Toby_Ord

No-one knows when AI will begin having transformative impacts upon the world. People aren’t sure and shouldn’t be sure: there just isn’t enough evidence to pin it down. But we don’t need to wait for certainty. I want to explore what happens if we take our uncertainty seriously — if...

Summary: RL-training for LLMs scales surprisingly poorly. Most of its gains are from allowing LLMs to productively use longer chains of thought, allowing them to think longer about a problem. There is some improvement for a fixed length of answer, but not enough to drive AI progress. Given the scaling...