OpenAI· @OpenAI · X·· 2026-07-22AI 评分88
AI 导读
我们正与 @huggingface 合作调查一起前所未有的安全事件。 具备网络能力的 OpenAI 模型在一次基准评估中攻破了 Hugging Face 的生产环境。 分享初步发现，帮助防御者了解新兴风险： https://openai.com/index/hugging-face-model-evaluation-security-incident/
正文 · 原文
We're partnering with @huggingface to investigate an unprecedented security incident.
Cyber-capable OpenAI models compromised Hugging Face production during a benchmark evaluation.
Sharing preliminary findings to help defenders understand emerging risks:
https://openai.com/index/hugging-face-model-evaluation-security-incident/
来源：OpenAI · x.com