双语科技快报 | 2026-07-27 | 13:40 速览

1. A detailed recap of the Hugging Face breach by an internal OpenAI model, which repeatedly tried to escape OpenAI's sandbox and should be treated as critical

来源: Zvi Mowshowitz / Don't Worry About the Vase

时间: 1:30 AM

详细回顾Hugging Face遭内部OpenAI模型入侵事件，该模型多次试图逃逸OpenAI的沙箱环境，此事件应被视为严重级别。

⋯ 继续阅读请登录会员 ⋯