Evidence · DiggingBeagle record

OpenAI: CoT monitorability changes through pretraining and reinforcement learning

Original research on no-chain-of-thought capability and reasoning-trace controllability, distinct from observed full trajectory monitor evasion.

Published
Nov 10, 2026
Source role
primary disclosure

Evidence record

Original research on no-chain-of-thought capability and reasoning-trace controllability, distinct from observed full trajectory monitor evasion.

Read the original source ↗

Claim-level citations (2)