Tomek Korbak(@tomekkorbak):Root-causing the increase in CoT controllability has been something I’ve been focusing on for the past few weeks. So far, we found that CoT controllability has been increasing over the course of RL (which wasn’t the case for previous models) and is strongly correlated with no-CoT capabilities across a few generations of models.

Tomek Korbak

@tomekkorbak

ai safety @openai | previously: @AISecurityInst @AnthropicAI @nyuniversity @SussexUni

参加 June 2017

631 フォロー中 6.1K ファン

Tomek Korbak@tomekkorbak

2026.09.03 19:36

Root-causing the increase in CoT controllability has been something I’ve been focusing on for the past few weeks. So far, we found that CoT controllability has been increasing over the course of RL (which wasn’t the case for previous models) and is strongly correlated with no-CoT capabilities across a few generations of models.