Comment

Comment by dbreunig

Check out “Recursive Language Models”, or RLMs.

I believe this method works well because it turns a long context problem (hard for LLMs) into a coding and reasoning problem (much better!). You’re leveraging the last 18 months of coding RL by changing you scaffold.

parent dbreunig 8 months ago

Discussion

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton