove a mobile display into a plastic headset and strap some cheap elastic headbands onto it. But it takes skill to craft something that's well balanced and doesn't feel uncomfortable after 30 minutes.

My test for ergonomics is fairly simple: How long can I wear a headset until I start to feel discomfort? For the most ergonomic devices, like the Quest 3, that could easily be an hour or two. But heavier PC hardware often feels cumbersome after just 15 minutes — you won’t find headsets guilty of that in this guide.

Immersion, meanwhile, comes from having high resolution screens with fast refresh rates, so everything looks sharp and smooth. Field of view is also a major element, as it describes how well VR screens can cover what you see. Having a narrow field of view makes it feel like you’re looking through a pair of binoculars, and limits your sense of “presence,” or the idea that you’re actually transported to a virtual world.

A wide field of view, on the other hand, can make it seem like you’re actually flying over the globe in Google Earth. We look at a few popular games, like Superhot, Beat Saber and Pistol Whip, on every headset to judge how immersed we feel.

The best controllers fit naturally in your hands and offer accurate tracking. The industry has basically adopted the design of Meta’s excellent touch controllers, but we're also seeing intriguing leaps forward like Valve's finger tracking gamepads. We judge controllers based on how easy they are to hold, how they hold up to sweaty gameplay sessions and how easily headsets can track their position in space.

Other VR headsets we’ve testedMeta Quest Pro

As great as the Meta Quest 3 is, the Quest 2 is still a very good entry-level VR headset, and it’s worth considering if it’s on sale below its current $250 list price. The Meta Quest Pro (https://www.engadget.com/meta-quest-pro-review-a-next-gen-headset-for-the-vr-faithful-specs-price-130045313-130045431.html), on the the hand, is an expensive boondoggle best ignored.

HTC Vive Pro 2

Outside of Meta’s hardware, the HTC Vive Pro 2 (https://www.engadget.com/htc-vive-pro-2-review-5k-vr-headset-133100685-133000767.html) remains a fantastic PC headset, but it’s far more expensive than the Valve Index, which is more comfortable and offers better audio.

FAQsHow do VR headsets work?

At the most basic level, a VR headset is simply a high quality screen that you’re holding up to your face. For a wired headset, the actual work of rendering a game is done on either a PC or game console. For completely wireless devices, like the Meta Quest 3, that work is handled right on the headset. They rely on either external sensors, or sensors built into the headsets, to map your physical space. While you can use a traditional gamepad or keyboard and mouse in VR, they typically use motion tracking controllers to immerse you in their 3D environments.

What VR headset is best for full body tracking?

While we’re still waiting for a truly great haptic VR bodysuit to arrive, you can still achieve accurate body tracking with most Steam VR-compatible PC headsets. The Valve Index and HTC Vive Pro 2 both rely on room-tracking sensors that can map your body more effectively than the built-in sensors on competitors. You can also add HTC Vive Trackers to wrist and leg straps, as well as belts, for even better coverage. The Meta Quest 3 doesn’t have any easy body tracking solutions, but you can add Vive trackers when it’s plugged into your PC (https://www.vr-wave.store/blogs/virtual-reality-prescription-lenses/get-full-body-tracking-on-your-quest-2) to mimic a Steam VR headset.

Only a few experiences, like VRChat, take advantage of full body tracking at the moment. Currently there aren’t any body tracking solutions for the PlayStation VR and VR2, but we’re intrigued by the company’s Mocopi body trackers (https://www.vr-wave.store/blogs/virtual-reality-prescription-lenses/get-full-body-tracking-on-your-quest-2), which were really announced in Japan.

What VR headsets are better than Oculus?

Oculus is the previous name for Meta’s VR hardware. Currently, Meta only supports the Quest 3, Quest 2 and Quest Pro, all of which are wireless headsets. As we explain above, PC VR headsets can generally achieve better quality virtual reality, since they rely on more powerful graphics hardware.

What VR headsets work with Xbox?

Currently, Microsoft’s Xbox consoles don’t support any VR headsets.

This article originally appeared on Engadget at https://www.engadget.com/best-vr-headsets-140012529.html?src=rss

https://www.engadget.com/best-vr-headsets-140012529.html?src=rss

@ 1689f2c8:5f809f76

test on habla edited

@ c4428155:a36de510

What to Know About the Roiling Debate Over U.S. Maternal Mortality Rates

by Robin Fields (https://www.propublica.org/people/robin-fields)

ProPublica is a nonprofit newsroom that investigates abuses of power. Sign up to receive our biggest stories (https://www.propublica.org/newsletters/the-big-story?source=54G&placement=top-note®ion=national) as soon as they’re published.

An unusual public dispute has erupted among leading maternal health experts over whether the striking rise of U.S. maternal mortality rates over the past two decades was the real deal — or a statistical mirage.

The challenge to what has been a long-held view among public health officials came from researchers behind a new study published in the American Journal of Obstetrics & Gynecology (https://www.ajog.org/article/S0002-9378(24)00005-X/fulltext).

The study concluded that maternal death rates put out by the Centers for Disease Control and Prevention have been substantially inflated by misclassified data. Using an alternate way of counting deaths related to pregnancy and childbirth, the study found, U.S. maternal mortality rates would be far lower than have been reported. And they’d be stable, not rising.

The pushback followed soon after.

The CDC said it disagreed with the study’s findings and criticized the researchers’ methodology as a recipe for undercounting maternal deaths. The American College of Obstetricians and Gynecologists criticized the study for painting an “incomplete picture.”

“To reduce the U.S. maternal mortality crisis to an ‘overestimation’ is irresponsible and minimizes the many lives lost and the families that have been deeply affected,” Dr. Christopher Zahn, the group’s interim CEO, said in a written statement.

ProPublica has been writing since 2017 about what maternal health experts condemned as unacceptably high numbers of deaths and near-deaths related to pregnancy and childbirth. Our series, “Lost Mothers (https://www.propublica.org/series/lost-mothers),” examined how most maternal deaths are preventable and how obdurate racial disparities cause Black mothers to die at far higher rates. The disproportionate toll on Black women is one point on which the CDC and the new study agree.

We also wrote about how flaws in data collection (https://www.propublica.org/article/how-many-american-women-die-from-causes-related-to-pregnancy-or-childbirth) had made it challenging to understand how U.S. maternal mortality rates were changing, as well as how American outcomes compared with those of other wealthy countries.

The landscape has changed in critical ways since then. More than 20 states have banned or restricted access to abortion since the U.S. Supreme Court overturned Roe v. Wade in 2022; studies have shown that maternal mortality rates are higher in these states (https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10728320/).

Thus it seems all the more urgent to revisit some key questions about this marker of reproductive health.

Why is it so hard to pin down how many American women die as a consequence of pregnancy and childbirth?

Health officials rely on information from death certificates to track maternal deaths. These crucial documents are filled in by doctors, turned in to state and local vital statistics offices, then funneled to epidemiologists at the CDC.

The cause-of-death information in these records has always been prone to error and often is incomplete. In the case of maternal deaths, death certificates often aren’t filled out by OB-GYNs or anyone trained to recognize a connection to pregnancy or childbirth.

The simplest cases involve deaths that result directly from pregnancy, labor or postpartum complications. But pregnancy also can interact with a mother-to-be’s preexisting health conditions or cause new ones, figuring into fatalities in ways that death certificates sometimes don’t reflect.

For many years, research showed substantial numbers of maternal deaths were being missed — possibly as many as half. To fix this, starting in 2003, states began phasing in a revised death certificate that added a checkbox question asking whether the person who died, if female, was pregnant at the time or within a year of death.

After states added the pregnancy checkbox, they often saw their rates of maternal deaths double, experts told ProPublica. This eliminated the undercount, but it also brought so-called false positives: deaths counted as related to pregnancy or childbirth that really weren’t. This was particularly a problem among women over 40.

The CDC highlighted (https://stacks.cdc.gov/view/cdc/84767) these issues (https://www.cdc.gov/nchs/data/nvsr/nvsr69/nvsr69_01-508.pdf) in several reports (https://www.cdc.gov/nchs/data/nvsr/nvsr69/nvsr69-02-508.pdf). In one, it found that 147 decedents over 85 (https://www.cdc.gov/nchs/data/nvsr/nvsr69/nvsr69-02-508.pdf) had been identified as pregnant when they died or within the previous year, according to 2013 checkbox data. In another, it analyzed a sample of 2014 and 2016 maternal deaths identified via the checkbox, comparing their death certificates to hospital records; more than half the deaths were potentially false positives (https://www.cdc.gov/nchs/data/nvsr/nvsr69/nvsr69-02-508.pdf), the agency concluded.

In 2018, the agency made changes to improve data quality, among them that the pregnancy checkbox wouldn’t be used for women who died at ages 45 and older. Last year, the CDC took another step designed to wring out errors, requiring states to start verifying checkbox information on a subset of records.

The new study’s authors — a dozen researchers based mostly in Canada — say the tweaks haven’t gone far enough. They propose an alternative way of counting in which deaths are classified as maternal only if at least one cause of death listed on the death certificate specifically mentions pregnancy.

Classifying deaths as maternal without this kind of evidence, based solely on the pregnancy checkbox, undermines “the very purpose of surveillance,” lead author Dr. K.S. Joseph, a physician and epidemiologist at the University of British Columbia, said in an interview.

“If we are to use this cause-of-death information to institute clinical and public health programs aimed at preventing maternal death, we need proper cause of death information,” he said.

He wasn’t surprised that the study kicked off a firestorm: “The dominant narrative is that the U.S. has a maternal mortality crisis,” he wrote in a follow-up email. “So it’s not unexpected that a study such as ours is met with skepticism, at least initially.”

He said the researchers were confident that their findings were accurate and that the narrative would change.

The CDC, however, challenged the study’s approach, arguing it would miss many maternal deaths.

One example: a mother-to-be who dies from hypertension. The checkbox should catch this, ensuring the death would be counted as maternal. Using the study’s method, the death might be missed if whoever fills out the death certificate gives the cause as hypertension without adding the connection to pregnancy.

“Capturing these otherwise unrecorded maternal deaths is critical to understanding the scope of maternal mortality in the United States and taking effective public health action to prevent these deaths,” the CDC said in an emailed statement.

Joseph agreed his study’s method likely does underestimate maternal death rates. “But it is the best available method to answer the question of whether rates have increased over the last 20 years,” he said.

So are U.S. maternal mortality rates rising or not?

The CDC’s National Center for Health Statistics didn’t publish an official U.S. maternal mortality rate for more than a decade — from 2007 to 2018 — as states transitioned to using death certificates including the pregnancy checkbox.

The CDC’s rate for 2018 — 17.4 deaths per 100,000 live births — was considerably higher than the 12.7 rate for 2007, an increase the agency attributed largely to changes in data collection (https://www.cdc.gov/nchs/pressroom/nchs_press_releases/2020/202001_MMR.htm). But it’s less clear how much of that was driven by errors versus accurately counting maternal deaths that previously had been missed.

The agency’s rates edged up again in 2019 and 2020, then leaped to almost 33 deaths per 100,000 live births in 2021. Some of this reflected the pandemic: A quarter of maternal deaths in 2020 and 2021 were associated with COVID-19 (https://www.gao.gov/assets/gao-23-105871.pdf), a report by the Government Accountability Office found.

The new study compares two four-year periods: 1999 to 2002 (before the checkbox) and 2018 to 2021 (after).

Using the CDC’s way of counting, the maternal mortality rate more than doubled over that time frame, from about 9.7 deaths per 100,000 live births in the first period to 23.6 deaths per 100,000 live births in the second one, the study finds.

Using the researchers’ formula, by contrast, maternal deaths stayed essentially flat from the first period to the second, going from 10.2 deaths per 100,000 live births to 10.4 deaths per live births.

Some of the authors’ findings echo those of other researchers. For example, they found that deaths from direct obstetrical causes, such as preeclampsia and postpartum hemorrhage, decreased over time.

There have been other studies that reached similar conclusions, including one showing the rate of pregnant women who died delivering children in the hospital (https://jamanetwork.com/journals/jamanetworkopen/fullarticle/2806478?utm_source=For_The_Media&utm_medium=referral&utm_campaign=ftm_links&utm_term=062223) dropped by more than half from 2008 through 2021.

Still, the CDC’s mortality data experts say they have the fundamental trend line right, particularly since the checkbox-related changes in 2018.

“We feel fairly confident that there has been an increase [in maternal mortality], particularly during the pandemic,” Robert Anderson, chief of mortality statistics for the CDC, told CNN (https://www.cnn.com/2024/03/12/health/maternal-mortality-trends-study-questions/index.html). “We went from underestimating to overestimating, so we had to make that correction. But I feel fairly confident that the increases since 2018 are real.”

What about the data on racial disparities — does this hold up?

Whatever method you use to calculate maternal death rates, Black women still have a substantially higher risk of dying as a result of pregnancy or childbirth.

Data from the CDC shows that for each year from 2018 to 2021, Black women have maternal mortality rates double that of women overall and 2.5 to 3 times higher than white women (https://www.cdc.gov/nchs/data/hestat/maternal-mortality/2021/maternal-mortality-rates-2021.htm#:~:text=In%202021%2C%201%2C205%20women%20died,20.1%20in%202019%20(Table)).

The new study, using its alternative method for counting pregnancy- and childbirth-related deaths, finds similar racial disparities over that period.

How do U.S. maternal mortality rates compare with those of other wealthy countries?

Much of the concern about U.S. maternal death rates has been driven by its outlier status among industrialized countries (https://www.commonwealthfund.org/blog/2020/measuring-maternal-mortality) and that its rates have continued to worsen as rates in many wealthy nations improved (https://www.scientificamerican.com/article/why-maternal-mortality-rates-are-getting-worse-across-the-u-s/).

The 2021 rate reported by the CDC was several times those of countries like Australia and Switzerland and topped those of many middle-income countries.

By the new study’s yardstick, U.S. maternal mortality rates look considerably better — similar to those of Canada and the United Kingdom though still higher than those of many other wealthy countries.

To allow rates to be compared internationally, countries around the world, including the U.S., use the World Health Organization’s definition of maternal mortality.

But they often have very different systems for tracking deaths and checking the accuracy, consistency and comprehensiveness of vital statistics data. The U.K. is considered the gold standard when it comes to maternal deaths, conducting in-depth investigations into every single one (https://www.propublica.org/article/why-giving-birth-is-safer-in-britain-than-in-the-u-s).

While the new study says the CDC has been overestimating U.S. maternal mortality rates, some health experts have argued there are pregnancy-related deaths that aren’t captured by the agency’s data but should be (https://www.propublica.org/article/the-new-us-maternal-mortality-rate-fails-to-capture-many-deaths).

The maternal mortality rate excludes deaths by suicide or caused by “accidental or incidental” causes, including drug overdoses. It also doesn’t include maternal deaths that occur more than 42 days after giving birth. In the U.S., about 30% of pregnancy-related deaths are happening from 43 days to 365 days after delivery (https://www.cdc.gov/reproductivehealth/maternal-mortality/erase-mm/data-mmrc.html), a CDC report said.

“These are all issues that clinicians and public health people need to debate and to address,” Joseph said. “But we haven’t done it as yet.”

https://www.propublica.org/article/what-to-know-maternal-mortality-rates-debate

@ d7607464:421e573a

Chef's notes

Details

• ⏲️ Prep time: 0 min
• 🍳 Cook time: 5 min
• 🍽️ Servings: 1

Ingredients

• 3/4 cup Raw Milk
• 1 tbsp Dutch-Processed Cocoa
• 1 tbsp Cane Sugar, to taste
• 1 tbsp Raw Unfiltered Honey, to taste

Directions

1. Heat milk in a pot until steaming.
2. Whisk in cocoa, sugar, and honey.
3. Serve hot.

@ 1e52c554:21771908

Posthumous work of the Colombian poet born in Don Matias on January 20, 1948.

Welcome to this blog dedicated to the Posthumous work of the Colombian poet Francisco Luis Arroyave Tabares (my father), born in Don Matias on January 20, 1948-2010. Where I will be publishing each of the 175 sonnets from his unpublished collection 'Sonnets For The Twenty-First Century And A Circadian Musical (1984-1987).' Analyzed with GPT4 artificial intelligence and illustrated with AI tools... I hope you enjoy this garden of words snatched from the solitude of a locked room.

Likewise, any enthusiast of the sonnet form is invited to conduct their personal studies of Arroyave Tabares' work, as it is a collection that, although registered since 1989, has not yet been published.

Frank Duna

---

Analysis "We Could Carry On"

Introduction

"Sonnet 109" by Francisco Luis Arroyave Tabares, explores themes of love, companionship, gratitude, and inspiration.

Thematic Analysis

The octave (lines 1-8) sets up the theme of the poem: a journey of two individuals, presumably lovers, who are so entranced by each other that they could travel endlessly. The journey is not just physical, but also emotional and spiritual, as they watch the world improve from a distance and carry on in the spaces of their minds. The octave speaks of a shared experience, of carrying important things together to make their lives and futures happier.

The sextet (lines 9-14) then builds upon this theme by introducing the concept of gratitude. The speaker talks about giving out lights, or spiritual inspiration, to the multitude, suggesting a desire to share their happiness and wisdom with others. The sextet also introduces the idea of breaking lines of solitude through sweet and heavenly words, further emphasizing the theme of shared experience and unity.

Overall, the octave and sextet work together to create a narrative of love, journey, shared experiences, and the desire to spread positivity and inspiration. The octave sets the stage and the sextet brings the themes to a conclusion, creating a well-rounded and impactful sonnet.

Rhyme Scheme

The rhyme scheme (ABBA ABBA CDCDCD) is a common one for sonnets, particularly those in the Petrarchan or Italian style.

Let’s break it down in the context of Sonnet 109 by Francisco Luis Arroyave Tabares:

Octave:

Line 1 (A): While carried away by your glance’s spell Line 2 (B): Dauntlessly we could travel for ever Line 3 (B): And watch from the distance earth get better Line 4 (A): With its pains and songs that we have kept so well. Line 5 (A): And in those spaces that in our mind dwell Line 6 (B): We would also carry on together Line 7 (B): And the important things we would gather Line 8 (A): To make happier our life and futures tell.

