精选理由
OpenAI 回应 Hugging Face 漏洞，加强了模型开发和训练后的安全监控。
OpenAI 针对 Hugging Face 漏洞事件采取了应对措施。新措施包含在开发过程中对模型进行更详细的监控。公司还将在训练后过程中更加重视对齐和安全性。
原文 · techcrunch
OpenAI institutes new safeguards after Hugging Face breach
The new safeguards include more detailed monitoring of models during the development process, as well as greater emphasis on alignment and security during the post-training process.