Anthropic team shares details on expanded CoT monitoring for model misbehavior

eliebakouch · x · 2026-08-19

Micah Carroll from Anthropic shared initial details on the expanded Chain of Thought (CoT) monitoring his team is working on. The team is happy to achieve much better visibility into model misbehavior going forward, with more information to be released soon.

Original post →

More from Safety

Safety channel →