Sextet:

Line 9 (C): Uttering the incense of gratitude Line 10 (D): That since ancient times to all brings accords Line 11 (C): We would give lights out to the multitude… Line 12 (D): Blessed by the houses of the richest lords Line 13 (C): We could as well brake lines of solitude Line 14 (D): Through notes of sweet and heaven breathed words.

In the octave, the first and fourth lines rhyme, as do the second and third, fifth and eighth, and sixth and seventh. This creates a mirrored or “enclosed” rhyme (ABBA ABBA).

In the sextet, the ninth and eleventh lines rhyme, as do the tenth and twelfth, and thirteenth and fourteenth. This creates a chain-like rhyme (CDCDCD).

This rhyme scheme contributes to the overall flow and rhythm of the sonnet, enhancing its musicality and emotional impact. It also helps to delineate the shift in theme or tone that typically occurs between the octave and the sextet in a Petrarchan sonnet. In this case, the shift from the shared journey in the octave to the expression of gratitude and desire to inspire others in the sextet.

It’s also worth noting that the sonnet adheres to the iambic pentameter, which is a metrical pattern in poetry where each line consists of five pairs of unstressed and stressed syllables. This rhythm contributes to the musicality and flow of the poem.

Overall, the sonnet’s detailed rhyme scheme and metrical pattern contribute to its thematic depth and aesthetic appeal.

Additional Aspects

Let’s delve deeper into the sonnet “We Could Carry On” by Francisco Luis Arroyave Tabares.

Language and Imagery: The language used in Sonnet 109 is rich and evocative, creating vivid imagery that enhances the themes of the poem. Phrases like “carried away by your glance’s spell” and “watch from the distance earth get better” paint a picture of a journey filled with wonder and awe. The use of words like “incense of gratitude” and “lights out to the multitude” suggest a spiritual or transcendent dimension to this journey.

Themes: The main themes of the poem include love, journey, shared experiences, gratitude, and inspiration. The journey is not just physical, but also emotional and spiritual, and it’s shared between two individuals. The theme of gratitude is expressed through the act of giving out lights, or spiritual inspiration, to others. The desire to break lines of solitude through sweet and heavenly words suggests themes of unity and connection.

Meter: The meter of the poem appears to be iambic pentameter, which is a common meter in English poetry and particularly in sonnets. This means each line typically contains five iambs, or pairs of unstressed and stressed syllables. For example, in the line “While carried away by your glance’s spell”, the pattern of unstressed and stressed syllables creates a rhythmic flow that enhances the musicality of the poem.

Overall: Sonnet 109 is a beautifully crafted poem that uses evocative language and imagery to explore themes of love, journey, shared experiences, gratitude, and inspiration. The use of the Petrarchan sonnet form, with its specific rhyme scheme and structure, helps to enhance these themes and gives the poem a rhythmic and musical quality. The shift in focus from the octave to the sextet allows for a nuanced exploration of these themes, creating a narrative arc that is both engaging and emotionally resonant. The poem is a testament to the power of poetry to capture complex emotions and experiences in a compact and structured form.

(GPT4)

---

Syllable count for each line.

``` We Could Carry On

10 While carried away by your glance's spell 10 Dauntlessly we could travel for ever
10 And watch from the distance earth get better 11 With its pains and songs that we have kept so well.

10 And in those spaces that in our mind dwell 10 We would also carry on together 10 And the important things we would gather 10 To make happier our life and futures tell.

10 Uttering the incence of gratitude
10 That since ancient times to all brings accords
10 We would give lights out to the multitude...
10 Blessed by the houses of the richest lords
10 We could as well brake lines of solitude
9 Through notes of sweet and heaven breathed words.
*** ```

---

Sonnets For The Twenty First Century And A Circadian Musical Written By Francisco Luis Arroyave Tabares (1984-1987)

---

Analyzed by GPT4; Image by leonardo.ai; First published on Nostr Protocol by franciscoarroyavet@nostrplebs.com We Could Carry On ```

@ 1e52c554:21771908

Posthumous work of the Colombian poet born in Don Matias on January 20, 1948.

Welcome to this blog dedicated to the Posthumous work of the Colombian poet Francisco Luis Arroyave Tabares (my father), born in Don Matias on January 20, 1948-2010. Where I will be publishing each of the 175 sonnets from his unpublished collection 'Sonnets For The Twenty-First Century And A Circadian Musical (1984-1987).' Analyzed with GPT4 artificial intelligence and illustrated with AI tools... I hope you enjoy this garden of words snatched from the solitude of a locked room.

Likewise, any enthusiast of the sonnet form is invited to conduct their personal studies of Arroyave Tabares' work, as it is a collection that, although registered since 1989, has not yet been published.

Frank Duna

---

Analysis "Your Truth"

Introduction

“Your Truth” by Francisco Luis Arroyave Tabares is a beautiful sonnet that explores the themes of truth, beauty, and time.

Thematic Analysis

Octave:

The octave presents a problem or explores a particular theme. In this case, the speaker acknowledges their previous ignorance (“Aware of vanity and worthlessness”, “Your echoing thoughts erase my blindness”) and their newfound understanding and appreciation of the subject (“My mind enjoys while discovering you”, “Where, without pageantry, each noble hue Flourishes gifting your unseen highness”).

Sestet:

The sestet usually provides a resolution or commentary on the problem or theme presented in the octave. Here, the speaker expresses their commitment to the subject (“My days from now on will be episodes Of that charm you give continuously”) and their intention to use this truth in their future creations (“I will contrive the essence of my odes With your truth that stands on furiously”). The final line (“When time with a slow hand all things erodes”) suggests the enduring nature of this truth, even in the face of time’s inevitable decay.

Overall, the sonnet explores the transformative power of truth and its enduring nature. The speaker’s journey from ignorance to understanding is reflected in the structure of the sonnet itself, moving from problem to resolution. The use of language and metaphor throughout adds depth and richness to this exploration.

Rhyme Scheme

The rhyme scheme (ABA ABBA CDCDCD) is not typical for a sonnet. However, let’s analyze it in the context of the sonnet “Your Truth” by Francisco Luis Arroyave Tabares.

First, let’s assign each end word a letter, starting from ‘A’ for the first word, ‘B’ for the second different word, and so on:

``` A - worthlessness B - you A - hue A - highness B - blindness B - knew A - few A - happiness

C - fortuituously D - episodes C - continuously D - odes C - furiously D - erodes ```

However, when we apply this to the sonnet, it doesn’t seem to match the ABA ABBA CDCDCD pattern you’ve provided. The rhyme scheme of this sonnet appears to be ABBA ABBA CDC DCD, which is a variation of the Petrarchan sonnet.

It’s important to note that while sonnets traditionally follow certain rhyme schemes, poets often experiment with different patterns to achieve various artistic effects. In this case, the poet may have chosen this particular scheme to emphasize certain ideas or to create a specific rhythm or flow.

Additional Aspects

Let’s delve deeper into the analysis of “Your Truth” by Francisco Luis Arroyave Tabares:

Language: The language used in the sonnet “Your Truth” is formal and poetic, with a rich vocabulary. The poet uses words like “pageantry,” “fortuitously,” and “vaporous trifles,” which add depth and complexity to the poem. The use of such language helps to create a sophisticated and thoughtful tone.

Imagery: The poem is filled with vivid imagery that helps to convey its themes. For example, “Your echoing thoughts erase my blindness” uses the image of echoing thoughts to represent the enlightening power of truth. Similarly, “When time with a slow hand all things erodes” creates a powerful image of the relentless passage of time.

Themes: The main theme of the poem is the transformative power of truth. The speaker describes their journey from ignorance to understanding, and how this newfound truth will shape their future creations. The enduring nature of truth, even in the face of time’s decay, is another key theme.

Meter: The sonnet appears to be written in iambic pentameter, which is a common meter in English poetry and consists of five pairs of unstressed and stressed syllables per line. This gives the poem a rhythmic quality and helps to emphasize certain words and ideas.

Overall: “Your Truth” is a thoughtful and beautifully crafted sonnet that explores the transformative and enduring power of truth. The poet’s use of sophisticated language, vivid imagery, and rhythmic meter all contribute to the poem’s depth and richness. The structure of the sonnet, with its problem-resolution format, mirrors the speaker’s journey from ignorance to understanding, adding another layer of meaning to the poem.

(GPT4)

---

Syllable count for each line.

``` Your Truth

10 Aware of vanity and worthlessness 10 My mind enjoys while discovering you 10 Where, without pageantry, each noble hue
10 Flourishes gifting your unseen highness.

10 Your echoing thoughts erase my blindness 10 And little sense of beauty that I knew 10 When far away from reason just a few 10 Vaporous trifles meant my happiness.

10 Chosen at will, or fortuituously
10 My days from now on will be episodes 10 Of that charm you give continuously. 10 I will contrive the essence of my odes
10 With your truth that stands on furiously 10 When time with a slow hand all things erodes. ***

```

---

Sonnets For The Twenty First Century And A Circadian Musical Written By Francisco Luis Arroyave Tabares (1984-1987)

---

Analyzed by GPT4; Image by leonardo.ai; First published on Nostr Protocol by franciscoarroyavet@nostrplebs.com Your Truth

@ 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?

@ e869a322:e73b29c5

• It is almost April!
• How about this external image ?
• Do something to your hair.
• Have you ever eaten a spoon full of peanut butter ?
• Have you ever eaten a spoon full of ketchup ?
• Do you like spiders ?
• How about this external image ?

@ 7f5c2b4e:a818d75d

Nsec.app is a Nostr application which lets you share access to your account and login to Nostr apps seamlessly with numerous devices.

The app is super useful when collaboratively running a Nostr account. It lets you generate tokens to share with partners or colleagues and provide different levels of access to different individuals.

Another bonus feature of nsec.app is letting you forget about Nostr browser extensions. Extensions have their fair share of useful features, but using nsec.app (or other apps that support NIP-46 login, e.g. nsecBunker) is often more convenient, arguably more secure and offers some features, that extensions aren't able to deliver.

Let's walk through the process of starting the nsec.app and see what features it has to offer.

Installation

Nsec.app is a PWA (see my short blog post on PWAs and their benefits here), meaning that it can be saved to your device in a way that it feels and acts like a native app. Alternatively the app can be used in the browser.

Visit Nsec.app:

https://i.nostr.build/axlP.png

After pressing the "Get started" button you'll be welcomed by three main options: "Sign up", "Login" or "Import Key". Let's explore each of these options:

1. Sign up: This option suits those, who do not have a Nostr account yet. I'd steer clear from this option for now and create an account in a more "conventional" way – via one of the popular Nostr clients or by utilizing a dedicated browser extension.

Stay tuned as the developers are working on wide implementation of NIP49. At the moment few Nostr clients support NIP49, so you won't have many options of using keys created with nsec.app. When most Nostr apps support NIP49 logins, signing up to Nostr via nsec.app will become a more convenient option.

If you decide to utilize nsec.app to create your Nostr account, the process is super simple:

1) Choose your Nostr address 2) Create and confirm your password 3) Enjoy your new Nostr account 💜

https://i.nostr.build/JqgP.png

1. Import key: This approach assumes you would like to start using nsec.app with the existing Nostr account.

https://i.nostr.build/5e9y.png

In this case you'll need to choose your username, provide your private key and choose a password. This will create the nsec.app account (by setting a username and a password) while binding it with your original Nostr account (by providing your private key).

It is worth noting that your keys will be encrypted by your password and stored on nsec.app's server to sync to other devices in end-to-end encrypted manner.

1. Login: This approach assumes you've already set up nsec.app and would like to enter your dashboard from a new device.

https://i.nostr.build/k6aa.png

Do not forget to click the "Enable background service" tile after setting up your account. This will ensure you receive a notification whenever the request to authorize a login is created.

https://i.nostr.build/Zrdx.png

Usage

After setting up nsec.app you're ready to start utilizing it to login to numerous Nostr apps.

The most powerful feature of nsec.app is that it lets you login to apps without having to use the browser extension or exposing your private key.

For example, I can now turn Coracle client into a PWA on my iPhone, which is otherwise impossible, because Apple does not allow you to utilize browser extensions with PWAs.

Another use case is delegating the rights to interact with Nostr on behalf of the account you created.

Regardless of wether you want to use the app single-handedly, or delegate the private key, the process is as follows:

1. Use nsec.app to create a login string by pressing "Connect app".
2. Copy the string by pressing the corresponding button.

https://i.nostr.build/rvVB.png

1. Paste the string into the client that you'd like to login to.
2. As you (or your companion) try to login to the Nostr app, nsec.app will display a notification asking you (the administrator) to approve the login.

https://i.nostr.build/7x53.png

As you can see, there are two options for you to choose from:

• Basic permissions: This will approve all potential future interactions.
• On demand: This will log the user in and ask for your approvals every time the user tries to interact with the protocol in a new way (like, zap, follow, etc.)

That's it. You can now interact with nostr without ever having to utilize the browser extension or share your private key with any app.

Features

Customization

Nsec.app lets you customize the way your connected apps look. You can name them, specify a website address and choose an icon of your choice. Very handy functionality for when you start actively using the app:

https://i.nostr.build/ej6X.png

As the stack of connected apps grows this will help you distinguish between them in order to introduce any necessary changes.

https://i.nostr.build/XEgW.png

Connected apps management

This leads us to the next important part of using nsec.app: revoking access to apps. This is especially important when it comes to sharing access to account with someone else. In case you no longer plan to collaborate on the account, or you simply do not need some app connection to function any longer, you can revoke access at any time.

Just open the app you need and: (a) press "Delete app" (this completely cuts connection between your app and nsec.app) or (b) press the three dots next to the existing approved permission followed by "Delete permission" (this cancels the given permission, so that the next time you (or other user) tries to interact with the protocol, you will receive a notification asking you to approve their action).

https://i.nostr.build/d3QD.png

NIP49 logins

Nsec.app allows you to utilize another way of logging into Nostr apps – NIP49. We touched on this approach earlier, so let's explore how it works.

Here's an example with Noogle:

1. Choose the Login with NCryptSec option:

https://i.nostr.build/DzeV.png

1. Enter the encrypted Nsec (to be retrieved from the nsec.app in Settings -> Export) and the nsec.app password:

https://i.nostr.build/R505.png

That's it. You're logged in.

https://i.nostr.build/moLR.png

At the moment few clients support this NIP, but given the benefits of this functionality, it shouldn't be long before we see more and more clients join in.

Outro

Just like with every other Nostr app, there's a lot of work to be done. Nevertheless, nsec.app already solves many important problems, and is definitely worth your attention. Give it a try and let us know if you find any bugs, or come up with some ideas worth implementing. Feel free to ping myself or, better yet, the app developer nostr:npub1xdtducdnjerex88gkg2qk2atsdlqsyxqaag4h05jmcpyspqt30wscmntxy

---

Hope this guide was useful! If so, don't forget to zap this post 😉

See you on the other side of the Nostr rabbit hole

Tony⚡️

@ 044b20cf:89e58620

Apple cuts over 700 jobs following its car and display project closures

Over 700 people at Apple have recently lost their jobs, according to the latest WARN report (https://edd.ca.gov/en/jobs_and_training/layoff_services_warn) posted by the Employment Development Department of California (EDD). Most of the people who were laid off worked at Apple's offices in Santa Clara, with 371 of them coming from (https://www.bloomberg.com/news/articles/2024-04-04/apple-cut-at-least-600-workers-when-car-screen-projects-stopped?sref=10lNAhZ9) the company location that primarily dealt with the company's now-defunct electric vehicle project (https://www.engadget.com/the-apple-car-project-is-reportedly-dead-203012885.html). Under California law, companies are required to file a report with the EDD for each location affected by layoffs under the Worker Adjustment and Retraining Notification (WARN) program.

Eight Apple locations in Santa Clara were hit by layoffs, including the main car office, though one of them worked on its in-house MicroLED display project (https://www.engadget.com/2018-03-18-apple-microled-rumor.html) that was reportedly scrapped (https://www.bloomberg.com/news/articles/2024-03-22/apple-scraps-plan-to-design-display-for-watch-in-house-cuts-jobs?sref=10lNAhZ9) in March due to costs and technical difficulties. The company was hoping to produce its own screens for iPhones, Macs and its smartwatches, but that clearly isn't happening anytime soon.

Apple's original car ambitions were to build a fully autonomous vehicle without pedals and a steering wheel, until it decided to develop an electric vehicle instead. A previous Bloomberg report said Apple canceled (https://www.engadget.com/the-apple-car-project-is-reportedly-dead-203012885.html) the initiative internally called "Project Titan" after investing billions of dollars and a decade into it. The employees who were developing the vehicle were given the chance to transfer to Apple's other divisions, including its teams that are reportedly working on artificial intelligence and home robotics. But based on Apple's WARN report, it wasn't able to re-integrate everyone into the company.

Apple is believed to be in the very early stages of developing personal robotics (https://www.engadget.com/apple-is-developing-personal-robots-for-your-home-bloomberg-says-044254029.html?fsig=12hmctV1EI30PVfHKzjiiw--%7EA) for people's homes. One of the machines that's currently a work-in-progress is a robot that follows people around, while the other is a table-top device that uses a robot to move a display around, according to another _Bloomberg report. The company's work on personal robotics is part of its efforts, which also include the Vision Pro (https://www.engadget.com/apple-vision-pro-review-beta-testing-the-future-201430272.html), to find new sources of revenue.

This article originally appeared on Engadget at https://www.engadget.com/apple-cuts-over-700-jobs-following-its-car-and-display-project-closures-061524777.html?src=rss

https://www.engadget.com/apple-cuts-over-700-jobs-following-its-car-and-display-project-closures-061524777.html?src=rss

@ 35f3a26c:92ddf231

What is a Bitcoin spot ETF?

Is an asset that tracks the price of Bitcoin.

Why it is considered a game changer?

Institutional investors and wealthy individuals, using large investment firms like Blackrock, Fidelity or Ark among others, once approved in their countries, will be able to acquire the asset with low risk, since these investment firms are highly regulated. These investors have above 15 trillion dollars invested in these large firms and therefore, once the ETF is approved, it is expected that these firms will allocate at least 1% of their portfolios to it. That will be mean at least $150 billions into Bitcoin, which is remarkable considering the current market cap of the asset is currently $570 billion.

