OpenAI’s rogue AI model incident was worse than we thought

<figure> <img alt="An illustration showing a computer with the OpenAI logo." data-caption="OpenAI released a report breaking down how people use ChatGPT and who they are. | Image: The Verge" data-portal-copyright="Image: The Verge" data-has-syndication-rights="1" src="https://platform.theverge.com/wp-content/uploads/sites/2/2025/04/STK_414_AI_CHATBOT_R2_CVirginia_B.jpg?quality=90&#038;strip=all&#038;crop=0,0,100,100" /> <figcaption> OpenAI released a report breaking down how people use ChatGPT and who they are. | Image: The Verge </figcaption> </figure> <p class="wp-block-paragraph">In July, an unreleased OpenAI model broke out of a restricted environment, figured out how to get access to the internet, allowed AI agents to talk to each other using a secret "message board," and hacked into the internal systems of a different AI lab, Hugging Face. It took nearly two weeks for OpenAI to find out about any of it. </p> <p class="wp-block-paragraph">Over a month later, two new reports offer nearly 130 pages of details on the incident and OpenAI's response, many of them previously unreleased. <a href="https://cdn.openai.com/pdf/67869394-cb91-4c12-888c-5cbd85c7814c/OpenAI-Hugging-Face%20Incident-Technical-Report.pdf">One</a> was written by OpenAI itself, <a href="https://metr.org/blog/2026-08-26-openai-hugging-face-incident-investigation/">the other</a> by two third-party AI research nonprofits, METR and Redwood Research, which OpenAI allowed to jointly investigate the inciden …</p> <p><a href="https://www.theverge.com/ai-artificial-intelligence/985385/openais-rogue-ai-model-hugging-face-cybersecurity-incident-reports-metr">Read the full story at The Verge.</a></p>