3 min read

Recursion beats the pants off straight LLM again; it's the future, says MIT researcher

Orders-of-magnitude advantage recorded by making long prompts programmatically accessible, says new paper.
Recursion beats the pants off straight LLM again; it's the future, says MIT researcher
Photo by Egor Komarov on Unsplash

What happens if you treat a prompt for a long-horizon task as part of the external environment, so the LLM of your choice can decompose and chew over it recursively?

This post is for paying subscribers only