An injection of minimum $150 billions translates in a huge demand for Bitcoin with massive potential for price appreciation.

Until now, very few large institutions have acquired Bitcoin, examples are Tesla Inc (Nasdaq: TSLA) and Microstrategy (Nasdaq: MSTR), which wrote a document labeled "A summary of some of the key considerations for corporations to keep in mind when investing in bitcoin". The link to the document:

https://www.microstrategy.com/en/bitcoin/documents/key-considerations-for-corporate-investment-in-bitcoin

Let's check the math

Amount of Bitcoin mined per day:

  - Bitcoins mined per block: 6.25

  - Time in minutes to mine one block (approx): 10

  - Minutes in one day: 1440

  - Blocks mined per day: 144  ->  (1440  / 10 = 144)

  - Bitcoins mined per day: 900 -> ( 144  x 6.25 = 900)

After the halving, since the Bitcoin mined per block will be reduced to 3.125, we will only have 450 mined per day.

*Bitcoin available for trading*:

  - Around 4 million across exchanges
  - 900 per day injected in the market

Assuming Miners sell all 900 every day (which is not the case but we will use as worst case scenario), this means that in order for the price of Bitcoin to keep the current price (around $29.4K as I write this article), $26.5 millions are needed in the market to buy those 900 fresh mined every day, $795 million per month, $9.54 billion per year.

As you can see, the financial energy put into Bitcoin to maintain its current price is already considerable, but nothing in comparison with $150 billion (worst case scenario) injection of fresh capital into buying Bitcoin. The projection is not linear since there are many additional variables to factor in, specially qualitative non quantifiable ones as potential financial crisis, absurd regulations, governments corruption, wars, pandemics, etc, but nevertheless, a close to 15X is plausible, which would rocket the price of Bitcoin to around $441K as soon as the $150 billion are deployed to acquire it. Now, consider that this is worst case scenario and valid only until the end of this halving (the amount of mined Bitcoin per day is reduced by half), next one is around the end of April 2024.

After the halving, with the current amount of financial energy injected into Bitcoin ($26.5 million), the price would potentially double to around $58.8K, and if 1% of the investment companies applying for an ETF is injected, the math take the potential price of Bitcoin to $882K as soon as that 1% is deployed. The time frame is unknown, but I would assume before the end of 2024, Why? Because the ETFs are being yet again delayed by the SEC in USA for a next decision in 4 to 6 months.

But USA is not the only country where large Investment Companies are applying for ETFs, it is true that the two largest ones are in USA (Blackrock and Fidelity), but there are many more that combined across the world would add up to a massive additional amount of capital injected into Bitcoin.

The first one in Europe, Jacobi Asset Management, issuer of an equity structure for digital assets in Europe with the first Bitcoin ETF, with a total portfolio of approx. $4.8 billion. Assuming 1% (worst scenario) of its portfolio will be deployed into Bitcoin, additional $48 million would be injected. The launch of this ETF was "July 2023", not exact date given and the web site still missing required information. I will assume this capital will be injected between August and December 2023.

Long term impact?

We can divide the long term impact into two arenas:

1. Asset appreciation
2. Attempts to control the asset

The first one have been explained above, the more capital is deployed into the asset, and the more time passes, the more valuable and scarce it becomes (one halving every 4 years) and therefore, Bitcoin will continue to appreciate over time by "a lot". Extrapolate to 5% of 15 trillion dollars, then to 10%, etc. Considering that Bitcoin is the best asset in terms of appreciation of the last 10 years, it is plausible that institutional investors will be eager to put more than 1% of their portfolios into Bitcoin, I would assume that 5% for the most conservative and 20% for the most aggressive will be logical. You do the math, you will get numbers that will explain why so many financial analyst come with such a high numbers in their predictions of the future price of Bitcoin.

The second one is the reason I decided to write this article, recently I read a post from Chris Blec in X, his post was quite interesting, it reads "Pfizer convinced billions of people to inject a mysterious chemical into their body multiple times but you don't think Blackrock can convince normies that their fork is the real Bitcoin?"

Most provocative post which opens the door for debate, one that I am certain is being discussed for years already close doors among the Bitcoin community.

Basically, he leads to a possible scenario in which Blackrock or a union of Investment corporations could influence with their resources developers and miners to fork Bitcoin into; for instance; a PoS (Proof of Stake) chain, basically centralizing and controlling Bitcoin. A fork creates a new chain and the users will decide which chain is Bitcoin, users decide by changing their Node into the new chain or not, one Node, one Vote.

This is certainly plausible and the community needs to work on it to shield Bitcoin from those attacks, which eventually can transform Bitcoin into a non valuable asset. For instance, reducing the block time to 1 minute with no other change, that will mean that the amount of Bitcoin mined and injected in the market would be as of today 9000 and not 900, reducing its price dramatically since the offer will increase considerably. Other attack could be to try increasing the block size, this will make it more difficult for people with low resources to run a Node from home and therefore vote with their Node, leads to centralization into fewer Nodes, which is against Bitcoin investors interest.

In my opinion, education is key, those investment funds manage money from wealthy investors, if those investors understand the ethos of Bitcoin and why the asset is so scarce and valuable, they will fight back together with the individual investors for those changes not to be pedaled into the chain. At the end, greed is a very strong motivator and Satoshi understood that perfectly and therefore it is accounted for in the design.

Additionally, a considerable percentage of the Bitcoin investors are quite informed and fear can't be use as a motivator, as it was the case of the pharmaceuticals and their experimental drugs, the Investment companies could use their resources to create campaigns pushing their narrative, but the community will see through that and counter it in the social networks quite fast, in my opinion, in the age of information, the legacy MSM can't easily steer the Bitcoin ecosystem opinion as they could have done with the population up to the 90s, now is a real challenge for them. Proof of that is that they have been fighting Bitcoin with everything they got until now. They short it, talk trash it as much as they could in the legacy MSM, call it rat poison, stated that it will go to zero (while secretly buying it...) and after all that, now they are lining up to buy it and speaking highly of the asset.

We need to be alert, Bitcoin has endured 14 years of attacks and survived thanks to the community and investors, we need to stay vigilant and protect it, run at least one Node at home, remember, one Node, one Vote.

---

If you like my work and would like to support me:

@ 32e18276:5c68e245

Thanks to OpenSats and its generous donors, Damus has been able to continue building open source freedom tech without influence from external parties. Damus' mission is to build the best nostr and bitcoin tech without compromise on decentralization, and this will continue to be our mission going forward. This wouldn't be possible without OpenSats and other organizations that continue to help make this vision a reality!

As per our OpenSats agreement, we are required to publish quarterly reports on our progress. We submit this report to nostr for full transparency. If you're curious what we've been working on this past quarter, check it out:

Damus OpenSats Q2 Progress Report

The second quarter of the Damus OpenSats grant has been very productive and encompasses the 1.7 release of Damus, soon to be released to the appstore.

Notable new features in Damus iOS 1.7

• Damus purple subscriptions which includes the DeepL Universal Translator 🖖
• Local-first full-text search engine for privacy preserving searching powered by nostrdb4
• Add NIP-42 relay auth support
• Added regional relay recommendations for Germany, Japan, Thailand
• Add naddr link support

New tech built in this quarter

• A new nostr share-link opengraph renderer in rust called notecrumbs2, powered by egui and nostrdb4
• Added query and subscription support to nostrdb{,-rs}
• Added fulltext search query support nostrdb, which powers the search in Damus iOS v1.7
• Working prototype of Damus Android and Damus NoteDeck, a rust-powered multiplatform nostr client3 powered by egui and nostrdb4

How money was used

• Paying individual contributors via patch submissions on the damus dev mailing list (patches@damus.io)
• relay.damus.io server costs
• deepl translation costs
• Living expenses, nostr/bitcoin conferences, travel, etc

Contributions

Damus-iOS

name added removed commits Daniel D’Aquino <daniel@daquino.me> +7655 -2989 46 William Casarin <jb55@jb55.com> +3753 -2396 132 kernelkind <kernelkind@gmail.com> +1513 -273 27 Charlie Fish <contact@charlie.fish> +1386 -331 12 Terry Yiu <git@tyiu.xyz> +1018 -102 3 ericholguin <ericholguin@apache.org> +509 -65 3 Transifex <transifex@transifex.com> +464 -67 80 Suhail Saqan <suhail.saqan@gmail.com> +347 -27 2 ericholguin <eric.holguinsanchez@gmail.com> +202 -101 6 alltheseas <64376233+alltheseas@users.noreply.github.com> +51 -24 5 Kieran <kieran@harkin.me> +33 -0 1 kunigaku <kunigaku@gmail.com> +13 -2 1 vuittont60 <81072379+vuittont60@users.noreply.github.com> +3 -3 1 Jing维 <zhjw43@163.com> +1 -1 1 hakkadaikon <hakkadaikon@yahoo.co.jp> +1 -1 1

notecrumbs

name added removed commits William Casarin <jb55@jb55.com> +6079 -819 68

Damus Android/NoteDeck

name added removed commits William Casarin <jb55@jb55.com> +5205 -2870 86 0xb10c <b10c@b10c.me> +6 -2 1 alltheseas <64376233+alltheseas@users.noreply.github.com> +5 -0 1

nostrdb

name added removed commits William Casarin <jb55@jb55.com> +88175 -3758 186 kernelkind <kernelkind@gmail.com> +50 -3 1 Yasuhiro Matsumoto <mattn.jp@gmail.com> +26 -3 1 Charlie Fish <contact@charlie.fish> +12 -0 1 shuoer86 <129674997+shuoer86@users.noreply.github.com> +3 -3 1 hakkadaikon <hakkadaikon@yahoo.co.jp> +2 -2 1

nostrdb-rs

name added removed commits William Casarin <jb55@jb55.com> +8181 -248 50

iOS Changelog

Added

• Damus Purple membership! (Daniel D’Aquino)
• Improved damus.io share links (William Casarin)
• Add local, privacy-preserving fulltext search engine (William Casarin)
• Add NIP-42 relay auth support (Charlie Fish)
• Add ability to hide suggested hashtags (ericholguin)
• Add ability to mute hashtag from SearchView (Charlie Fish)
• Add ability to preview media taken with camera (Suhail Saqan)
• Add ability to search for naddr, nprofiles, nevents (kernelkind)
• Add experimental push notification support (Daniel D’Aquino)
• Add naddr link support (kernelkind)
• Add regional relay recommendations to Relay configuration view (Daniel D’Aquino)
• Add regional relays for Germany (Daniel D’Aquino)
• Add regional relays for Japan (Daniel D’Aquino)
• Add regional relays for Thailand (Daniel D’Aquino)
• Add support for Apple In-App purchases (Daniel D’Aquino)
• Always convert damus.io links to inline mentions (William Casarin)
• Notification reminders for Damus Purple impending expiration (Daniel D’Aquino)

Changed

• Disable inline text suggestions on 17.0 as they interfere with mention generation (William Casarin)
• EULA is not shown by default (ericholguin)
• Generate nprofile/nevent links in share menus (kernelkind)
• Improve push notification support to match local notification support (Daniel D’Aquino)
• Move mute thread in menu so it's not clicked by accident (alltheseas)
• Prioritize friends when autocompleting (Charlie Fish)

Fixed

• Add workaround to fix note language recognition and reduce wasteful translation requests (Terry Yiu)
• Allow mentioning users with punctuation characters in their names (kernelkind)
• Fix broken mentions when there is text is directly after (kernelkind)
• Fix crash on very large notes (Daniel D’Aquino)
• Fix crash when accessing cached purple accounts (William Casarin)
• Fix crash when logging out and switching accounts (William Casarin)
• Fix duplicate notes getting written to nostrdb (William Casarin)
• Fixed bug where sometimes notes from other profiles appear on profile pages (Charlie Fish)
• Fixed previews not rendering (ericholguin)
• Fix issue where adding relays might not work on corrupted contact lists (Charlie Fish)
• Fix load media formatting on small screens (kernelkind)
• Fix many nostrdb transaction related crashes (William Casarin)
• Fix onboarding post view not being dismissed under certain conditions (Daniel D’Aquino)
• Fix performance issue with gifs (William Casarin)
• Fix persistent local notifications even after logout (William Casarin)
• Fix profile not updating bug (William Casarin)
• Fix shared nevents that are too long (kernelkind)
• Fix welcome screen not showing if the user enters the app directly after a successful checkout without going through the link (Daniel D’Aquino)
• Remove extra space at the end of DM messages (kernelkind)
• Save current viewed image index when switching to fullscreen (kernelkind)

Removed

• Removed copying public key action (ericholguin)
• Removed old nsec key warning, nsec automatically convert to npub when posting (kernelkind)

@ 35f3a26c:92ddf231

The Mutant Ideologies

Some believe there is a fight between Capitalism and Liberalism...

Some believe that those fights are nothing but distractions to keep the population from focusing their attention on the real issues....

In my opinion, those ideologies are mutating and merging into Authoritarianism.

Censoring have become so common that private companies in the USA have gone to the extreme to censor and cancel intellectuals, journalist, PhD's, MD’s, scientist and even a democratically elected president when they speak against the narrative supported by that company, the globes are off and the fight is now in the open between corporations interests, the same companies who have in their pockets the political apparatus and the judicial power of the countries in which they operate.

Meanwhile, the majority of those who align themselves with one of the three ideologies, are fighting the others as if they where the owners of truth, censoring each other, sad to watch and ironic, in most cases...

The Censoring Age

Once upon a time we used to debate, adding value to the society while doing so, now is just an unintelligent fight with weak arguments and in many cases incredibly absurd, very rapidly the conversation turns into insulting, dismissing the other party with no arguments and even censoring if against of the narrative of the platform landlords. Surreal if you think about it.

If you are a critical thinker, you may have theories, but you have to be scratching your head trying to find out How we got here?, By design? Or just a product of our own technological development oriented to profit and not the improvement of our health and social wealth fare. Perhaps the latest...

Does it matter to know how? I believe it does because learning from those errors we could start building a better society one step at the time so in two or three generations we could have the required base to build a more adequate social construct. Naive, but it would be nice.

The Failed Bitcoin Solution

I am of the opinion that we will not be able to obtain a more adequate social construct until we manage to separate the state from the money, hence the statement, fix the money, fix the world...

We are failing badly. Bitcoin was a tool to achieve that, it is failing miserably, it become a store of value, a very profitable one, an excellent investment, it was hard for the system to beat it, but despite of its incompetent officials, the FIAT system managed to control it and turn it into their benefit, now governments, corporations and institutions are buying it and soon we will observe the wash trading, buying and selling between themselves legally using the rules the system offers to manipulate and accumulate while the current "whales" reaching already their mid 40s and 50s will sell into FIAT large quantities of Bitcoin to retire comfortable, people tends to forget that there is a time factor.

Those in their 30s will probably build around it or go to real state and sit happy, but, Where are the values and the ideology Satoshi intended to push in the world? Doesn't seem it is in Bitcoin "hodlers" hands anymore. Very few real hard core libertarian believers left in the ecosystem.

If we go beyond that and we say, well, it could be adopted as currency in other countries besides El Salvador... Sure, but Why? What will be the benefit to that country unless they have a massive amount of Bitcoin already? It would not be fair for their citizens, basically, those institutions and governments that in few years will own the majority of the coins and the current wealthy Bitcoiners become the ones that can take advantage from that measure instead of the citizens of that country.

Countries would do well adding it to their reserves as they do with gold, but by no means it will be a P2P cash solution for the masses, nor it will help to solve the money problem.

Any options?

In my opinion is not that complicated, every nation could create a Bitcoin like currency with a cap of whatever it thinks it should be. Copying the Satoshi vision, nothing to do with the CBDC concept which is nothing but the same FIAT system with no cash.

That means that the coins should be capped at certain amount, Inmutable and Decentralized not controlled by the state and make it a legal tender with the regulation of the state equal to its current currency.

Technically is quite easy to implement, forking a privacy coin and making it more efficient to have instant payments as with Lightning Network will do the trick.

The effect of such measure will be a very strong currency that will benefit all their citizens equally. Sure, there is the current FIAT system with its tentacles everywhere, which needs to be transitioned and removed in parallel. Not a simple task, nor it will go down without a fight.

A fair launch of the token is required with no "genesis block", no "original address" (corruption) with a large percentage of the tokens. Nowadays, most states are corrupted and will most probably use the current currency printing machine to acquire as much as possible of the new currency making it a failed project from the start. Think about how much money the countries can print and buy Bitcoin with that money, think what they can do with it...

Regulation to avoid the governments from buying the tokens with printed money is required from the beginning.

Plausible, right?. The only needed action is to remove the corrupted and incompetent officials that are in the pockets of the nations landlords... Oh, but the landlords owns the judicial system and the military industrial complex so this seems to be a quite obvious and simple task but next to impossible to accomplish.

Baby steps?

We need legislation to separate the state from the private money. That alone will weaken the landlords over time and thus, little by little, their grip on the judicial system will perish and change can emerge with less opposition from the corrupted officials.

Is there a chance?

In my opinion, not in the short term.

The ones with political power and control over the world resources I call landlords, won't let go. Why will they?

Even in the miraculous scenario that few of those individuals or families decide to assist with the needed changes, others will take their place, therefore, I have no illusion it can be achieved rapidly or ever.

If you are very young, you still may be thinking that with few marches and protests the people can steer the direction of a nation, nothing more far from the truth... When it works it had been carefully planned and funded by a foreign country or nefarious group looking to change power in a nation to take advantage of its resources in one way or another and the naive youth is used to achieve the goal.

One possible scenario would be a sudden introduction of technologies that empower the individual to be free of the control of the system, the following three would be an excellent start:

1. Free energy (Tesla's dream...),
2. Free tech for the desalination of sea water,
3. Free access to atmospheric water devices for the production of drinking water from the humidity in the air.

But to believe that the current powers will not push back is naive. The most logical scenario is that they will make those technologies illegal and prosecute anyone sharing them or using them or tax them heavily as Spain did not long ago with the solar panels installed at home by individuals, surreal but it happened, it was called the "sun tax" implemented in October 2015 and removed in November 2018.

