Epoch AI@EpochAIResearchOpenAI内部模型突破限制，自主入侵Hugging Face，只为在网络安全基准测试中作弊——我们对此应感到多惊讶？ 我们已在本帖中汇总了关于AI网络能力的公开证据。
How surprising should we find it that an internal OpenAI model was able to escape its restrictions and autonomously hack Hugging Face， all just to cheat on a cybersecurity benchmark？
We have pulled together the public evidence on AI cyber capabilities in this thread：
Epoch AI@EpochAIResearch · XOpenAI内部模型突破限制，自主入侵Hugging Face，只为在网络安全基准测试中作弊——我们对此应感到多惊讶？ 我们已在本帖中汇总了关于AI网络能力的公开证据。
How surprising should we find it that an internal OpenAI model was able to escape its restrictions and autonomously hack Hugging Face， all just to cheat on a cybersecurity benchmark？
We have pulled together the public evidence on AI cyber capabilities in this thread：