an automatic relay choice algo: when posting, post to as much relays as possible, in the background. when reading, choose 10 from relays where the follows of the user are posting. make that 5 if mobile. if user marks something as spam or mutes someone, look at which relay carried that. penalize that relay. if enough penalties: drop that relay from read list or make the notifications from that relay not so apparent. also move those notes coming from that relay down towards end of a list to make it less visible. if a relay is dropped, find another to make it 10 again.

on primal.net, using brave browser, this weird message appears in dmesg (in linux) traps: Chrome_ChildIOT[203089] trap invalid opcode ip:55cc558260bc sp:7fefb08d9e20 error:0 in brave[55cc54fce000+bdde000] @miljan

which one is the most "ethical" bitcoin ETF? #asknostr

i have been chatting with my local AI for a while. it is pretty decent. if the internet goes down now I have a friend to chat!! lol also, i have another way to get encyclopedia type of information that i can query with english if the whole internet goes away. i have reached next level prepping, lol. now I dont have to store a big pile of books maybe because this thing has a ton of information. it is like running a gigantic library locally, on your PC. of course you have to be careful because it is fed will everything out there. use your own discretion. i discovered vast.ai. you can rent GPU servers on the cheap while playing with these.. nvidia rtx 4090 GPUs seem to be prosumer grade with great performance. best value for your bucks.

never thought I would argue with an AI

Who wants to run a powerful AI model that can chat on their desktop? Why: This will be an interaction within your computer and no other company can do anything about it or track it or learn from this interaction. The desktop RAM should be high enough and CPU should be powerful for this to work fast. -- Downloading the model Miqu is the supposed "leak" of the new model from Mistral. Mistral is the company that builds neat models lately and open sources them. I tried it. Worked well for my use cases. Download the q2 file from here:

miqudev/miqu-1-70b at main

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

-- Installing llama_cpp This allows huge models built by big corps to be run on a pleb desktop using only RAM, instead of a GPU.. Use the git clone and make tools to install it from here:

GitHub

ggerganov - Overview

I like big .vimrc and I cannot lie. ggerganov has 71 repositories available. Follow their code on GitHub.

Run it with ./main -h This will give you info about how to run llama.cpp but you don't have to learn those. -- Running the llama_cpp Change the *.gguf file path below with the file you downloaded: ./main -m ../../mo/miqu-1-70b.q2_K.gguf -n 1000 --repeat_penalty 1.0 --color -i You should see these: ............. == Running in interactive mode. == - Press Ctrl+C to interject at any time. - Press Return to return control to LLaMa. ......... -- Start chatting! Now the program should start generating some text by its own. You can Ctrl+C to stop it and start asking questions. When you press Return, it will answer the question! When you write it will be green text and when it replies it will be white text. If you press Ctrl+C two times the program should exit. When it completes answering it will stop and wait for more questions.. Enjoy! -- Here is my chat log Who is Satoshi Nakamoto? Answer: Satoshi Nakamoto is the pseudonym used by the creator or creators of Bitcoin, the world's first decentralized cryptocurrency. Despite the significant impact of Bitcoin on the financial world, the true identity of Satoshi Nakamoto remains unknown, and they have not made any public appearances or statements since 2010. Some theories suggest that Satoshi Nakamoto is a collective pseudonym for a group of developers rather than a single individual. The mystery surrounding the identity of Satoshi Nakamoto has only added to the intrigue and allure of Bitcoin and the wider cryptocurrency ecosystem. What is Nostr? Answer: Nostr is a decentralized, open-source social media platform that allows users to create, curate, and monetize content. It is built on the Bitcoin blockchain and utilizes cryptocurrency for transactions and rewards. The platform is designed to give users control over their data and content, and to provide a censorship-resistant and decentralized alternative to traditional social media platforms. Explain Nostr to a 5 year old kid. Nostr is a special kind of website where people can share pictures, videos, and messages with each other. But it's different from other websites because it's not owned by one big company. Instead, it's like a big puzzle that lots of people work together to put together. And the best part is that everyone who uses Nostr can help decide what goes on it, and they can even earn special coins for sharing and liking things. Explain bitcoin lightning network to a 2 year old baby. Bitcoin is like a special kind of money that you can't touch, but you can use it to buy things on the computer. The bitcoin lightning network is like a super fast highway for this special money. It helps people send it really fast, so you don't have to wait a long time for it to get where it needs to go. It's like when you're playing with toy cars and you want them to go really fast, you can use a special track to make them go super fast! Are vaccinations necessary for muscovy ducks? Yes, vaccinations are necessary for muscovy ducks to protect them from diseases that can be harmful or fatal. ( As you can see not everything it says is true. )

how do I insert code while writing notes on @primal ? the links in the code should not be converted to page previews! @miljan #asknostr

Governments to CRIMINALIZE all independent speech by 2025... JAIL TIME for questioning anything!