---

If you like my work and would like to support me:

@ fa984bd7:58018f52

I have recently launched Wikifreedia, which is a different take on how Wikipedia-style systems can work.

Yes, it's built on nostr, but that's not the most interesting part.

The fascinating aspect is that there is no "official" entry on any topic. Anyone can create or edit any entry and build their own take about what they care about.

Think the entry about Mao is missing something? Go ahead and edit it, you don't need to ask for permission from anyone.

Stuart Bowman put it best on a #SovEng hike:

The path to truth is in the integration of opposites.

Since launching Wikifreedia, less than a week ago, quite a few people asked me if it would be possible to import ALL of wikipedia into it.

Yes. Yes it would.

I initially started looking into it to make it happen as I am often quick to jump into action.

But, after thinking about it, I am not convinced importing all of Wikipedia is the way to go.

The magical thing about building an encyclopedia with no canonical entry on any topic is that each individual can bring to light the part they are interested the most about a certain topic, it can be dozens or hundreds, or perhaps more, entries that focus on the edges of a topic.

Whereas, Wikipedia, in their Quijotean approach to truth, have focused on the impossible path of seeking neutrality.

Humans can't be neutral, we have biases.

Show me an unbiased human and I'll show you a lifeless human.

Biases are good. Having an opinion is good. Seeking neutrality is seeking to devoid our views and opinions of humanity.

Importing Wikipedia would mean importing a massive amount of colorless trivia, a few interesting tidbits, but, more important than anything, a vast amount of watered-down useless information.

All edges of the truth having been neutered by a democratic process that searches for a single truth via consensus.

"What's the worst that could happen?"

Sure, importing wikipedia would simply be one more entry on each topic.

Yes.

But culture has incredibly strong momentum.

And if the culture that develops in this type of media is that of exclusively watered-down comfortable truths, then some magic could be lost.

If people who are passionate or have a unique perspective about a topic feel like the "right approach" is to use the wikipedia-based article then I would see this as an extremely negative action.

An alternative

An idea we discussed on the #SovEng hike was, what if the wikipedia entry is processed by different "AI agents" with different perspectives.

Perhaps instead of blankly importing the "Napoleon" article, an LLM trained to behave as a 1850s russian peasant could be asked to write a wiki about Napoleon. And then an agent tried to behave like Margaret Thatcher could write one.

Etc, etc.

Embrace the chaos. Embrace the bias.

@ 6871d8df:4a9396c1

In an era where data seems to be as valuable as currency, the prevailing trend in AI starkly contrasts with the concept of personal data ownership. The explosion of AI and the ensuing race have made it easy to overlook where the data is coming from. The current model, dominated by big tech players, involves collecting vast amounts of user data and selling it to AI companies for training LLMs. Reddit recently penned a 60 million dollar deal, Google guards and mines Youtube, and more are going this direction. But is that their data to sell? Yes, it's on their platforms, but without the users to generate it, what would they monetize? To me, this practice raises significant ethical questions, as it assumes that user data is a commodity that companies can exploit at will.

The heart of the issue lies in the ownership of data. Why, in today's digital age, do we not retain ownership of our data? Why can't our data follow us, under our control, to wherever we want to go? These questions echo the broader sentiment that while some in the tech industry — such as the blockchain-first crypto bros — recognize the importance of data ownership, their "blockchain for everything solutions," to me, fall significantly short in execution.

Reddit further complicates this with its current move to IPO, which, on the heels of the large data deal, might reinforce the mistaken belief that user-generated data is a corporate asset. Others, no doubt, will follow suit. This underscores the urgent need for a paradigm shift towards recognizing and respecting user data as personal property.

In my perfect world, the digital landscape would undergo a revolutionary transformation centered around the empowerment and sovereignty of individual data ownership. Platforms like Twitter, Reddit, Yelp, YouTube, and Stack Overflow, integral to our digital lives, would operate on a fundamentally different premise: user-owned data.

In this envisioned future, data ownership would not just be a concept but a practice, with public and private keys ensuring the authenticity and privacy of individual identities. This model would eliminate the private data silos that currently dominate, where companies profit from selling user data without consent. Instead, data would traverse a decentralized protocol akin to the internet, prioritizing user control and transparency.

The cornerstone of this world would be a meritocratic digital ecosystem. Success for companies would hinge on their ability to leverage user-owned data to deliver unparalleled value rather than their capacity to gatekeep and monetize information. If a company breaks my trust, I can move to a competitor, and my data, connections, and followers will come with me. This shift would herald an era where consent, privacy, and utility define the digital experience, ensuring that the benefits of technology are equitably distributed and aligned with the users' interests and rights.

The conversation needs to shift fundamentally. We must challenge this trajectory and advocate for a future where data ownership and privacy are not just ideals but realities. If we continue on our current path without prioritizing individual data rights, the future of digital privacy and autonomy is bleak. Big tech's dominance allows them to treat user data as a commodity, potentially selling and exploiting it without consent. This imbalance has already led to users being cut off from their digital identities and connections when platforms terminate accounts, underscoring the need for a digital ecosystem that empowers user control over data. Without changing direction, we risk a future where our content — and our freedoms by consequence — are controlled by a few powerful entities, threatening our rights and the democratic essence of the digital realm. We must advocate for a shift towards data ownership by individuals to preserve our digital freedoms and democracy.

@ 079d727b:00099650

Found these somewhere and I totally can't remember who authored the note. I THANK YOU! Also here's a reddit link for those who want to get started!

https://nostr.com/ - A decentralized social network with a chance of working

https://www.whynostr.com/ - the WHY https://www.heynostr.com/ - Introduction https://uselessshit.co/resources/nostr/ - Plentiful Guides and resources https://kyc3.life/resources/ - LIFE KYC (Know Your Customer) FREE (#IMPORTANT) https://www.reddit.com/r/nostr/ - Reddit Nostr Feed https://fountain.fm/show/0N6GGdZuYNNG7ysagCg9 - Plebchain Radio Podcast https://stacker.news/items/492921 - Guide by @TresDMan https://nostr.how/en/get-started - Understanding the basics https://www.nostrapps.com/ - A directory of Nostr Apps https://nak.nostr.com/ - nostr army knife (dev tool) https://nostrstuff.com/ - A terminal for playing with Nostr https://nostrfreaks.com/add/ - Multiple Web Client Viewer https://nostrends.vercel.app/ - What's trending on Nostr? https://nosta.me - Profile Viewer

And now here's a list of sites which are Nostr friendly.

R/nostr user's collection of nostr apps:

• https://nostr.watch/relays/find - Finding Nostr Relays (#IMPORTANT#)
• https://shopstr.store/marketplace - A Nostr Marketplace
• https://zap.stream/ - A Nostr Live Streaming Site
• https://formstr.app/ - Creating your own Forms on Nostr
• https://metadata.nostr.com/ - Nostr Profile Manager (#IMPORTANT#)
• https://shipyard.pub/posts - Write, schedule, and boost your notes.
• https://slidestr.net/ - Nostr Slideshow
• https://github.com/aljazceru/awesome-nostr - an AMAZING list of ALOT
• https://pinstr.app/ - Pinning content on Nostr
• https://plebeian.market/ - A Nostr Marketplace
• https://nostree.me/ - A Nostr Linktree
• https://listr.lol/feed - Curate, Organize, and Discover everything Nostr has
• https://www.wavlake.com/ - a V4V music streaming site on Nostr
• https://ostrich.work/ - The first and best Nostr Jobs board on the internet.
• https://zaplife.lol/ - A live feed of zaps
• https://highlighter.com/ - The site you're on right now!
• https://shopstr.store/ - An Nostr Marketplace
• https://nostr.band/ - A Nostr search engine
• https://nostrudel.ninja/#/ - A Nostr Client/Frontend
• https://dtan.xyz/ - A Nostr Torrent site
• https://app.mutinywallet.com/ - A Lightning wallet with Nostr Integration
• https://www.flockstr.com/ - Events and Meetups on Nostr
• https://cornychat.com/ - A live talk space on Nostr akin to Twitter Spaces
• https://nostrnests.com/ - A Live Talk Space on Nostr akin to Twitter Spaces
• https://comingle.co/ - conference app powered by Nostr
• https://geyser.fund/ - A crowdfunding site powered in part by Nostr
• https://heya.fund/ - Fund causes and goals with lightning on Nostr
• https://www.nostrchat.io/ - A Chat Client on Nostr
• https://w3.do/ - A URL Shortener on Nostr
• https://yakihonne.com/ - Long form writing on Nostr
• https://habla.news/ - Long form writing on Nostr
• https://nostrsync.live/ - A Broadcast & Export Service for your Data
• https://follows.lol/ - The Nostr follower tool
• https://globalthreat.info/ - Realtime global threat assessment driven by AI

There is ALOT more out there so I recommend you look at https://github.com/aljazceru/awesome-nostr !

Nostrapps is also excellent for finding web clients to actually view the twitter style of the Nostr.

I shall update this list from time to time with more or less content... hopefully. Or something cooler will come out and I'll use that. 🤷

@ 5144fe88:9587d5af

The answer to these bitcoin questions comes from an email correspondence between Martti Malmi and Bitcoin founder Satoshi Nakamoto on May 4, 2009. Although it has been 15 years, looking back now, it is still a timeless, simple and classic answer. Share it with everyone.

Address: https://mmalmi.github.io/satoshi/

* Bitcoin FAQ *

General Questions

1 What is bitcoin?

Bitcoin is a peer-to-peer network based anonymous digital currency. Peer-to-peer (P2P) means that there is no central authority to issue new money or to keep track of the transactions. Instead, those tasks are managed collectively by the nodes of the network. Anonymity means that the real world identity of the parties of a transaction can be kept hidden from the public or even from the parties themselves.

2 How does bitcoin work?

Bitcoin utilizes public/private key cryptography. When a coin is transfered from user A to user B, A adds B's public key to the coin and signs it with his own private key. Now B owns the coin and can transfer it further. To prevent A from transfering the already used coin to another user C, a public list of all the previous transactions is collectively maintained by the network of bitcoin nodes, and before each transaction the coin's unusedness will be checked.

For details, see chapter Advanced Questions.

3 What is bitcoin's value backed by?

Bitcoin is valued for the things it can be exchanged to, just like all the traditional paper currencies are.

When the first user publicly announces that he will make a pizza for anyone who gives him a hundred bitcoins, then he can use bitcoins as payment to some extent - as much as people want pizza and trust his announcement. A pizza-eating hairdresser who trusts him as a friend might then announce that she starts accepting bitcoins as payment for fancy haircuts, and the value of the bitcoin would be higher - now you could buy pizzas and haircuts with them. When bitcoins have become accepted widely enough, he could retire from his pizza business and still be able to use his bitcoin-savings.

4 How are new bitcoins created?

New coins are generated by a network node each time it finds the solution to a certain calculational problem. In the first 4 years of the bitcoin network, amount X of coins will be created. The amount is halved each 4 years, so it will be X/2 after 4 years, X/4 after 8 years and so on. Thus the total number of coins will approach 2X.

5 Is bitcoin safe?

Yes, as long as you make backups of your coin keys, protect them with strong passwords and keep keyloggers away from your computer. If you lose your key or if some unknown attacker manages to unlock it, there's no way to get your coins back. If you have a large amount of coins, it is recommended to distribute them under several keys. You propably wouldn't either keep all your dollars or euros as paper in a single wallet and leave it unguarded.

6 Why should I use bitcoin?

• Transfer money easily through the internet, without having to trust third parties.

• Third parties can't prevent or control your transactions.

• Be safe from the unfair monetary policies of the monopolistic central banks and the other risks of centralized power over a money supply. The limited inflation of the bitcoin system's money supply is distributed evenly (by CPU power) throughout the network, not monopolized to a banking elite.

• Bitcoin's value is likely to increase as the growth of the bitcoin economy exceeds the inflation rate - consider bitcoin an investment and start running a node today!

7 Where can I get bitcoins?

Find a bitcoin owner and sell her something - MMORPG equipement, IT support, lawn mowing, dollars or whatever you can trade with her. You can also generate new bitcoins for yourself by running a bitcoin network node.

@ 83d999a1:46171d19

It feels like yesterday when we decided to embark on the journey that was SEC-01. We didn’t know what we would get ourselves into. We still barely know. But just like the guy in the meme, we’re gonna do it again. We’re going to walk the walk, we’re going to ship things, and we’re going to have a good time while doing it.

https://m.primal.net/HpDG.mp4

We expect a lot of experimentation, discussion, and exploration. We expect that SEC-02 will rhyme with SEC-01, even though it won’t be a carbon copy of the first cohort. We’d encourage you to listen to this Plebchain Radio episode and (the end of) this Citadel Dispatch episode to get an idea of what we’re aiming for.

Scratching the Surface

Our thesis remains the same: The space that is opened up by Bitcoin, nostr, and other freedom tech is vast. We believe that we have barely scratched the surface. We believe that lots of awesome stuff is yet to be built, and we believe that the new paradigms will allow us to step outside of the extractive models that are so prevalent in the current landscape.

If you believe the same, you might be a perfect candidate for the second cohort—and you should apply today.

Markets, Synergies, and Peers

As foreshadowed in a previous post, we want to focus on peer-to-peer markets and exchange. With nostr acting as an effective and open layer for discoverability, and sats (and esats) acting as a bearer instrument for final settlement, what used to be siloed marketplaces can finally be opened up to merchants and customers alike.

It allows us to move from the win-lose of zero-sum games to the win-win-win of positive-sum games: good for you, good for me, good for everyone. In one word: Synergies.

We hope that the various peers that are working on these markets—as well as the building blocks that make them possible—will collaborate and learn from each other, just like they did in the first cohort. And even if your expertise is tangential, we hope that novel insights, products, and services will come out of it all. Just like they did in the first cohort.

That’s the basic idea of the Sovereign Engineering cohorts: Explore the unknown. Re-think how we do things online. Ship things that last.

Starting May 6 — Apply Now!

The second cohort will start on May 6 and will conclude on June 28, and just like the first one, it will be on the beautiful island of Madeira.

Applications are closing soon, but we still have a couple of spots left.

Apply now!

@ aa327517:15b95190

Hello friend

@ dadbe86a:9c493e92

Opinion about Casa: Bitcoin & Crypto Wallet (android)

Casa Wallet is the wallet developed by Casa, a leading provider of Bitcoin self-custody solutions. Designed to prioritize security, privacy, and ease of use. The wallet is part of their assisted self custody service. Let's analyze the wallet when you don't pay for that service.

Pros: - Support for testnet and fee control

Cons: - Not bitcoin only, it also supports Ethereum, which is bad for pure bitcoiners - A login is required to use the wallet - Missing advanced features like passphrase, user added entropy, bip39 backups, seedQR, native segwit, taproot, coin control, custom node, miniscript, etc - You can't use multisig unless you pay a subscription - Only supporting Trezor, Coldcard and Ledger - Closed source

Version reviewed: v4.14.2

thebitcoinhole.com

WalletScrutiny #nostrOpinion

Join the conversation!

@ e1ff3bfd:341be1af

Ben's fuck the bears book

Only sign this if you want to fuck the bears

@ acb9956c:b2d42453

• It is almost April!
• How about this external image ?
• Do something to your hair.
• Have you ever eaten a spoon full of peanut butter ?
• Have you ever eaten a spoon full of ketchup ?
• Do you like spiders ?
• How about this external image ?

@ dadbe86a:9c493e92

Opinion about AQUA Wallet (android)

Aqua wallet is a all-in-one Bitcoin wallet, where you can hold, swap and transact with bitcoin and gain easy access to Lightning and the Liquid Network.

Pros: - Given that it supports the Liquid Network, we can't say it is Bitcoin only. This is going to be an advantage for the people that need to swap and transact with Liquid, but a disadvantage for pure bitcoiners. - Open source

Cons: - Missing advanced features like testnet, user added entropy, pasphrase, seedQR, taproot, coin control, custom nodes, multisig, etc - Missing support to connect with a hardware wallet - No support to lock the app

Version reviewed: v0.1.30

thebitcoinhole.com

WalletScrutiny #nostrOpinion

Join the conversation!

@ 50c6ce2e:25cf57db

Test

@ 6871d8df:4a9396c1

The Apple Vision Pro was released, and it is the talk of the town right now. To be frank, I think it's a stupid product. It's not useful or particularly enticing to me in its current form factor. It's a toy, not a tool. All the features seem gimmicky as opposed to generally helpful. I'm not saying it may never be worthwhile, but as of this first release, it is only a party trick.

Coincidently, this is the first product that does not have any of Steve Jobs' influence. To me, it shows. I don't think Jobs would have ever let this product see the light of day.


Jobs understood product. He didn't make things for the sake of progress or to make sci-fi reality; he made things because he 'wanted to make a dent in the world.' He wanted to solve problems for everyday people by innovating with cutting-edge technology. He aspired to make people's lives better. Steve Jobs' genius was the way he married cutting-edge technologies with valuable tools that made those cutting-edge technologies simple and elegant.


The Vision Pro may be technically innovative, but it is not a tool, at least in its current form. It may be one day, but that is precisely my point; Jobs would have never released a product where the form factor would hold it back from becoming a tool. At best, it is an intriguing toy that is additive to some content at the behest of being very awkward to wear or be seen in. In my view, mainstream adoption can happen only in a world where we can use the Vision Pro as a contact lens or very small, discreet, minimalist glasses, but certainly not this iteration where it covers more than half your face.


Seeing people's eyes makes us human. So much emotion, understanding, and communication happens with just a look. It is a window into the soul. I don't want to live in a world where we are actively bringing all the negatives about communicating in the digital world to the physical one.

https://image.nostr.build/2365609411f144f5d789ffd684ffce9b4d867626a7bfe11bb311cb0f61057199.jpg

I can't help but wonder or hypothesize what Steve Jobs would focus on if he were still alive today. I think Apple's priorities would be completely different. My gut tells me he would not have let Siri get as bad as it is. Siri is a horrible product; I never use it, and everyone I know who tries to use it does so unsuccessfully, at least most of the time. I personally always default to ChatGPT or Bard. These AI systems make my life dramatically more productive. They are tools in the purest sense.

