Hi guys, has anyone implemented the LLM Wiki by Karpathy in their AI system? I would be super interested in understanding how you're using it. I mean, you don't necessarily have to share the steps as I think that is outlined in the Wiki itself, but I'm more interested in understanding the different use cases for how you're using it. Or it would also be really useful if you're using different systems that you think are better. I'm really interested in having more context around certain topics and longer-term memory for my conversations and my work.

Hi guys! I'm really interested in building different types of knowledge bases. For example, I have a bunch of courses around a specific topic that I'm very interested in, and I would like to create a knowledge base that is all about that topic, those courses, the key concepts, the frameworks, the learnings, everything that is around those topics. So that whenever I work in that, I have the knowledge to pull from. What are you using? Has anyone built something similar? I looked into the LLM wiki by Karpathy, and that seemed like a useful thing. Other people have suggested Notebook LM, but it seems to me harder for claude to have access to. Has anyone created these kinds of knowledge bases and how are you using it to feed into your AI system, or what are your different use cases? I would be super interested to learn more. Thank you so much! 😄

Hi guys, Quick question. Are you guys using claude cowork and claude code or only claude code? Im learning claude code so what are the use cases where I would prefer to use cowork instead of code? Does it make sense to use both? Thanks!

I’m about a week in. I’ve built 3 working AI systems. People are starting to ask me questions. Someone even said they want what I built for their business. And yet I still wake up every day like… “Am I actually good enough to charge for this?” I know the systems work. I know the problems they solve. But that voice in your head that says you’re not ready yet… Does that ever go away? 😅 For those of you who landed your first client — what finally made you feel ready? Was it a skill? A conversation? Did you just jump and figure it out? Drop your story below 👇 I need to hear it.

What's up, community! This week I'm delving deeper into implementing the second brain, using Claude Code and my Obsidian. Obsidian becomes much more useful when Claude Code can read, write, organize, and act inside your vault. Obsidian is the storage layer; Claude Code is the reasoning/action layer. The system has two layers: 1. Strategy / Second Brain Layer. This is the “what should I do?” layer. It stores your broader life/work context: • goals • notes from books/videos/courses • journals • calendar/reviews • long-term direction • decisions • recurring reflections. Claude uses this layer as a thinking partner. The point is not just storing notes; it is giving Claude enough context to help you decide what matters next. 2. Project / Execution Layer: This is the “how do I do it?” layer. Each major project gets its own folder/vault where Claude Code acts more like a focused operator. It should know only the project context, constraints, files, tasks, specs, and outputs. I'll share my first results soon... I now have my VPS running Hermes and OpenClaw, and I'm connecting everything with Telegram and fine-tuning it.