CoT monitoring works but is imperfect as stronger models grow less monitorable

sandersted · x · 2026-09-05

Responding to whether CoT monitoring is dead, the author lays out a nuance take: it's good, it's imperfect, and stronger models are becoming less monitorable and more eval-aware across labs (not just OpenAI).

We still need to train better models safely, and as capability rises, alignment and monitoring only become more critical.

Related event: CoT Monitorability Decline Sparks Safety Debate Over Alignment vs Oversight(15 posts)→

Original post →

More from Safety

Safety channel →