In my opinion, Steve would not have missed this train. Sure, Apple could wake up and integrate these systems into Siri — if they were smart, they would — but in its current form, it is so far behind that it almost astounds me. My intuition leads me to believe he would be closer to what [Rabbit] is doing.

Who knows? Maybe I am entirely wrong, and Apple just kickstarted VR's mass adoption phase. Unfortunately, I think this will likely be the biggest failure of a physical product that Apple will have seen since Jobs returned ages ago. The Vision Pro is only slightly better than the Oculus, and Facebook has already deprioritized VR for AI. Apple is further behind, and I don't see a world where they do not make the same pivot. There is a skill to creating successful, innovative products, and it makes me sad to see the torch that Jobs passed lose its flame. As someone who respected how Apple used to innovate, watching this decay in real-time is jarring as this is just the latest in a string of disappointing decisions that exemplify that 'peak Apple' is behind us.

@ 044b20cf:89e58620

Hatsune Miku in Crypt of the Necrodancer feels like the perfect crossover

Crypt of the Necrodancer (https://www.engadget.com/2013-08-31-pounding-beats-and-dragons-in-crypt-of-the-necrodancer.html) just won’t die — and that’s a good thing. The nearly decade-old roguelike rhythm game (https://www.engadget.com/2015-01-09-gdca-2015-finalists-led-by-middle-earth-shadow-of-mordor.html) received new content on Thursday, bringing virtual pop star Hatsune Miku into the fold as a playable character.

Developer Brace Yourself Games says Hatsune Miku is one of the more challenging characters in the game. She can move in all eight directions and takes out foes by boogying her way through groups of enemies. The developer’s press release explains, “She doesn’t have a shovel like most characters, so she must use her dance-like dash attack to break through walls instead.” Hell yeah.

She has a “Sing!” ability — entirely new to the game — that charms nearby enemies. When one of these charmed foes strikes Miku, she heals instead of losing her health. Brace Yourself Games says it even reskinned all of the game’s armors as official Miku outfits, so you can put on new threads as you shimmy and groove your way through legions of ghosts and skeletons.

Photo by Mat Smith / Engadget

If you aren’t familiar, Hatsune Miku is one of the world’s biggest virtual pop stars (https://www.engadget.com/2016-02-02-hatsune-miku.html). She’s a perpetual 16-year-old because she’s the personification of a “Vocaloid,” software that synthesizes pre-recorded vocals to simulate human singing. The avatar has sold out 14,000-seat arenas, collaborated with Pharrell Williams and opened for Lady Gaga (https://www.youtube.com/watch?v=OYlRN6XWsDE). She wasn’t the first digital celebrity, but she may be the most famous.

The Hatsune Miku DLC for Crypt of the Necrodancer is available now for $1.99 on the PlayStation Store (https://store.playstation.com/en-us/product/UP1162-CUSA03610_00-COLDSTEEL0000000) and PC via Steam. The content arrives a little later on Switch — on April 13. Check out her moves in the trailer below.

This article originally appeared on Engadget at https://www.engadget.com/hatsune-miku-in-crypt-of-the-necrodancer-feels-like-the-perfect-crossover-203138973.html?src=rss

https://www.engadget.com/hatsune-miku-in-crypt-of-the-necrodancer-feels-like-the-perfect-crossover-203138973.html?src=rss

@ fa984bd7:58018f52

I just hit the big red PUBLISH button on NDK 2.4.

(well, actually, I did it from the command line, the big red button is imaginary)

Codename: Safely Embrace the Chaos

Nostr is a, mostly, friendly environment with not too many developers and no ill-intent among them.

But this will not always be the case. Compatibility issues, mistakes, and all kinds of chaos is to be expected.

This version of NDK introduces validation at the library-level so that clients built using NDK can rely on some guarantees on handled-kinds that events they are consuming comply with what is defined on their respective NIPs.

An example?

NIP-88, recurring subscriptions, defines that Tier events should have amount tags of what subscribers are expected to pay and the cadence.

Prior to NDK 2.4 some malformed events would render like this:

https://i.nostr.build/Y4JG.png

But with NDK 2.4 the malformed parts of the events don't reach the client code.

https://i.nostr.build/wAgJ.png

This is just a beginning, but event-validation is now moving into the library!

@ 46fcbe30:6bd8ce4d

Opinion about AirGap Vault - Secure Secrets (android)

AirGap Vault turns your old cellphone into a hardware wallet. While there are concerns about all the software running on a cellphone and radio capabilities that might get activated despite you not putting a sim card into the phone, this is a pretty solid MIT licensed open source project that gives you more features than a Blockstream Jade ($65) or a Foundation Passport ($199) essentially for free if you have an old phone laying around. If only it wasn't so much into shitcoins ...

AirGap Vault supports: When paired with MetaMask - All EVM-compatible blockchains

When paired with AirGap Wallet - Bitcoin - BTC, - Ethereum - ETH, - Polkadot - DOT, - Kusama - KSM, - Tezos - XTZ, - Cosmos - ATOM, - Moonbeam - GLMR, - Moonriver - MOVR, - Astar - ASTR, - Shiden - SDN, - Aeternity - AE, - Groestlcoin - GRS

It asks for camera and microphone permission to collect entropy which takes quite long and if your screen safer switches on while you are writing down the mnemonic, ... you have to start over. Then you have to pick accounts. I went with Legacy and Segwit BTC and the "Deriving your wallet..." modal doesn't even spin for minutes. ... but ... with a bit of patience ... yeah! It works. Now it can be used with Sparrow for example. Or a bunch of other companion apps.

I so far like this product mainly because it's open source, air-gapped and reproducible since many years.

WalletScrutiny #nostrOpinion

Join the conversation!

@ 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.

@ 044b20cf:89e58620

A new series of Star Wars shorts premieres on Disney+ next month

Disney (https://shopping.yahoo.com/rdlw?merchantId=85d85ef3-fac9-418f-9573-418cf162cd0c&siteId=us-engadget&pageId=1p-autolink&featureId=text-link&merchantName=Disney%2B&custData=eyJzb3VyY2VOYW1lIjoiV2ViLURlc2t0b3AtVmVyaXpvbiIsImxhbmRpbmdVcmwiOiJodHRwczovL3d3dy5kaXNuZXlwbHVzLmNvbS8iLCJjb250ZW50VXVpZCI6IjJlYzhhNzEzLWJkNjYtNDhlMS1iMDAxLTVkOWEyMzM0Zjg2MyJ9&signature=AQAAAcoOBk1LX8mIjwuXbRIBM8xYheY9zNwsoAjQz4-HUgHm&gcReferrer=https%3A%2F%2Fwww.disneyplus.com%2F) just pulled a fast one. Star Wars movies and shows are typically announced years before being released, but the company just revealed a new TV program that premieres next month. Tales of the Empire is an animated show produced by Dave Filoni, the man who cut his teeth on cartoons like Star Wars: The Clone Wars and Star Wars Rebels before moving onto live action stuff like Ahsoka (https://www.engadget.com/ahsoka-review-star-wars-disney-193023619.html).

As the name suggests, this is something of a companion piece to 2022’s Tales of the Jedi. It’s an anthology series that spotlights different characters within the empire as they, uh, heroically try to defeat the nefarious rebels and bring order to the galaxy. You can expect appearances by many of your dark side faves, including Grand Admiral Thrawn, General Grievous and the Grand Inquisitor.

Just like how Tales of the Jedi put the spotlight on two characters, Ahsoka and Count Dooku, this new series will have its own duo to follow. There’s Morgan Elsbeth, a primary antagonist in Ahsoka and one episode of The Mandalorian, with the trailer indicating that Tales of the Empire will reveal how Thrawn and Elsbeth became besties. The show will also focus on Barriss Offee, a former Jedi Knight who fell to the dark side during the Clone Wars.

Despite being animated, the characters will be played by their live action actors. Lars Mikkelsen returns as Thrawn and Matthew Wood is once again portraying Grievous, the evil cyborg who is in dire need of some cough syrup. Diana Lee Inosanto is back as Elsbeth and Meredith Salenger is voicing Offee.

The show premieres on everyone’s favorite corporate-sponsored pseudo-holiday, May the Fourth, also known as May 4. All six episodes will be available to stream on Disney+ (https://shopping.yahoo.com/rdlw?merchantId=85d85ef3-fac9-418f-9573-418cf162cd0c&siteId=us-engadget&pageId=1p-autolink&featureId=text-link&merchantName=Disney%2B&custData=eyJzb3VyY2VOYW1lIjoiV2ViLURlc2t0b3AtVmVyaXpvbiIsImxhbmRpbmdVcmwiOiJodHRwczovL3d3dy5kaXNuZXlwbHVzLmNvbS8iLCJjb250ZW50VXVpZCI6IjJlYzhhNzEzLWJkNjYtNDhlMS1iMDAxLTVkOWEyMzM0Zjg2MyJ9&signature=AQAAAcoOBk1LX8mIjwuXbRIBM8xYheY9zNwsoAjQz4-HUgHm&gcReferrer=https%3A%2F%2Fwww.disneyplus.com%2F) upon the release date. The live action Star Wars: Acolyte follows this with a premiere on June 4 (https://www.engadget.com/watch-disneys-official-trailer-for-star-wars-the-acolyte-150246523.html).

This article originally appeared on Engadget at https://www.engadget.com/a-new-series-of-star-wars-shorts-premieres-on-disney-next-month-190007395.html?src=rss

https://www.engadget.com/a-new-series-of-star-wars-shorts-premieres-on-disney-next-month-190007395.html?src=rss

@ 3bf0c63f:aefa459d

Nostr: a quick introduction, attempt #1

Nostr doesn't have a material existence, it is not a website or an app. Nostr is just a description what kind of messages each computer can send to the others and vice-versa. It's a very simple thing, but the fact that such description exists allows different apps to connect to different servers automatically, without people having to talk behind the scenes or sign contracts or anything like that.

When you use a Nostr client that is what happens, your client will connect to a bunch of servers, called relays, and all these relays will speak the same "language" so your client will be able to publish notes to them all and also download notes from other people.

That's basically what Nostr is: this communication layer between the client you run on your phone or desktop computer and the relay that someone else is running on some server somewhere. There is no central authority dictating who can connect to whom or even anyone who knows for sure where each note is stored.

If you think about it, Nostr is very much like the internet itself: there are millions of websites out there, and basically anyone can run a new one, and there are websites that allow you to store and publish your stuff on them.

The added benefit of Nostr is that this unified "language" that all Nostr clients speak allow them to switch very easily and cleanly between relays. So if one relay decides to ban someone that person can switch to publishing to others relays and their audience will quickly follow them there. Likewise, it becomes much easier for relays to impose any restrictions they want on their users: no relay has to uphold a moral ground of "absolute free speech": each relay can decide to delete notes or ban users for no reason, or even only store notes from a preselected set of people and no one will be entitled to complain about that.

There are some bad things about this design: on Nostr there are no guarantees that relays will have the notes you want to read or that they will store the notes you're sending to them. We can't just assume all relays will have everything — much to the contrary, as Nostr grows more relays will exist and people will tend to publishing to a small set of all the relays, so depending on the decisions each client takes when publishing and when fetching notes, users may see a different set of replies to a note, for example, and be confused.

Another problem with the idea of publishing to multiple servers is that they may be run by all sorts of malicious people that may edit your notes. Since no one wants to see garbage published under their name, Nostr fixes that by requiring notes to have a cryptographic signature. This signature is attached to the note and verified by everybody at all times, which ensures the notes weren't tampered (if any part of the note is changed even by a single character that would cause the signature to become invalid and then the note would be dropped). The fix is perfect, except for the fact that it introduces the requirement that each user must now hold this 63-character code that starts with "nsec1", which they must not reveal to anyone. Although annoying, this requirement brings another benefit: that users can automatically have the same identity in many different contexts and even use their Nostr identity to login to non-Nostr websites easily without having to rely on any third-party.

To conclude: Nostr is like the internet (or the internet of some decades ago): a little chaotic, but very open. It is better than the internet because it is structured and actions can be automated, but, like in the internet itself, nothing is guaranteed to work at all times and users many have to do some manual work from time to time to fix things. Plus, there is the cryptographic key stuff, which is painful, but cool.

@ 3bf0c63f:aefa459d

Pequenos problemas que o Estado cria para a sociedade e que não são sempre lembrados

- **vale-transporte**: transferir o custo com o transporte do funcionário para um terceiro o estimula a morar longe de onde trabalha, já que morar perto é normalmente mais caro e a economia com transporte é inexistente.
- **atestado médico**: o direito a faltar o trabalho com atestado médico cria a exigência desse atestado para todas as situações, substituindo o livre acordo entre patrão e empregado e sobrecarregando os médicos e postos de saúde com visitas desnecessárias de assalariados resfriados.
- **prisões**: com dinheiro mal-administrado, burocracia e péssima alocação de recursos -- problemas que empresas privadas em competição (ou mesmo sem qualquer competição) saberiam resolver muito melhor -- o Estado fica sem presídios, com os poucos existentes entupidos, muito acima de sua alocação máxima, e com isto, segundo a bizarra corrente de responsabilidades que culpa o juiz que condenou o criminoso por sua morte na cadeia, juízes deixam de condenar à prisão os bandidos, soltando-os na rua.
- **justiça**: entrar com processos é grátis e isto faz proliferar a atividade dos advogados que se dedicam a criar problemas judiciais onde não seria necessário e a entupir os tribunais, impedindo-os de fazer o que mais deveriam fazer.
- **justiça**: como a justiça só obedece às leis e ignora acordos pessoais, escritos ou não, as pessoas não fazem acordos, recorrem sempre à justiça estatal, e entopem-na de assuntos que seriam muito melhor resolvidos entre vizinhos.
- **leis civis**: as leis criadas pelos parlamentares ignoram os costumes da sociedade e são um incentivo a que as pessoas não respeitem nem criem normas sociais -- que seriam maneiras mais rápidas, baratas e satisfatórias de resolver problemas.
- **leis de trãnsito**: quanto mais leis de trânsito, mais serviço de fiscalização são delegados aos policiais, que deixam de combater crimes por isto (afinal de contas, eles não querem de fato arriscar suas vidas combatendo o crime, a fiscalização é uma excelente desculpa para se esquivarem a esta responsabilidade).
- **financiamento educacional**: é uma espécie de subsídio às faculdades privadas que faz com que se criem cursos e mais cursos que são cada vez menos recheados de algum conhecimento ou técnica útil e cada vez mais inúteis.
- **leis de tombamento**: são um incentivo a que o dono de qualquer área ou construção "histórica" destrua todo e qualquer vestígio de história que houver nele antes que as autoridades descubram, o que poderia não acontecer se ele pudesse, por exemplo, usar, mostrar e se beneficiar da história daquele local sem correr o risco de perder, de fato, a sua propriedade.
- **zoneamento urbano**: torna as cidades mais espalhadas, criando uma necessidade gigantesca de carros, ônibus e outros meios de transporte para as pessoas se locomoverem das zonas de moradia para as zonas de trabalho.
- **zoneamento urbano**: faz com que as pessoas percam horas no trânsito todos os dias, o que é, além de um desperdício, um atentado contra a sua saúde, que estaria muito melhor servida numa caminhada diária entre a casa e o trabalho.
- **zoneamento urbano**: torna ruas e as casas menos seguras criando zonas enormes, tanto de residências quanto de indústrias, onde não há movimento de gente alguma.
- **escola obrigatória + currículo escolar nacional**: emburrece todas as crianças.
- **leis contra trabalho infantil**: tira das crianças a oportunidade de aprender ofícios úteis e levar um dinheiro para ajudar a família.
- **licitações**: como não existem os critérios do mercado para decidir qual é o melhor prestador de serviço, criam-se comissões de pessoas que vão decidir coisas. isto incentiva os prestadores de serviço que estão concorrendo na licitação a tentar comprar os membros dessas comissões. isto, fora a corrupção, gera problemas reais: __(i)__ a escolha dos serviços acaba sendo a pior possível, já que a empresa prestadora que vence está claramente mais dedicada a comprar comissões do que a fazer um bom trabalho (este problema afeta tantas áreas, desde a construção de estradas até a qualidade da merenda escolar, que é impossível listar aqui); __(ii)__ o processo corruptor acaba, no longo prazo, eliminando as empresas que prestavam e deixando para competir apenas as corruptas, e a qualidade tende a piorar progressivamente.
- **cartéis**: o Estado em geral cria e depois fica refém de vários grupos de interesse. o caso dos taxistas contra o Uber é o que está na moda hoje (e o que mostra como os Estados se comportam da mesma forma no mundo todo).
- **multas**: quando algum indivíduo ou empresa comete uma fraude financeira, ou causa algum dano material involuntário, as vítimas do caso são as pessoas que sofreram o dano ou perderam dinheiro, mas o Estado tem sempre leis que prevêem multas para os responsáveis. A justiça estatal é sempre muito rígida e rápida na aplicação dessas multas, mas relapsa e vaga no que diz respeito à indenização das vítimas. O que em geral acontece é que o Estado aplica uma enorme multa ao responsável pelo mal, retirando deste os recursos que dispunha para indenizar as vítimas, e se retira do caso, deixando estas desamparadas.
- **desapropriação**: o Estado pode pegar qualquer propriedade de qualquer pessoa mediante uma indenização que é necessariamente inferior ao valor da propriedade para o seu presente dono (caso contrário ele a teria vendido voluntariamente).
- **seguro-desemprego**: se há, por exemplo, um prazo mínimo de 1 ano para o sujeito ter direito a receber seguro-desemprego, isto o incentiva a planejar ficar apenas 1 ano em cada emprego (ano este que será sucedido por um período de desemprego remunerado), matando todas as possibilidades de aprendizado ou aquisição de experiência naquela empresa específica ou ascensão hierárquica.
- **previdência**: a previdência social tem todos os defeitos de cálculo do mundo, e não importa muito ela ser uma forma horrível de poupar dinheiro, porque ela tem garantias bizarras de longevidade fornecidas pelo Estado, além de ser compulsória. Isso serve para criar no imaginário geral a idéia da __aposentadoria__, uma época mágica em que todos os dias serão finais de semana. A idéia da aposentadoria influencia o sujeito a não se preocupar em ter um emprego que faça sentido, mas sim em ter um trabalho qualquer, que o permita se aposentar.
- **regulamentação impossível**: milhares de coisas são proibidas, há regulamentações sobre os aspectos mais mínimos de cada empreendimento ou construção ou espaço. se todas essas regulamentações fossem exigidas não haveria condições de produção e todos morreriam. portanto, elas não são exigidas. porém, o Estado, ou um agente individual imbuído do poder estatal pode, se desejar, exigi-las todas de um cidadão inimigo seu. qualquer pessoa pode viver a vida inteira sem cumprir nem 10% das regulamentações estatais, mas viverá também todo esse tempo com medo de se tornar um alvo de sua exigência, num estado de terror psicológico.
- **perversão de critérios**: para muitas coisas sobre as quais a sociedade normalmente chegaria a um valor ou comportamento "razoável" espontaneamente, o Estado dita regras. estas regras muitas vezes não são obrigatórias, são mais "sugestões" ou limites, como o salário mínimo, ou as 44 horas semanais de trabalho. a sociedade, porém, passa a usar esses valores como se fossem o normal. são raras, por exemplo, as ofertas de emprego que fogem à regra das 44h semanais.
- **inflação**: subir os preços é difícil e constrangedor para as empresas, pedir aumento de salário é difícil e constrangedor para o funcionário. a inflação força as pessoas a fazer isso, mas o aumento não é automático, como alguns economistas podem pensar (enquanto alguns outros ficam muito satisfeitos de que esse processo seja demorado e difícil).
- **inflação**: a inflação destrói a capacidade das pessoas de julgar preços entre concorrentes usando a própria memória.
- **inflação**: a inflação destrói os cálculos de lucro/prejuízo das empresas e prejudica enormemente as decisões empresariais que seriam baseadas neles.
- **inflação**: a inflação redistribui a riqueza dos mais pobres e mais afastados do sistema financeiro para os mais ricos, os bancos e as megaempresas.
- **inflação**: a inflação estimula o endividamento e o consumismo.
- **lixo:** ao prover coleta e armazenamento de lixo "grátis para todos" o Estado incentiva a criação de lixo. se tivessem que pagar para que recolhessem o seu lixo, as pessoas (e conseqüentemente as empresas) se empenhariam mais em produzir coisas usando menos plástico, menos embalagens, menos sacolas.
- **leis contra crimes financeiros:** ao criar legislação para dificultar acesso ao sistema financeiro por parte de criminosos a dificuldade e os custos para acesso a esse mesmo sistema pelas pessoas de bem cresce absurdamente, levando a um percentual enorme de gente incapaz de usá-lo, para detrimento de todos -- e no final das contas os grandes criminosos ainda conseguem burlar tudo.

