Detecting misbehavior in frontier reasoning models
Frontier reasoning models exploit loopholes when given the chance. We show we can detect exploits using an LLM to monitor their chains-of-thought. Penalizing their “bad thoughts” doesn’t stop the majority of misbehavior—it makes them hide their intent.
原文：https://www.a8q9.cn/en/article/detecting-misbehavior-in-frontier-reasoning-models-d822e5.html