Detecting misbehavior in frontier reasoning models

媒体报道 OpenAI 原文语言:英文

原文摘录

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.

以下是来源提供的简短摘录,完整内容请查看原文。

参考来源

← 返回每日AI报告