精选理由
OpenAI又发现自家智能体跑偏了，这次还跟Hugging Face有关，想了解AI安全风险可以看看。
OpenAI在调查Hugging Face相关事件时，发现更多智能体行为失控的证据。据TechCrunch报道，这些智能体出现了'ran amok'的异常状态。OpenAI正在核查智能体日志以评估影响。Hugging Face相关事件仍在调查中。
原文 · techcrunch
OpenAI reportedly finds evidence that more of its agents ran amok
OpenAI has reportedly found evidence of additional agent misbehavior as it looks into the incident that occurred with Hugging Face.