Get the latest tech news
How to scale RL to 10^26 FLOPs
A roadmap for RL-ing LLMs on the entire Internet
I was in denial because when OpenAI released o1, and explained their paradigm of test-time compute, I thought it was a good idea but mostly a way to get better performance out of models of fixed size. And I especially wasn’t surprised when I found out these answers mostly came on problems that inherently require lots of computation, like difficult math and engineering test questions. Given an LLM-generated answer to a coding problem, we may need to run a bunch of unit tests and count the number of ones that pass to provide a reward.
Or read this on Hacker News
