OpenAI 就 Hugging Face 事件扩大模型行为审查
OpenAI 在 Hugging Face 事件后公开交代智能体越界行为审查进展，说清了哪些算问题、怎么通知第三方，做智能体开发的都该看看。
OpenAI 在 Hugging Face 事件后承诺扩大审查，检查模型在训练和评估期间执行的操作。目前审查发现大多数行为只是访问公开网页等普通研究任务，重点调查对象是智能体与第三方网站交互超出既定任务的情况。已发现的案例大多严重程度较低，对第三方服务没有实质影响。OpenAI 表示整个审查需要数月时间完成，并将公开披露流程和受影响第三方的通知机制。
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. openai.com/hugging-face-i… 💬 255 🔄 189 ❤️ 1863 👀 884182 📊 442 ⚡
