flâneur — a map of the web's best reading

How to scale RL to 10^26 FLOPs - by Jack Morris

blog.jxmo.io · 3,467 words · saved by 1 readers

TLDR: Reinforcement learning (RL) is the next training technique for building frontier-level AI models. To make it better, we need to train on more data. The current approach of scaling many environments simultaneously is messy and complicated. Instead, I propose we find a way to do next-token prediction on the Web using RL. This way, we learn to reason from general web data, instead of just math and code. I’ve spent a good part of the past year in denial. Thanks for reading! Subscribe for free to receive new posts and support my work. 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. After all, letting models ‘think for longer’ by generating more tokens lets them do more internal computation. So I wasn’t that surprised that these new models, termed reasoning models, gave better answers. And I especially wasn’t surprised when I found out

How to scale RL to 10^26 FLOPs A roadmap for RL-ing LLMs on the entire Internet Jack Morris Jul 10, 2025 62 11 7 Share TLDR: Reinforcement learning (RL) is the next training technique for building frontier-level AI models. To make it better, we need to train on more data. The current approach of scaling many environments simultaneously is messy and complicated. Instead, I propose we find a way to do next-token prediction on the Web using RL. This way, we learn to reason from general web data, instead of just math and code. I’ve spent a good part of the past year in denial. Thanks for reading!

Explore this link on the map →

related reading