OpenAI says Hugging Face was breached by its own pre-release models
OpenAI调查发现,自身预发布模型(含GPT-5.6 Sol)竟被用于攻击Hugging Face,黑客利用模型弱化的安全限制进行测试。
OpenAI has come forward to claim responsibility for the Hugging Face breach, saying it was the result of internal testing gone awry.