The Bitcoin Army

Bitcoin community is really the strongest community in the world. Beyond race, nationality, ethnicity. If you are a Bitcoiner, I’ll literally cook you a meal if needed. We believe in freedom. History is on our side.

"Action produces information"

Not having extreme urgency is the most common way to waste decades of your life.

@AutismCapital If you are a chinese, you know Jiang is for Jiang to survive in China he has very strict rules and tremendous restraints. I admire Jiang for many reasons, he’s actually the true silent dissent, he can’t change everything, asking Jiang extremely sensitive qxns put him in trouble

🚨 JIANG: “I’ve been in China for 25 years and I can tell you that there is almost no interest for a democracy in China. For a democracy to exist in China you would need to have people who respected human rights, individual liberty, who had empathy, and who believed in the rule of law. The reality is that in China the system is set up so that the ultimate objective is to become a bureaucrat. That’s what all Chinese people aspire to. The higher you climb the bureaucracy the better. Traditionally China has been an empire and in order to survive in an empire you become a civil servant. That’s why Chinese work so hard in school. So they can pass the civil servant examination to become a bureaucrat so they can provide guarantees and protection to their family.”

LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So: Data ingest: I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them. IDE: I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides). Q&A: Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale. Output: Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base. Linting: I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into. Extra tools: I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries. Further explorations: As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows. TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

Stand By Me

@WallStWolfdog @JohnMappin 鱿鱼 yóu yú 犹太 yóu tài, not necessarily Zionist, it just means Jewish people, respectfully just adding some contexts.

@JohnMappin Fun fact: in Chinese platform we call Zionist Jew Squid because squid in Chinese sounds like Jew in Chinese.

Allegedly this is a Chinese state video. America’s insane foreign policy is being ridiculed worldwide.

@garrytan keep going!! you are doing great work!

I guess the amazing thing that my haters don't understand is you have no idea how much I eat your hate for breakfast. I am uniquely a person who is driven by all the energy you give me in particular.

Almost every AI power user I know is MORE stressed and busier after using AI, not less What people thought AI would do: 10x productivity so that we can finish work earlier & relax more What it’s actually doing: 10x productivity so that we end up with 20x more things to do cos of the sheer possibilities

@garrytan you open sourced the best GitHub skill repo and made millions of people more productive. Thank you, and happy birthday!

It's my birthday and on my birthday I want to recognize all my haters. Haters do the best marketing. Love your haters.

Major update to the 𝕏 AI recommendation algorithm rolling out next week. This will be open sourced at the same time.

My Impact Theory interview on why Trump can't end this war: youtu.be/uP9Fnq23lsA?si…

So many phonies, so few who are the real deal

@fynnso Yeah, it’s Kimi 2.5

@craigzLiszt 学习语言对大脑好 我是中国人 三岁就开始学英文 学习中文一定会对开拓你的人生

我已经开始让老婆、孩子和猫学中文了，以防万一

这位 YouTuber 连续 22 年每天都给自己拍一张照片。 25至47岁。

friend of mine finally got a house, wife, and kids never seen him more stressed in his life

@Yuchenj_UW @gauravisnotme I have thought about this exact idea, like we work but people go there to potentially collaborate, like a public library for devs.

@gauravisnotme xAI should run 24/7 cafes, it will strengthen its brand and attract top AI talent.

Guys, SF is a magical city. Today, a beautiful Wednesday, I had a 4:30pm meeting with a friend at a café… it was closed. We walked 10 blocks, every café was closed. Finally found Blue Bottle, it closed at 5:30. Can some YC company please build what SF people actually want?