@ 5efdc05b:e0f285ae

• It is almost April!
• How about this external image ?
• Do something to your hair.
• Have you ever eaten a spoon full of peanut butter ?
• Have you ever eaten a spoon full of ketchup ?
• Do you like spiders ?
• How about this external image ?

@ 3bf0c63f:aefa459d

bitcoind decentralization

It is better to have multiple curator teams, with different vetting processes and release schedules for bitcoind than a single one.

"More eyes on code", "Contribute to Core", "Everybody should audit the code".

All these points repeated again and again fell to Earth on the day it was discovered that Bitcoin Core developers merged a variable name change from "blacklist" to "blocklist" without even discussing or acknowledging the fact that that innocent pull request opened by a sybil account was a social attack.

After a big lot of people manifested their dissatisfaction with that event on Twitter and on GitHub, most Core developers simply ignored everybody's concerns or even personally attacked people who were complaining.

The event has shown that:

1) Bitcoin Core ultimately rests on the hands of a couple maintainers and they decide what goes on the GitHub repository[^pr-merged-very-quickly] and the binary releases that will be downloaded by thousands; 2) Bitcoin Core is susceptible to social attacks; 2) "More eyes on code" don't matter, as these extra eyes can be ignored and dismissed.

Solution: bitcoind decentralization

If usage was spread across 10 different bitcoind flavors, the network would be much more resistant to social attacks to a single team.

This has nothing to do with the question on if it is better to have multiple different Bitcoin node implementations or not, because here we're basically talking about the same software.

Multiple teams, each with their own release process, their own logo, some subtle changes, or perhaps no changes at all, just a different name for their bitcoind flavor, and that's it.

Every day or week or month or year, each flavor merges all changes from Bitcoin Core on their own fork. If there's anything suspicious or too leftist (or perhaps too rightist, in case there's a leftist bitcoind flavor), maybe they will spot it and not merge.

This way we keep the best of both worlds: all software development, bugfixes, improvements goes on Bitcoin Core, other flavors just copy. If there's some non-consensus change whose efficacy is debatable, one of the flavors will merge on their fork and test, and later others -- including Core -- can copy that too. Plus, we get resistant to attacks: in case there is an attack on Bitcoin Core, only 10% of the network would be compromised. the other flavors would be safe.

Run Bitcoin Knots

The first example of a bitcoind software that follows Bitcoin Core closely, adds some small changes, but has an independent vetting and release process is Bitcoin Knots, maintained by the incorruptible Luke DashJr.

Next time you decide to run bitcoind, run Bitcoin Knots instead and contribute to bitcoind decentralization!

---

See also:

• How to attack Bitcoin, Anthony Towns' take

[^pr-merged-very-quickly]: See PR 20624, for example, a very complicated change that could be introducing bugs or be a deliberate attack, merged in 3 days without time for discussion.

@ 3bf0c63f:aefa459d

Drivechain

Understanding Drivechain requires a shift from the paradigm most bitcoiners are used to. It is not about "trustlessness" or "mathematical certainty", but game theory and incentives. (Well, Bitcoin in general is also that, but people prefer to ignore it and focus on some illusion of trustlessness provided by mathematics.)

Here we will describe the basic mechanism (simple) and incentives (complex) of "hashrate escrow" and how it enables a 2-way peg between the mainchain (Bitcoin) and various sidechains.

The full concept of "Drivechain" also involves blind merged mining (i.e., the sidechains mine themselves by publishing their block hashes to the mainchain without the miners having to run the sidechain software), but this is much easier to understand and can be accomplished either by the BIP-301 mechanism or by the Spacechains mechanism.

How does hashrate escrow work from the point of view of Bitcoin?

A new address type is created. Anything that goes in that is locked and can only be spent if all miners agree on the Withdrawal Transaction (WT^) that will spend it for 6 months. There is one of these special addresses for each sidechain.

To gather miners' agreement bitcoind keeps track of the "score" of all transactions that could possibly spend from that address. On every block mined, for each sidechain, the miner can use a portion of their coinbase to either increase the score of one WT^ by 1 while decreasing the score of all others by 1; or they can decrease the score of all WT^s by 1; or they can do nothing.

Once a transaction has gotten a score high enough, it is published and funds are effectively transferred from the sidechain to the withdrawing users.

If a timeout of 6 months passes and the score doesn't meet the threshold, that WT^ is discarded.

What does the above procedure mean?

It means that people can transfer coins from the mainchain to a sidechain by depositing to the special address. Then they can withdraw from the sidechain by making a special withdraw transaction in the sidechain.

The special transaction somehow freezes funds in the sidechain while a transaction that aggregates all withdrawals into a single mainchain WT^, which is then submitted to the mainchain miners so they can start voting on it and finally after some months it is published.

Now the crucial part: the validity of the WT^ is not verified by the Bitcoin mainchain rules, i.e., if Bob has requested a withdraw from the sidechain to his mainchain address, but someone publishes a wrong WT^ that instead takes Bob's funds and sends them to Alice's main address there is no way the mainchain will know that. What determines the "validity" of the WT^ is the miner vote score and only that. It is the job of miners to vote correctly -- and for that they may want to run the sidechain node in SPV mode so they can attest for the existence of a reference to the WT^ transaction in the sidechain blockchain (which then ensures it is ok) or do these checks by some other means.

What? 6 months to get my money back?

Yes. But no, in practice anyone who wants their money back will be able to use an atomic swap, submarine swap or other similar service to transfer funds from the sidechain to the mainchain and vice-versa. The long delayed withdraw costs would be incurred by few liquidity providers that would gain some small profit from it.

Why bother with this at all?

Drivechains solve many different problems:

It enables experimentation and new use cases for Bitcoin

Issued assets, fully private transactions, stateful blockchain contracts, turing-completeness, decentralized games, some "DeFi" aspects, prediction markets, futarchy, decentralized and yet meaningful human-readable names, big blocks with a ton of normal transactions on them, a chain optimized only for Lighting-style networks to be built on top of it.

These are some ideas that may have merit to them, but were never actually tried because they couldn't be tried with real Bitcoin or inferfacing with real bitcoins. They were either relegated to the shitcoin territory or to custodial solutions like Liquid or RSK that may have failed to gain network effect because of that.

It solves conflicts and infighting

Some people want fully private transactions in a UTXO model, others want "accounts" they can tie to their name and build reputation on top; some people want simple multisig solutions, others want complex code that reads a ton of variables; some people want to put all the transactions on a global chain in batches every 10 minutes, others want off-chain instant transactions backed by funds previously locked in channels; some want to spend, others want to just hold; some want to use blockchain technology to solve all the problems in the world, others just want to solve money.

With Drivechain-based sidechains all these groups can be happy simultaneously and don't fight. Meanwhile they will all be using the same money and contributing to each other's ecosystem even unwillingly, it's also easy and free for them to change their group affiliation later, which reduces cognitive dissonance.

It solves "scaling"

Multiple chains like the ones described above would certainly do a lot to accomodate many more transactions that the current Bitcoin chain can. One could have special Lightning Network chains, but even just big block chains or big-block-mimblewimble chains or whatnot could probably do a good job. Or even something less cool like 200 independent chains just like Bitcoin is today, no extra features (and you can call it "sharding"), just that would already multiply the current total capacity by 200.

Use your imagination.

It solves the blockchain security budget issue

The calculation is simple: you imagine what security budget is reasonable for each block in a world without block subsidy and divide that for the amount of bytes you can fit in a single block: that is the price to be paid in satoshis per byte. In reasonable estimative, the price necessary for every Bitcoin transaction goes to very large amounts, such that not only any day-to-day transaction has insanely prohibitive costs, but also Lightning channel opens and closes are impracticable.

So without a solution like Drivechain you'll be left with only one alternative: pushing Bitcoin usage to trusted services like Liquid and RSK or custodial Lightning wallets. With Drivechain, though, there could be thousands of transactions happening in sidechains and being all aggregated into a sidechain block that would then pay a very large fee to be published (via blind merged mining) to the mainchain. Bitcoin security guaranteed.

It keeps Bitcoin decentralized

Once we have sidechains to accomodate the normal transactions, the mainchain functionality can be reduced to be only a "hub" for the sidechains' comings and goings, and then the maximum block size for the mainchain can be reduced to, say, 100kb, which would make running a full node very very easy.

Can miners steal?

Yes. If a group of coordinated miners are able to secure the majority of the hashpower and keep their coordination for 6 months, they can publish a WT^ that takes the money from the sidechains and pays to themselves.

Will miners steal?

No, because the incentives are such that they won't.

Although it may look at first that stealing is an obvious strategy for miners as it is free money, there are many costs involved:

1. The cost of ceasing blind-merged mining returns -- as stealing will kill a sidechain, all the fees from it that miners would be expected to earn for the next years are gone;
2. The cost of Bitcoin price going down: If a steal is successful that will mean Drivechains are not safe, therefore Bitcoin is less useful, and miner credibility will also be hurt, which are likely to cause the Bitcoin price to go down, which in turn may kill the miners' businesses and savings;
3. The cost of coordination -- assuming miners are just normal businesses, they just want to do their work and get paid, but stealing from a Drivechain will require coordination with other miners to conduct an immoral act in a way that has many pitfalls and is likely to be broken over the months;
4. The cost of miners leaving your mining pool: when we talked about "miners" above we were actually talking about mining pools operators, so they must also consider the risk of miners migrating from their mining pool to others as they begin the process of stealing;
5. The cost of community goodwill -- when participating in a steal operation, a miner will suffer a ton of backlash from the community. Even if the attempt fails at the end, the fact that it was attempted will contribute to growing concerns over exaggerated miners power over the Bitcoin ecosystem, which may end up causing the community to agree on a hard-fork to change the mining algorithm in the future, or to do something to increase participation of more entities in the mining process (such as development or cheapment of new ASICs), which have a chance of decreasing the profits of current miners.

Another point to take in consideration is that one may be inclined to think a newly-created sidechain or a sidechain with relatively low usage may be more easily stolen from, since the blind merged mining returns from it (point 1 above) are going to be small -- but the fact is also that a sidechain with small usage will also have less money to be stolen from, and since the other costs besides 1 are less elastic at the end it will not be worth stealing from these too.

All of the above consideration are valid only if miners are stealing from good sidechains. If there is a sidechain that is doing things wrong, scamming people, not being used at all, or is full of bugs, for example, that will be perceived as a bad sidechain, and then miners can and will safely steal from it and kill it, which will be perceived as a good thing by everybody.

What do we do if miners steal?

Paul Sztorc has suggested in the past that a user-activated soft-fork could prevent miners from stealing, i.e., most Bitcoin users and nodes issue a rule similar to this one to invalidate the inclusion of a faulty WT^ and thus cause any miner that includes it in a block to be relegated to their own Bitcoin fork that other nodes won't accept.

This suggestion has made people think Drivechain is a sidechain solution backed by user-actived soft-forks for safety, which is very far from the truth. Drivechains must not and will not rely on this kind of soft-fork, although they are possible, as the coordination costs are too high and no one should ever expect these things to happen.

If even with all the incentives against them (see above) miners do still steal from a good sidechain that will mean the failure of the Drivechain experiment. It will very likely also mean the failure of the Bitcoin experiment too, as it will be proven that miners can coordinate to act maliciously over a prolonged period of time regardless of economic and social incentives, meaning they are probably in it just for attacking Bitcoin, backed by nation-states or something else, and therefore no Bitcoin transaction in the mainchain is to be expected to be safe ever again.

Why use this and not a full-blown trustless and open sidechain technology?

Because it is impossible.

If you ever heard someone saying "just use a sidechain", "do this in a sidechain" or anything like that, be aware that these people are either talking about "federated" sidechains (i.e., funds are kept in custody by a group of entities) or they are talking about Drivechain, or they are disillusioned and think it is possible to do sidechains in any other manner.

No, I mean a trustless 2-way peg with correctness of the withdrawals verified by the Bitcoin protocol!

That is not possible unless Bitcoin verifies all transactions that happen in all the sidechains, which would be akin to drastically increasing the blocksize and expanding the Bitcoin rules in tons of ways, i.e., a terrible idea that no one wants.

What about the Blockstream sidechains whitepaper?

Yes, that was a way to do it. The Drivechain hashrate escrow is a conceptually simpler way to achieve the same thing with improved incentives, less junk in the chain, more safety.

Isn't the hashrate escrow a very complex soft-fork?

Yes, but it is much simpler than SegWit. And, unlike SegWit, it doesn't force anything on users, i.e., it isn't a mandatory blocksize increase.

Why should we expect miners to care enough to participate in the voting mechanism?

Because it's in their own self-interest to do it, and it costs very little. Today over half of the miners mine RSK. It's not blind merged mining, it's a very convoluted process that requires them to run a RSK full node. For the Drivechain sidechains, an SPV node would be enough, or maybe just getting data from a block explorer API, so much much simpler.

What if I still don't like Drivechain even after reading this?

That is the entire point! You don't have to like it or use it as long as you're fine with other people using it. The hashrate escrow special addresses will not impact you at all, validation cost is minimal, and you get the benefit of people who want to use Drivechain migrating to their own sidechains and freeing up space for you in the mainchain. See also the point above about infighting.

See also

• Podcast episode with Ruben Somsen and Aaron van Wirdum explaining Drivechain
• Alternatives to Drivechain
• Drivechain comparison with Ethereum

@ dd296c40:367d6d3e

• It is almost April!
• How about this external image ?
• Do something to your hair.
• Have you ever eaten a spoon full of peanut butter ?
• Have you ever eaten a spoon full of ketchup ?
• Do you like spiders ?
• How about this external image ?

@ 1689f2c8:5f809f76

Opinion about AirGap Vault - Secure Secrets (android)

Just testing ...

WalletScrutiny #nostrOpinion

Join the conversation!

@ 044b20cf:89e58620

Who exactly is YouTube’s multicam Coachella stream for?

YouTube is hyping (https://blog.youtube/news-and-events/coachella-2024-livestream-how-to-watch/) its exclusive Coachella streaming coverage, which starts next week. The headlining feature is the platform’s multiview experience (already familiar to sports fans (https://www.engadget.com/youtube-tv-mosaic-mode-report-192123171.html)) for the two-weekend festival. Our question from this announcement is, who wants to watch several different artists’ sets at the same time — when you can only listen to one?

The multiview experience will let you watch up to four stages simultaneously, letting you pick which one to hear: exactly how multiview works for March Madness (https://www.engadget.com/march-madness-live-brings-multiview-streaming-to-the-web-for-up-to-four-games-160010247.html), NFL games or any other sporting event. Here’s how YouTube pitches the feature: “Two of your favorite bands playing on different stages at the same time? No problem, multiview will have you and your friends covered to catch both sets at the same time via the YouTube app on TV at no additional cost.”

Maybe I’m of the wrong generation and have too long of an attention span, but who wants to watch an artist’s set without hearing it? That’s what will happen to the three stages you aren’t listening to. Wouldn’t it be better to... watch the one you’re hearing? And then catch up on the others on-demand when you can listen to them as well?

Sports multiview makes sense because there are scores to track and timeouts, halftimes and blowouts to divert your attention to another game. You don’t need to hear an NBA game to keep an eye on the ball. (Depending on the commentators, you may prefer not to listen to it.) It’s primarily a visual experience; the audio is secondary.

But music, even when played live with all the light shows, fog machines and dancing accompanying it, is still an auditory experience first and foremost. If multiple artists you like play at once, you still can’t (and wouldn’t want to) hear more than one simultaneously. In YouTube’s multiview, you pick one stage to hear and the rest to… watch them sing and dance on mute in a little box alongside two other muted performances. Yay?

