full llm.txt files from web where it's just all of the docs rarely make sense.

An agentic approach allowing to navigate the docs and pick what is needed or manually pasting relevant pages is way more efficient

Farcaster Development Boutique @ https://dTech.vision 💜 in love with tech 🤓decentralization, fitness and oldschool rap 😎

Doesn’t Karpathy think one big context window is more effective?

For large code bases they are not yet big enough 

Also if I can do the picking of important info for the model with clear instructions the task description gets more precise leading to better outcomes

I believe eventually we just put as much as we want in there but not today (though way way better then 6 months ago already)

Most of what makes cursor better then anything else is its ability to manage what’s important to include

Just ask it to simplify the llms.txt to your relevant question and then restart with a new chat?

I don’t like new chats if one chat works I beat that one to death

It’s like the model is in flow and I don’t interrupt until it goes off trac


Not sure why but works quite well