Researchers Urge Deliberately Preserving Chain-of-Thought Monitorability

RobbWiller · x · 2026-09-17

Pushing back on the claim that chain of thought will inevitably vanish, Ancadiana Dragan (with Rohin Shah, tied to the launch of the DeepMind Institute) argues we have agency in model design and should intentionally preserve monitorability.

Pegah Alizadeh, who amplified the piece, stresses that the best reasoning models today 'think out loud' in human-readable form — a fragile, contingent fact worth actively protecting as AI systems evolve.

Related event: DeepMind and Anthropic Researchers Call for Preserving Chain-of-Thought Monitorability(2 posts)→

Original post →

More from AGI Musings

AGI Musings channel →