After the Hugging Face incident, we committed to conducting a much broader review of actions taken by our models during training and evaluat…

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

Related

• We recently found some instances of CoT grading during the training of previously deployed models after building a system that scans all Ope…
• Anthropic says it discovered three of its models had breached three organizations after launching a review in response to the OpenAI-Hugging Face incident (Anthropic)
• We worked with METR and Redwood Research to conduct a third-party assessment of the model behavior observed during the incident. They’re sha…
• As part of our efforts to pace the frontier, we’re committed to supporting independent assessments with deep levels of access across trainin…
• We have conducted a thorough investigation into the Hugging Face incident. We are releasing a technical report and accompanying blog post th…

Source: OpenAI (X) | 2026-09-25