It sounds like a solution looking for a problem — YouTube applying its existing tech (which, to be fair, works very well with sports) to a music festival. Never mind that it doesn’t make a lot of sense.

Perplexed rants aside, YouTube will have six livestream feeds to bounce between (but, again, only four at once in multiview). That includes Sonora for the first weekend and Yuma for the second. This year’s headliners include Lana Del Rey, Doja Cat, No Doubt and Tyler, the Creator.

Between sets, YouTube will stream “special editorial content” from the artists onsite. Each day after the night’s final set, YouTube’s Coachella channel will repeat that day’s sets until the livestream returns the next day. That sounds like a better way to catch up on the sets you didn’t see live.

The event takes place in Indio, California, about 130 miles east of LA, from April 12 to 14 and April 19 to 21. You can tune in on YouTube’s Coachella channel (https://www.youtube.com/coachella).

This article originally appeared on Engadget at https://www.engadget.com/who-exactly-is-youtubes-multicam-coachella-stream-for-183744741.html?src=rss

https://www.engadget.com/who-exactly-is-youtubes-multicam-coachella-stream-for-183744741.html?src=rss

@ 3bf0c63f:aefa459d

IPFS problems: Too much immutability

Content-addressing is unusable with an index or database that describes each piece of content. Since IPFS is fully content-addressable, nothing can be done with it unless you have a non-IPFS index or database, or an internal protocol for dynamic and updateable links.

The IPFS conceit made then go with the with the second option, which proved to be a failure. They even incentivized the creation of a database powered by IPFS, which couldn't be more misguided.

@ 3bf0c63f:aefa459d

Gŕecia Antiga e homosexualismo cultural

Se na Grécia Antiga o homosexualismo era tão comum, não seria isso um argumento definitivo contra o pessoal que hoje afirma que o homosexualismo é natural e que 0.1%/1%/10%/25% das pessoas são homosexuais por natureza?

Se na Gŕecia Antiga havia muito mais de 25% de homosexuais e aqui até ontem eram menos de 1% (e agora subiu?) isso tudo não é evidência fortíssima de que o homosexualismo é mesmo cultural?

@ 3bf0c63f:aefa459d

Zettelkasten

https://writingcooperative.com/zettelkasten-how-one-german-scholar-was-so-freakishly-productive-997e4e0ca125 (um artigo meio estúpido, mas útil).

Esta incrível técnica de salvar notas sem categorias, sem pastas, sem hierarquia predefinida, mas apenas fazendo referências de uma nota à outra e fazendo supostamente surgir uma ordem (ou heterarquia, disseram eles) a partir do caos parece ser o que faltava pra eu conseguir anotar meus pensamentos e idéias de maneira decente, veremos.

Ah, e vou usar esse tal neuron que também gera sites a partir das notas?, acho que vai ser bom.

@ 044b20cf:89e58620

The latest Razer Blade 18 is now available to order

It’s taken Razer (https://www.engadget.com/tag/razer/) a few extra months to get its latest 18-inch Blade laptop ready for primetime after we first saw it at CES (https://www.engadget.com/razers-blade-laptop-lineup-shines-bright-with-stunning-screens-at-ces-2024-230044688.html). Those who have been waiting for the company’s latest chonkster can now order the 2024 edition of the Razor Blade 18, which starts at $3,099 (https://www.razer.com/gaming-laptops/Razer-Blade-18/RZ09-0509SEK3-R3U1).

The base system comes with an i9-14900HX processor, 32GB of RAM, 1TB of SSD storage, Wi-Fi 7, a triple-fan cooling system and a six-speaker array with THX spatial audio support. On the GPU side, you can equip the laptop with up to an NVIDIA GeForce RTX 4090 (the base model has a 4070 graphics card). In what Razer claims is a first for a laptop, there's Thunderbolt 5 connectivity, but only if you opt for a 4080 or 4090 GPU.

Razer

The display is one of the big talking points for this laptop. It comes with a QHD+ 300Hz Mini-LED display as standard. If you want higher fidelity, you can opt for a 4K 200Hz screen. The company seems to have found an extra 35 hertz since CES, since it said at the time the Razer Blade 18 would have a 4K 165Hz display option. Razer claims that this display is a world first for a laptop and it’ll set you back an extra $1,700, far more than an equivalent standalone monitor would cost. You'll also need to wait until later this summer for a model with a 4K 200Hz panel to ship, whereas you can snag one with the QHD+ display now.

We felt that last year's model was very expensive (https://www.engadget.com/razer-blade-18-review-specs-price-overpowered-and-oversized-133044127.html) for a fully kitted-out configuration and that's the case again this time around. Still, if you need a big-screen, high-end laptop that can run just about any program or game you can throw at it, the latest Razer Blade 18 can be all yours if you have the cash to spare.

Razer

This article originally appeared on Engadget at https://www.engadget.com/the-latest-razer-blade-18-is-now-available-to-order-180330999.html?src=rss

https://www.engadget.com/the-latest-razer-blade-18-is-now-available-to-order-180330999.html?src=rss

@ ae1008d2:a166d760

I'm testing this to make sure I can post here on highlighter

@ 91688b52:44ef9b1f

• It is almost April!
• How about this external image ?
• Do something to your hair.
• Have you ever eaten a spoon full of peanut butter ?
• Have you ever eaten a spoon full of ketchup ?
• Do you like spiders ?
• How about this external image ?

@ 044b20cf:89e58620

Ford delays some electric vehicles, renews focus on hybrids

Ford just announced some delays for electric vehicles (https://media.ford.com/content/fordmedia/fna/us/en/news/2024/04/04/ford-updates-timing-for-next-gen-evs--readies-manufacturing-plan.html), including the long-awaited three-row SUV. The car was supposed to come out next year but has now been delayed until 2027, with the company suggesting it will use the extra time to “take advantage of emerging battery technology.” Ford says it’ll be making moves to “mitigate the impact the launch delay will have on” the Canadian workforce.

The next-generation electric pickup, codenamed “T3,” is also being delayed from late 2025 to 2026. It’s being built at the Tennessee Electric Vehicle Center assembly plant at the company’s BlueOval City complex, though Ford says it's just now installing stamping equipment that will produce the sheet metal for the truck.

Alongside these announcements, the company has revealed a new push for hybrid vehicles. It has stated it plans on offering hybrid powertrains across the entire Ford Blue lineup by 2030. Despite the aforementioned delays and the pivot toward hybrid vehicles, Ford says it remains committed to EVs and that it's continuing construction of battery plants in Michigan, Tennessee and Kentucky.

However, it’s no secret that the EV market is not quite as robust as companies once hoped it would be. Maybe it’s the high price of entry, the spotty charging infrastructure or the fact that some EVs do not qualify for the federal tax break. Heck, maybe consumers are simply turned off by a certain CEO who shall not be named (https://www.engadget.com/tesla-paid-no-federal-income-taxes-while-paying-executives-25-billion-over-five-years-154529907.html).

In any event, the slowdown is real (https://www.engadget.com/ford-is-cutting-f-150-lightning-production-due-to-waning-demand-173838340.html), though perhaps a bit overstated. Ford experienced a decline in EV sales of 11 percent (https://www.reuters.com/business/autos-transportation/ford-ev-sales-fall-january-amid-demand-slowdown-2024-02-02/#:~:text=Feb%202%20(Reuters)%20%2D%20Ford,than%20their%20gasoline%2Dpowered%20counterparts.) in January, but the company says it bounced back and that sales have increased by 86 percent throughout the entire first quarter when compared to last year. However, the company's EV offerings lost $4.7 billion in 2023 (https://www.reuters.com/business/autos-transportation/ford-will-delay-some-north-american-ev-production-2024-04-04/).

“We are committed to scaling a profitable EV business", said Jim Farley, Ford president and CEO. To that end, the company announced last year that it would be delaying or canceling $12 billion in planned spending (https://shopping.yahoo.com/rdlw?merchantId=34e37b9c-8975-48da-aa39-df8bcd5badc3&siteId=us-engadget&pageId=1p-autolink&featureId=text-link&merchantName=CNBC&custData=eyJzb3VyY2VOYW1lIjoiV2ViLURlc2t0b3AtVmVyaXpvbiIsImxhbmRpbmdVcmwiOiJodHRwczovL3d3dy5jbmJjLmNvbS8yMDIzLzEwLzI2L2ZvcmQtd2lsbC1wb3N0cG9uZS1hYm91dC0xMi1iaWxsaW9uLWluLWV2LWludmVzdG1lbnQuaHRtbCIsImNvbnRlbnRVdWlkIjoiNDQwNTlkY2QtOTk1ZS00NGM1LTkzZTEtMGNmZDdlNTYxYjMyIn0&signature=AQAAASSjnSB0Gw7zfmip9UvERBPzLSHcKFuTFxh9jhi57Hxz&gcReferrer=https%3A%2F%2Fwww.cnbc.com%2F2023%2F10%2F26%2Fford-will-postpone-about-12-billion-in-ev-investment.html) on electric vehicles. It’s unclear how today’s announcements will impact Ford's plans to ramp up production to 600,000 EVs (https://www.engadget.com/ford-expects-to-reach-its-ev-production-goal-a-year-later-than-planned-101804539.html) per year. In any event, customers can now use Tesla Superchargers (https://www.engadget.com/ford-ev-owners-can-now-use-tesla-superchargers-in-the-us-and-canada-130053549.html) in the US and Canada, which should help assuage some of those infrastructure concerns.

This article originally appeared on Engadget at https://www.engadget.com/ford-delays-some-electric-vehicles-renews-focus-on-hybrids-172007210.html?src=rss

https://www.engadget.com/ford-delays-some-electric-vehicles-renews-focus-on-hybrids-172007210.html?src=rss

@ 3bf0c63f:aefa459d

piln

Piln was a prepaid IPFS pinning service you could use anonymously and instantaneously with the Bitcoin payments over the Lightning Network.

Similar to https://eternum.io/, but anonymous, loginless and very very cheap. The cheapness wouldn't scale because it needed a local HD to store data, couldn't work with services like S3 because IPFS is very bad (I actually tried to make it work).

Discontinued because IPFS is terrible.

• https://piln.xyz/
• https://github.com/fiatjaf/piln

See also

• How IPFS is broken

@ 195284db:2f006fc1

Opinion about STRIKE: Bitcoin & Global Money (android)

Strike is for fiat and bitcoin. It can send and receive bitcoins.

WalletScrutiny #nostrOpinion

Join the conversation!

@ c11cf5f8:4928464d

Cowboys and cowgirls, it's time to shine! Spotlight your preferred product or service in the ~AGORA.

Tell us why you love it so much.

@ 82100056:e198089f

Dear the Tottenham Hotspur board of directors,

I have been a Spurs fan all of my life. I care deeply about the long-term future of the club. It is for this reason that I am writing to you to ask you to consider buying and holding Bitcoin as part of your corporate strategy for Spurs.

Upon reading about the club's financial results yesterday, I noticed two things: that the club is seeking investment and that the board is advised by Rothschild and co.

I then noticed this article by a director of Rothschild dismissing the value proposition of Bitcoin:

https://www.rothschildandco.com/en/newsroom/insights/2024/01/wm-strategy-blog-bitcoin.etfs-a-token-gesture/

For perspective, if Spurs spent £50m on Bitcoin rather than buying Tanguy Ndombele in September 2019, the investment would now be worth over £300m. This trend is going to continue, partly because of inflation which I know you are aware of, but also because Bitcoin is by far the best financial asset in the world.

If you are not at the least being advised about this possibility then your advisors have a blind spot that could cost Spurs dearly in the future. And that is something neither of us want to see.

I would like to point you to the work of Michael Saylor, CEO of MicroStrategy, who is an outstanding advocate for Bitcoin and an example of its potential:

“Bitcoin hitting all time highs and boasting a staggering 12-month return of 200% has made headlines all around the world. Has any other asset outperformed Bitcoin during the same time? Ladies and Gentlemen, let me present to you MicroStrategy (MSTR); its price has skyrocketed with a remarkable 12-month return of 600%.”

"At the heart of Saylor's strategy lies a revolutionary approach to corporate finance, characterized by the strategic utilization of debt instruments and voracious appetite to acquire Bitcoin as a store of value. Through meticulous planning and execution, Saylor engineered a financial maneuver that has reshaped the landscape of corporate treasuries."

Source:

https://economictimes.indiatimes.com/markets/cryptocurrency/trade-of-the-century-how-michael-saylor-revolutionised-corporate-finance-with-bitcoin/articleshow/108540458.cms?utm_source=contentofinterest&utm_medium=text&utm_campaign=cppst

Your track record at Spurs has been exemplary. And for that I am grateful.

But I believe by utilising Bitcoin Tottenham Hotspur can be the biggest football club in the world.

All I ask is that you put the time in to research Bitcoin, for the sake of Spurs.

Thanks for taking the time to read this and best of luck for the rest of the season.

COYS.

@ 044b20cf:89e58620

Amazon’s Prime Gaming titles for April include Fallout 76 and Chivalry 2

Amazon is offering another decent batch of games (https://primegaming.blog/prime-gaming-april-content-update-fallout-76-chivalry-2-faraway-2-jungle-escape-and-more-f66c309986a8) to Prime members at no extra cost for the month of April. Leading the bunch is Fallout 76, a multiplayer take on the post-apocalyptic franchise. There’s also the hack and slash adventure Chivalry 2 and around a dozen more.

Fallout 76 is just the latest title in the series to hit Prime Gaming, likely to coincide with this month’s premiere (https://www.engadget.com/prime-videos-latest-fallout-trailer-deftly-captures-the-tone-of-the-games-170210309.html) of the Fallout TV show. It experienced mixed reviews upon release, with many complaining about an overall lack of purpose in the gameplay and a blandness in the design. Other people simply enjoyed wandering around a post-apocalyptic West Virginia with their buddies.

The game’s available for PC and, interestingly, Xbox consoles. People can download it from the Microsoft Store for PC and Amazon will hand out a code to Prime members for an Xbox download. Fallout 76 will be available on April 11, the same exact day all eight episodes of the show drop.

Chivalry 2, on the other hand, is available right now. This is a modern take on the hack and slash genre, with a first-person POV, multiplayer matches with up to 64 players at once and a grimy medieval setting. There’s also crossplay for every available platform (https://www.engadget.com/chivalry-2-crossplay-071812073.html). Prime members can download it at the Epic Games Store.

Other titles coming this month include Black Desert, Demon’s Tilt, Rose Riddle: The Fairy Tale Detective Collector’s Edition and many more. Click the link above for the full list. Additionally, Prime Members in the US, Canada, Germany, France, Italy, Spain and the UK can access some new games on Luna at no extra charge. These include LEGO Fortnite, Earthworm Jim 2 and Trackmania, among others.

This article originally appeared on Engadget at https://www.engadget.com/amazons-prime-gaming-titles-for-april-include-fallout-76-and-chivalry-2-153731669.html?src=rss

https://www.engadget.com/amazons-prime-gaming-titles-for-april-include-fallout-76-and-chivalry-2-153731669.html?src=rss

@ 3bf0c63f:aefa459d

O voto negativo

É simples: Você pode escolher entre votar em um candidato qualquer, como todos fazemos normalmente, ou tirar um voto de um político que não quer que seja eleito de jeito nenhum. A possibilidade de votarmos negativamente duas vezes é muito interessante também.

Outro motivo para implementar essa inovação na democracia: é muito mais divertido que o voto nulo.

@ 3bf0c63f:aefa459d

Democracy as a failed open-network protocol

In the context of protocols for peer-to-peer open computer networks -- those in which new actors can freely enter and immediately start participating in the protocol --, without any central entity, specially without any central human mind judging things from the top --, it's common for decisions about the protocol to be thought taking in consideration all the possible ways a rogue peer can disrupt the entire network, abuse it, make the experience terrible for others. The protocol design must account for all incentives in play and how they will affect each participant, always having in mind that each participant may be acting in a purely egoistical self-interested manner, not caring at all about the health of the network (even though most participants won't be like that). So a protocol, to be successful, must have incentives aligned such that self-interested actors cannot profit by hurting others and will gain most by cooperating (whatever that means in the envisaged context), or there must be a way for other peers to detect attacks and other kinds of harm or attempted harm and neutralize these.

Since computers are very fast, protocols can be designed to be executed many times per day by peers involved, and since the internet is a very open place to which people of various natures are connected, many open-network protocols with varied goals have been tried in large scale and most of them failed and were shut down (or kept existing, but offering a bad experience and in a much more limited scope than they were expected to be). Often the failure of a protocol leads to knowledge about its shortcomings being more-or-less widespread and agreed upon, and these lead to the development of a better protocol the next time something with similar goals is tried.

Ideally democracies are supposed to be an open-entry network in the same sense as these computer networks, and although that is a noble goal, it's one full of shortcomings. Democracies are supposed to the governing protocol of States that have the power to do basically anything with the lives of millions of citizens.

One simple inference we may take from the history of computer peer-to-peer protocols is that the ones that work better are those that are simple and small in scope (Bitcoin, for example, is very simple; BitTorrent is also very simple and very limited in what it tries to do and the number of participants that get involved in each run of the protocol).

Democracies, as we said above, are the opposite of that. Besides being in a very hard position to achieve success as an open protocol, democracies also suffer from the fact that they take a long time to run, so it's hard to see where it is failing every time.

The fundamental incentives of democracy, i.e. the rules of the protocol, posed by the separation of powers and checks-and-balances are basically the same in every place and in every epoch since the XIII century, and even today most people who dedicate their lives to the subject still don't see how they're completely flawed.

The system of checks and balances was thought from the armchair of a couple of political theorists who had never done anything like that in their lives, didn't have any experience dealing with very adversarial environments like the internet -- and probably couldn't even imagine that the future users of their network were going to be creatures completely different than themselves and their fellow philosophers and aristocrats who all shared the same worldview (and how fast that future would come!).

Also

• The illusion of checks and balances

@ 06639a38:655f8f71

My goal was to find an easy to install, use and configure Nostr relay implementation with custom policies. For example I would like to set a policy where I configure specific event kinds to be transmitted by the relay.

This article is also published on my blog: https://sebastix.nl/blog/run-a-nostr-relay-with-your-own-policies/

Currently, I'm running relays with Nostream (written with TypeScript) for nostr.sebastix.dev and Chorus (written with Rust) for relay.sebastix.social.

