he rigs up 10 RTX 4090s, runs protein folding simulations, loads local LLMs for privacy, talks about quantization, multi-GPU sharding, RAG, how SLMs are underrated, AND says he’s fine-tuning his own model.
bro knows AI more than most of the AI influencers here.
Google published a 69-page whitepaper on Prompt Engineering and its best practices, a must-read if you are using LLMs in production:
> zero-shot, one-shot, few-shot
> system prompting
> chain-of-thought (CoT)
> ReAct
> code prompting
> best practices
Claude 3.7 Sonnet making a 3blue1brown kind of video like it's nothing
the moment we have ai that makes videos like this, learning will be much different
"I use AI in a separate window. I don't enjoy Cursor or Windsurf, I can literally feel competence draining out of my fingers."
@dhh, the legendary programmer and creator of Ruby on Rails has the most beautiful and philosophical idea about what AI takes away from programmers.
he’s right on point. you can actually LOVE studying new subjects. here’s how (i broke down 26 minutes of video):
> approach it with curiosity like a kid. gaslight yourself into having that curiosity, it produces dopamine, and brings focus and enjoyment. be like Feynman.
> track
a senior engineer at google just dropped a 400-page free book on docs for review: agentic design patterns.
the table of contents looks like everything you need to know about agents + code:
> advanced prompt techniques
> multi-agent patterns
> tool use and MCP
> you name it