How to Build a Personal LLM Knowledge Base (Karpathy’s Method)

A few days ago, Andre Karpathy, who's one of the early members of OpenAI and literally coined the [music] term vibe coding, posted a tweet that got 14 million views in 72 hours. And when Lex Fridman saw it, he replied and said, "I do the exact same thing. " So, what are two of the [music] smartest people in AI doing with their time right now? And the answer is that they are building personal [music] LLM knowledge bases. I've also heard this called an AI second brain, but it is an AI-maintained wiki that grows over time. You can ask complex questions against [music] it, and it never forgets anything, so it gets stronger over time. And they do the whole thing using just Obsidian, Claude, and your local computer files. And in this episode, I'm going to show you exactly [music] how to build one. Cuz if the smartest people in AI are doing this, we probably should be too. So, before I show you the tutorial, let me walk you through how this thing works at a high level. Cuz once you understand the concept, the tutorial will make way more sense. There's three phases: collect, compile, and query. Step one is collect. You find the best content on the topic that you want to get smarter about. The example that I'm going to use for the tutorial is lifting for hypertrophy, so building muscle, cuz that's something I let slip over the past few months, but I'm getting back into now and really want to optimize it. And the thing is, LLMs know a lot of information, but it's sort of an aggregate of what is generally agreed upon. And so, if you want cutting-edge research or more niche information, it's it's harder to get that from an LLM. So, you find the best content on the topic that you're interested in.