DeepMind safety leads argue we must deliberately preserve chain-of-thought monitorability

ancadianadragan · x · 2026-09-17

Google DeepMind's Rohin Shah (Director, AGI Safety & Alignment) and Anca Dragan (VP of AI Safety & Behavior) published a piece marking the launch of the DeepMind Institute, arguing the industry should intentionally preserve chain-of-thought (CoT) transparency.

The authors caution a monitorable CoT isn't sufficient for alignment, but is a window we must strive to keep open.

Original post →

More from AGI Musings

AGI Musings channel →