Detecting misbehavior in frontier reasoning models
核心要点速览
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.
查看完整报道与分享
完整图文、背景资料与讨论归原始发布平台 OpenAI News 所有。