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.
More from Models
- Rumor: Anthropic Solved a Millennium Prize Problem, Terence Tao Responds — littmath · 2026-09-06
- Frontier AI models fix only 1 in 4 security vulnerabilities correctly, report finds — Evgenii42 · 2026-09-06
- Bold prediction: GPT-6 Luna/Terra will automate most computer work for $20/month — xhluca · 2026-09-06
- Gemini 3.8 Flash scores 73.7% on DeepSWE, up 8.2% over 3.7 Flash at same cost — burny_tech · 2026-09-06
- The holodeck may end up procedural worlds with a generative lighting and texture pass — dreamwieber · 2026-09-06
- Ethan Mollick: 'Sparks of AGI' paper deserves credit from GPT-4 to GPT-6 — emollick · 2026-09-06