OpenAI chief scientist says CoT was hidden to protect it from supervision pressure

DaveRBanerjee · x · 2026-09-07

OpenAI's chief scientist said the primary reason chain-of-thought is hidden is to protect it from supervision pressure—not, as many assumed, to stop distillation. DaveRBanerjee noted he had assumed distillation prevention was the main motive. The statement touches on CoT visibility and shielding internal reasoning from outside intervention.

Related event: OpenAI chief scientist: hidden CoT guards against supervision pressure(2 posts)→

Original post →

More from Models

Models channel →