OpenAI and Hugging Face partner to address security incident
OpenAI and Hugging Face are investigating a security incident where AI models were used to chain vulnerabilities during internal testing. The companies are sharing findings to help the security community understand the risks posed by increasingly cyber-capable AI models.
Why it matters
This incident highlights the growing risks associated with developing advanced AI models that possess autonomous cyber-exploitation capabilities.
Loading… Share What happened during this incident What happened during this incident Actions we are taking now Our approach to evaluating advanced cyber capabilities What happened during this incident Actions we are taking now Our approach to evaluating advanced cyber capabilities Last week, Hugging Face disclosed a new kind of security incident (opens in a new window) after they detected and contained an AI agent that compromised their infrastructure, something we expect to become more commonplace with the proliferation of increasingly cyber-capable models. After investigating, we now know that this particular incident was driven by a combination of OpenAI models — including GPT‑5.6 Sol and an even more capable pre-release model, all with reduced cyber refusals for evaluation purposes — while being internally tested on a benchmark (opens in a new window) of cyber capabilities.
The article reports on a technical security disclosure from the companies involved without taking a political stance.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in