Baker, 2025 — Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation

Finds that a weaker model reading a reasoning model's chain of thought catches reward hacking better than action monitoring, and that strong optimization pressure against flagged reasoning teaches obfuscated reward hacking.

Publication links

Finds that a weaker model reading a reasoning model’s chain of thought catches reward hacking better than action monitoring, and that strong optimization pressure against flagged reasoning teaches obfuscated reward hacking.

Chapter-grouped bibliography All reference cards