Rusev

Karpathy's LLM Wiki concept + Obsidian + Claude Code = the best personal knowledge base I've ever had. Drop a source in → Claude creates structured, cross-linked wiki pages automatically. Knowledge compounds with every new book or article Details below: @evgeni.n.rusev/how-i-built-my-second-brain-with-obsidian-claude-code-9fb54b7665ca" target="_blank" rel="nofollow noopener">medium.com/@evgeni.n.ruse…

@APompliano Poor Charlie's Almanack: The Essential Wit and Wisdom of Charles T. Munger

What was the best thing you read, watched, or listened to this week? Any topic is fair game.

@APompliano What are some mental models that people can recommend?

The smartest people I know: 1. Obsessively read books 2. Pursue new mental models 3. Enjoy intelligent discourse 4. Quickly admit when they're wrong 5. Comfortable changing their opinion 6. Surround themselves w/ intelligence 7. Seek to understand every perspective on a topic

@hwchase17 I agree with your points. I learned the hard way that it’s much better to focus on simplicity & common-sense software engineering patterns instead of thinking in terms of these frameworks. Minimalistic abstractions can still help such as Pydantic and Instructor.

OpenAI recently released a guide on building agents which contains some misguided takes There's a lot of FUD, confusion, hype, and noise around agents I wrote a blog on how to think about agent frameworks. Includes: Background Info - What is an agent? - What is hard about building agents? - What is LangGraph? Flavors of agentic frameworks - “Agents” vs “workflows” - Declarative vs non-declarative - Agent abstractions - Multi agent Common Questions - What is the value of a framework? - As the models get better, will everything become agents instead of workflows? - What did OpenAI get wrong in their take? - How do all the agent frameworks compare?

@512x512 Is it as good as o1 or 4o for coding? If yes, I can switch

Have you used ChatGPT, Claude or Perplexity today? How can we improve Grok to make you switch?