HanneWhitt

Karma: 64

AI Safety Technical Research Manager at Meridian Research, Cambridge UK. Background in AI Control (MARS, LASR)

Unfaithful Reasoning Can Fool Chain-of-Thought Monitoring

Benjamin Arnav, Pablo Bernabeu Perez, Timothy Kostolansky, HanneWhitt, Nathan Helm-Burger and Mary Phuong

2 Jun 2025 19:08 UTC

78 points

17 comments3 min readLW link