CoT controllability rises during RL training and tracks no-CoT capability across model generations

tomekkorbak · x · 2026-09-04

Researcher tomekkorbak shares root-cause analysis from recent weeks: CoT controllability increases over the course of RL training, which was not the case for previous models, and it is strongly correlated with no-CoT capabilities across several generations of models.

Related event: DeepMind Researcher Warns CoT Monitorability Is Declining(4 posts)→

Original post →

More from Research

Research channel →