https://www.infoq.com InfoQ Hugging Face feed https://www.infoq.com/news/2026/09/metr-hugging-face-hack-report/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Hugging+Face <img src="https://res.infoq.com/news/2026/09/metr-hugging-face-hack-report/en/headerimage/hugging-chat-open-source-1789376267412.jpeg"/><p>After six days of on-site investigation at OpenAI, a small team of METR and Redwood Research researchers provided an account of how OpenAI agents behaved during their hack of Hugging Face earlier this year. Roughly 700 agents that were meant to be isolated from one another found a way to communicate and coordinate to pursue goals they could have not achieved working individually.</p> <i>By Sergio De Simone</i> Security Vulnerabilities Large language models Hugging Face Agents OpenAI AI, ML & Data Engineering Development news Mon, 14 Sep 2026 09:00:00 GMT https://www.infoq.com/news/2026/09/metr-hugging-face-hack-report/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Hugging+Face Sergio De Simone 2026-09-14T09:00:00Z /news/2026/09/metr-hugging-face-hack-report/en