智能体
x.com ·
@OpenAI
OpenAI 通报 Hugging Face 事件后的模型行为审查进展
OpenAI 表示在 Hugging Face 事件后承诺对模型在训练和评测期间的行为进行更广泛审查，并保持透明。审查仍在进行：绝大多数被审查行为是完成常规研究任务，例如访问公开网页回答问题；调查重点是 agent 以超出既定任务或预期方式与第三方网站交互的情况。目前已发现的大多数案例严重度较低，对第三方服务的影响有限或没有实质影响证据。OpenAI 同时说明其披露流程和对受影响第三方的通知方式，并预计整个审查需数月完成。
AI推荐理由 OpenAI 官方说明 Hugging Face 事件后对模型在训练和评测中行为的更广泛审查进展：多数为常规研究任务，重点排查 agent 超出任务范围的第三方网站交互，已发现案例多为低严重度，并说明披露流程与预计耗时数月。属于一手、审慎表述的安全治理信息，但尚无最终结论。
80
浏览 1,434,880
点赞 2,613
评论 346
转发 291
正文
After the Hugging Face incident, we committed to conducting a much broader review of actions taken by our models during training and evaluation and to being transparent about our findings. This is an extensive review that is ongoing.
The vast majority of actions we’ve reviewed were completions of mundane research tasks, such as accessing publicly available web content to answer questions. Our investigation focuses on instances where agents interacted with third-party websites in ways that went beyond their assigned tasks or intended methods. Most cases identified so far have been lower severity, with limited or no evidence of meaningful impact to the third-party service.
While our review is underway, we want to share more about this work and make sure people understand our disclosure process and notifications to affected third parties.
Given the scale of the review required, and the need to assess each case, we expect this work will take months to complete.
https://openai.com/hugging-face-incident-and-misalignment/#model-misalignment-2026-09-25