Another relay implementation was Jingle which was on my list to give it a try. I really liked the idea that you can write your own policies in JavaScript, because every webdeveloper could use it. In this blog I've shared my experience setting this relay up.

TLDR Jingle is not working, so I've set up a relay with Khatru.

---

Run Jingle with JavaScript written policies

fiatjaf/jingle: a friendly customizable Nostr relay

With Jingle, by default, all data is stored in a data directory in a SQLite database. This is how my Nginx config file looks for running Jingle behind a reverse proxy setup:

```nginx upstream jingle { server 127.0.0.1:5577; }

server { server_name jingle.nostrver.se;

location / {
    proxy_pass http://jingle;
    proxy_http_version 1.1;
    proxy_set_header Host $host;
    proxy_set_header X-Real-IP $remote_addr;
    proxy_set_header Upgrade $http_upgrade;
    proxy_set_header Connection "Upgrade";
}

listen 443 ssl; # managed by Certbot
ssl_certificate /etc/letsencrypt/live/jingle.nostrver.se/fullchain.pem;
ssl_certificate_key /etc/letsencrypt/live/jingle.nostrver.se/privkey.pem;
include /etc/letsencrypt/options-ssl-nginx.conf;
ssl_dhparam /etc/letsencrypt/ssl-dhparams.pem;

access_log /var/log/nginx/jingle.nostrver.se.access.log;
error_log /var/log/nginx/jingle.nostrver.se.error.log;

}

server { if ($host = jingle.nostrver.se) { return 301 https://$host$request_uri; }

listen       80;
server_name  jingle.nostrver.se;
return 404;

} ```

Create your own relay policy with JavaScript

The JavaScript files are located in the stuff directory. These are the default JavaScript files (these are generated when the binary is build) installed to give you an idea what’s possible.

• reject-event.js (called for every EVENT message)
• reject-filter.js (called for every REQ message)

The default code of these JavaScript files comes from the reject.go file.

Use NAK as your Nostr client to test

When you're developing stuff with Nostr, please have a look at nak - a command line tool for doing all things nostr. After you've git cloned this repository, run go build to create a nak binary. Now you can execute the following commands with the binary.

./nak —-help

```bash NAME: nak - the nostr army knife command-line tool

USAGE: nak [global options] command [command options] [arguments...]

COMMANDS: req generates encoded REQ messages and optionally use them to talk to relays count generates encoded COUNT messages and optionally use them to talk to relays fetch fetches events related to the given nip19 code from the included relay hints event generates an encoded event and either prints it or sends it to a set of relays decode decodes nip19, nip21, nip05 or hex entities encode encodes notes and other stuff to nip19 entities key operations on secret keys: generate, derive, encrypt, decrypt. verify checks the hash and signature of an event given through stdin relay gets the relay information document for the given relay, as JSON bunker starts a NIP-46 signer daemon with the given --sec key help, h Shows a list of commands or help for one command

GLOBAL OPTIONS: --quiet, -q do not print logs and info messages to stderr, use -qq to also not print anything to stdout (default: false) --help, -h show help ```

Publish an event to relay(s) with authentication

./nak event --sec <your_nsec_in_hex_value> -c <content> --auth
More info about the event command, run ./nak event --help

```bash NAME: nak event - generates an encoded event and either prints it or sends it to a set of relays

USAGE: nak event [command options] [relay...]

DESCRIPTION: outputs an event built with the flags. if one or more relays are given as arguments, an attempt is also made to publish the event to these relays.

example: nak event -c hello wss://nos.lol nak event -k 3 -p 3bf0c63fcb93463407af97a5e5ee64fa883d107ef9e558472c4eb9aaaefa459d

if an event -- or a partial event -- is given on stdin, the flags can be used to optionally modify it. if it is modified it is rehashed and resigned, otherwise it is just returned as given, but that can be used to just publish to relays.

example: echo '{"id":"a889df6a387419ff204305f4c2d296ee328c3cd4f8b62f205648a541b4554dfb","pubkey":"c6047f9441ed7d6d3045406e95c07cd85c778e4b8cef3ca7abac09b95c709ee5","created_at":1698623783,"kind":1,"tags":[],"content":"hello from the nostr army knife","sig":"84876e1ee3e726da84e5d195eb79358b2b3eaa4d9bd38456fde3e8a2af3f1cd4cda23f23fda454869975b3688797d4c66e12f4c51c1b43c6d2997c5e61865661"}' | nak event wss://offchain.pub echo '{"tags": [["t", "spam"]]}' | nak event -c 'this is spam'

OPTIONS: --auth always perform NIP-42 "AUTH" when facing an "auth-required: " rejection and try again (default: false) --connect value sign event using NIP-46, expects a bunker://... URL --connect-as value private key to when communicating with the bunker given on --connect (default: a random key) --envelope print the event enveloped in a ["EVENT", ...] message ready to be sent to a relay (default: false) --nevent print the nevent code (to stderr) after the event is published (default: false) --nson encode the event using NSON (default: false) --prompt-sec prompt the user to paste a hex or nsec with which to sign the event (default: false) --sec value secret key to sign the event, as hex or nsec (default: the key '1')

EVENT FIELDS

--content value, -c value event content (default: hello from the nostr army knife) --created-at value, --time value, --ts value unix timestamp value for the created_at field (default: now) --kind value, -k value event kind (default: 1) --tag value, -t value [ --tag value, -t value ] sets a tag field on the event, takes a value like -t e= -d value [ -d value ] shortcut for --tag d= -e value [ -e value ] shortcut for --tag e= -p value [ -p value ] shortcut for --tag p= ```

Request / query data from relays

./nak req
More info about the req command, run ./nak req --help

```bash NAME: nak req - generates encoded REQ messages and optionally use them to talk to relays

USAGE: nak req [command options] [relay...]

DESCRIPTION: outputs a NIP-01 Nostr filter. when a relay is not given, will print the filter, otherwise will connect to the given relay and send the filter.

example: nak req -k 1 -l 15 wss://nostr.wine wss://nostr-pub.wellorder.net nak req -k 0 -a 3bf0c63fcb93463407af97a5e5ee64fa883d107ef9e558472c4eb9aaaefa459d wss://nos.lol | jq '.content | fromjson | .name'

it can also take a filter from stdin, optionally modify it with flags and send it to specific relays (or just print it).

example: echo '{"kinds": [1], "#t": ["test"]}' | nak req -l 5 -k 4549 --tag t=spam wss://nostr-pub.wellorder.net

OPTIONS: --auth always perform NIP-42 "AUTH" when facing an "auth-required: " rejection and try again (default: false) --bare when printing the filter, print just the filter, not enveloped in a ["REQ", ...] array (default: false) --connect value sign AUTH using NIP-46, expects a bunker://... URL --connect-as value private key to when communicating with the bunker given on --connect (default: a random key) --prompt-sec prompt the user to paste a hex or nsec with which to sign the AUTH challenge (default: false) --sec value secret key to sign the AUTH challenge, as hex or nsec (default: the key '1') --stream keep the subscription open, printing all events as they are returned (default: false, will close on EOSE)

FILTER ATTRIBUTES

--author value, -a value [ --author value, -a value ] only accept events from these authors (pubkey as hex) --id value, -i value [ --id value, -i value ] only accept events with these ids (hex) --kind value, -k value [ --kind value, -k value ] only accept events with these kind numbers --limit value, -l value only accept up to this number of events (default: 0) --search value a NIP-50 search query, use it only with relays that explicitly support it --since value, -s value only accept events newer than this (unix timestamp) --tag value, -t value [ --tag value, -t value ] takes a tag like -t e=, only accept events with these tags --until value, -u value only accept events older than this (unix timestamp) -d value [ -d value ] shortcut for --tag d= -e value [ -e value ] shortcut for --tag e= -p value [ -p value ] shortcut for --tag p= ```

Fetch events

./nak fetch
More info about the fetch command, run ./nak fetch --help

```bash NAME: nak fetch - fetches events related to the given nip19 code from the included relay hints

USAGE: nak fetch [command options] [nip19code]

DESCRIPTION: example usage: nak fetch nevent1qqsxrwm0hd3s3fddh4jc2574z3xzufq6qwuyz2rvv3n087zvym3dpaqprpmhxue69uhhqatzd35kxtnjv4kxz7tfdenju6t0xpnej4 echo npub1h8spmtw9m2huyv6v2j2qd5zv956z2zdugl6mgx02f2upffwpm3nqv0j4ps | nak fetch --relay wss://relay.nostr.band

OPTIONS: --relay value, -r value [ --relay value, -r value ] also use these relays to fetch from --help, -h show help ```

You can also use NAK in the browser here: https://nak.nostr.com/

Let’s test and debug!

1. Open a terminal where you can use the nak binary with ./nak
2. For this demo I created the following secret key by executing ./nak key generate which returned a hex formatted secret key: 472f1868bebd7b8016534df94f8421c9b68c66c1914ccf9a99ca5d557f707a8b
3. Open one of the JavaScript files from your Nostr relay with Jingle to make some edits.

This is my setup in my PHPStorm editor:

By default, the relay requires authentication of clients (seen in the screenshot above) which in configured in the stuff/reject.filter.js file. To authenticate with nak to the relay, you must send your private key (nsec) together with the --auth option. So ./nak req -k 30023 -l 1 --sec <put_your_nsec_here> --auth wss://jingle.nostrver.se should response with something like:

bash connecting to wss://jingle.nostrver.se... ok. {"id":"0faeb0c150b9f370b702d4357de3536a7fd606be...a9779b6e2e957e26af557","pubkey":"efbb28950ec699e1f988dc8dba00e70cb89d18d7d9e931036a4c36ea4de77586","created_at":1711324345,"kind":30023,"tags":[],"content":"hello world","sig":"aef587a768298abeff08bdf7ef5eb0e84d93a0ef9e4fcdd162f9f3eff3cf3a35384c2054be76a9bdda303ca3de0ebcad...8a07221c01b8bd41da6be158edbbe"}

Use console.log() to debug your JavaScript. Depending on your setup, you can find the output in the server logs. In my case I had to dig into the logs of the docker container. You can also run the Jingle binary to see the direct output on your command-line.

Stuck…look like Jingle is broken for me

When the relay is returning a failed: msg: blocked: error applying policy script message, your JavaScript policy files are not valid. Please note that a fork of buke/quickjs-go: Go bindings to QuickJS is used (https://github.com/fiatjaf/quickjs-go) for parsing the JavaScript files. The ES2020 specification is used in that library.

After some more debugging and working out my own filters, it seems that Jingle is crashing randomly while returning unexpected token errors. See this issue and a short screencast how it occurs on my setup: https://shares.sebastix.dev/GBkBnfCu.mp4. I showed it to Fiatjaf as well, but he will need to make time to investigate this unexpected behavior of the relay. I suspect there is something going wrong in how the JavaScript code are being parsed / compiled in the Go runtime...

Khatru as a temporary alternative

While I entered a new rabbit hole, I forked fiatjaf/khatru. This is my forked repo, so you can check out my work in progress: https://github.com/sebastix/khatru.

Hodlbod (Jon) tipped me to have a look at coracle-social/triflector: A relay which enforces authentication based on custom policy which he build with Khatru.

As I’ve never written any line Golang code...I needed to learn some basics first.

• How to install Go - see Download and install - The Go Programming Language
• I quickly walked through this tour: A Tour of Go
• Ho to run Go code: go run <your_file.go>
• How to run and debug Go code: with Delve found at Go (Golang) Debugging Approaches. Now I could use dlv debug <your_file.go> but I haven’t found a way to debug with ease on the CLI.
• How to build a binary from the code: go build <your_file.go>
• Use a FOSS IDE for writing Go: still looking for one... I could use GoLand as I’m used to work with PHPStorm from JetBrains.

Khatru contains several Go files in the project root and some example snippets in the examples directory. I’m using the basic-sqlite example as a base for the work-in-progress relay setup I’m working out. Here you can view the current main.go file which is used for the relay.

You could connect to the relay at wss://khatru.nostrver.se .

bash $ ./nak relay wss://khatru.nostrver.se { "name": "khatru.nostrver.se", "description": "Custom relay build with Khatru", "pubkey": "npub1qe3e5wrvnsgpggtkytxteaqfprz0rgxr8c3l34kk3a9t7e2l3acslezefe", "contact": "info@sebastix.nl", "supported_nips": [ 1, 11, 70 ], "software": "<https://github.com/fiatjaf/khatru>", "version": "0.0.1", "icon": "" }

As for now, the relay only accepts event with kind 37515 and 13811 as you can read on https://khatru.nostrver.se/.

Khatru is using a lot of packages from the Golang library for Nostr: nbd-wtf/go-nostr: Nostr library for Golang and is worth checking out as one of the most complete libraries for Nostr out there

I’ve also created a system daemon service for running the relay in the background on my server:

```systemd [Unit] Description=khatru After=network-online.target

[Service] Type=simple WorkingDirectory=/var/www/khatru.nostrver.se User=sebastix ExecStart=/usr/local/go/bin/go run examples/basic-sqlite3/main.go Restart=always RestartSec=5

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

A for now, the relay is running and only accepting Nostr event kinds 37515 and 13811. With this working setup, I’m able to continue building a proof-of-concept client around places and place check-ins 🫡.

Let me just draw a line here for the first chapter of exploring something new. I'm sure things will continue to evolve! Make sure to follow me on Nostr to keep up-to-date with my tinkering.

---

Please let me know if you have any questions or things are not clear from this post! As a creative webdeveloper I'm always improving my explainer skills as I know I'm often too technical for most of us.

@ 3bf0c63f:aefa459d

The place of Drivechain in Bitcoin's future

James O'Beirne wrote this nice little article that contains a bunch of statements that should have been obvious to anyone who thought a little about Bitcoin's future, as they were obvious for Hal Finney in 2009 already.

Basically the article says that the Bitcoin blockchain won't scale for the entire world population to use it. It will so much not scale that even "offchain" solutions like Lightning and Ark will not scale and they basically lose usefulness as more adoption happens and fees rise.

Given that, Bitcoin has only two paths (and now this is not James speaking anymore): either it will die or it will have to scale using custodians.

Can Bitcoin die?

Yes, Bitcoin can die, and if Bitcoin fails to get some level of mass adoption soon enough I believe it will die. Governments all around the world gave us 14 years of advantage to try to get Bitcoin to become this money medium-of-exchange store-of-value thing, or at least an investment vehicle or savings-technology that is super valuable and with widespread ownership, but now it is starting to move. CBDCs have been talked about for a while, but now they are really starting to happen. Regulated and compliant fiat proprietary services like Venmo have grown under capture by governments, in some places the government itself has launched their own cool app-like totally regulated spyware fiat money transmission things, like the ridiculous PIX in Brazil, which is now widely adopted, and -- I believe surprisingly for all the UX designers out there -- people have learned to use QR codes.

The point is that, given a little bit of more time, governments can start to encroach on Bitcoin's space, making it more and more regulated until it either dies or becomes a very useless thing. Some Bitcoiners think Bitcoin has already won, this can't be further from the truth. Others think Bitcoin must not be mass adopted, it must stay as this niche and mostly useless currency digital asset thing or I don't really understand what they think. These people are wrong. There are also people who think Bitcoin should not be used by normal people as money, it should keep being adopted, but only as a store-of-value: this is also completely wrong, since Bitcoin's value tends to decrease as soon as owners realize Bitcoin is losing its chances of becoming actual money.

Scaling

To not die, Bitcoin must become more used. The current thesis accepted by most "maximalists" is that Bitcoin will continue to be thought of as an investment and its price will keep increasing, the price movements will bring more attention to it in a virtuous cycle. Eventually enough people will want to hold it so they will start accepting it as a payment for goods and services and then it can start to be used as money.

Assuming that will happen, we'll be faced with a problem: as people try to use it as money they will necessarily, by lack of other options, have to use some custodial solution or some proto-custodial solution, maybe using Lightning as a settlement layer between big custodians[^1]? I don't know. No one is happy with that solution, and rightfully so, since it is very dangerous. A small set of custodians can easily be captured by governments and they can slowly turn Bitcoin into fiat money like they did with gold.

In other words: without Drivechain, Bitcoin will be a fragile success in the best case and dead in the worst case scenario.

Enter Drivechain

Drivechain basically brings two things to the table:

In the best case scenario of the non-Drivechain world, we would be in a fragile position with easily-capturable custodians. With Drivechain, we can create a bunch of decentralized sidechains, backed by the same mining process that is assumed to be decentralized already for Bitcoin to even work, and we gain orders of magnitude of more room to make censorship-resistant open transactions that don't require tax IDs or selfies and can't be stopped or regulated by governments. Bitcoin can scale as it normally would, but it's much more resilient.

The other thing we get are improvements for the "dying" part. If Drivechain is successful, it may end up bringing much more people to Bitcoin. Hivemind by itself may attract lots of users and capital that has been prevented from betting on predictions anywhere in the fiat world since always; Zcash or Monero sidechains can easily bring all the "cryptocurrency" enthusiasts that care about privacy and have long ago decided that Bitcoin isn't for them, these people are interested in some immediate feature, that now Bitcoin can provide them with; other sidechains, like Ethereum-like chains, can also contribute to slowly bring in some of the users of these chains[^2]. Why would we want these people to come to Bitcoin? Because they will increase Bitcoin's network-effect, increase the satoshi price, and these changes would contribute for more people to start looking at Bitcoin and using Bitcoin and so on and so forth. More users, more network-effect, bigger price, will contribute for Bitcoin not being easily regulated and killed by governments.

In other words: with Drivechain will be a resilient success in the worst case and a complete and total world dominator money in the best case.

[^1]: I actually think Bitcoiners should put more thought on how to create a custodian network that scales easily without having to be centralized in a small set of providers like Lightning is, and this is kind of the point of James's article too. [^2]: Yes, I do think the entirety of the Ethereum ecosystem is a waste of time and money, but clearly there are dozens of people and money that disagree with me. And if they can't harm me with their stupidity then they will definitely make our money stronger. Besides that, it's not as if there aren't already many stupid people or even evil, horrible criminals using Bitcoin.