Greenblatt: OpenAI blocking reasoning=None hurts AI monitorability research

RyanGreenblatt · x · 2026-09-06

Ryan Greenblatt (Redwood Research) argues OpenAI's move to remove the reasoning=None option from its public API makes monitorability research harder, not safer: models can still reason latently without verbalizing, and the higher-capability reasoning-on case is the more concerning one. He suspects the real motives are jailbreak robustness or anti-distillation, notes Anthropic also disallows disabling CoT for Fable, and proposes a low-bar researcher access program to restore no-CoT experimentation.

Original post →

More from Models

Models channel →