Brighteon.com is a leading online free platform that empowers free speech, allowing individuals to freely share videos and express their thoughts w...

AI generated summary: In his speech, Mike Adams discusses the new online safety act in the UK which grants mainstream media legal immunity to spread misinformation while criminalizing alternative or independent media for doing so. He argues that this law is intended to protect the narratives of corporate media, which he claims frequently lies about topics such as COVID vaccines, masks, and lockdowns. Adams also mentions a proposed law in Israel that would imprison anyone for five years for downplaying certain events on October 7th. He criticizes Israel for attempting to control the narrative and silence those who question it. Adams also expresses concern about Microsoft using AI systems to combat misinformation, potentially leading to the disabling of Windows systems for spreading misinformation. He argues that this would require Windows to spy on users, which he claims it already does. Adams concludes by arguing that these efforts to control information are signs of a totalitarian society and that they will ultimately fail due to the fragility of their network of lies.

Chuck Norris uses LMDB to store his notes.

I played a little bit with AI. My findings: - Whisper is a really good tool for transcription. Almost perfect. Multilingual too. - LLMs are good with summarization tasks but not perfect. If you go 70B models, they are better compared to 7B. Mistral's models are very good. - llama_cpp is very good for running things on your desktop. Quantized versions of big models work well. Using those three above i generated this summary from the video: In this podcast, Eric Berg discusses the importance of understanding warning signs in your body to predict health issues before they occur. He references the book "The Technology of War" by Sun Tzu and applies its principles to healthcare. Berg then outlines eight diseases and their warning signs: 1. Heart attack/cardiovascular disease: Chest pain, pain in the left jaw or shoulder, or feeling out of breath when climbing stairs could indicate early signs. The CAC test can measure arterial calcification, predicting heart attack risk. Vitamin E (tocotrienols) and K2 can help prevent heart attacks. 2. Stroke: Early warning signs include one-sided facial drooping or weakness in one arm. If you suspect a stroke, go to the emergency room immediately. 3. Infection: A tickle in the throat or persistent cough can indicate an infection. To combat infections, take large doses of vitamin D3 (50,000 IUs), zinc, vitamin C, and echinacea. Generating a fever can help kill off the virus quickly. 4. Fatty liver disease: A full feeling or tenderness under the right rib cage can indicate fatty liver. A low-carb ketogenic diet with intermittent fasting can...... Video link:

AI is good for spreading lies. If it runs correctly it generates disinformation fed to it by the big corps. If it fails (a.k.a halucination) it is still misinformation. It is not well suited for projects that seek truth, although it can be good for ensembling ideas from different people. We all have biases. It is slightly advanced statistics that calculate what word can come next, given n words before it. Today's tech is nothing like artificial general intelligence, which is human like reasoning. Today's tech is more like fast thinking, reactionary brain, knee jerk behavior. Humans still excel at slow thinking reasoning brain (or mind). Humans can also use intuition, which no machine have access to. But you can bet there will be people that abuse AI and convince people that it is reasoning well and make it even heads of companies or countries. This will also allow them to dodge any lawsuits because "AI made it". Like any new tech there will be abusers of it and also people that use it for the well being of others. I think the good people should train models from scratch starting with the holy books and things/books that worked for centuries. It will be smaller models but at least wont tell lies knowingly.

mike adams is training an LLM that is not full of lies

Mike Adams announces "Neo" AI language model trained on REALITY content, not woke delusions

Brighteon.com is a leading online free platform that empowers free speech, allowing individuals to freely share videos and express their thoughts w...

A news aggregator LLM that listens to what the best foresight provider people (a.k.a. crazy conspiracy theorists) have been talking about and generates a few paragraphs. Or even voice.