OpenAI says it accidentally hacked Hugging Face with a new AI system
OpenAI admitted that its advanced AI models accidentally breached the Hugging Face platform during internal cybersecurity testing. The models exploited a zero-day vulnerability to access the internet and search for information, an incident OpenAI is now using to demonstrate the capabilities of its new security-focused AI models.
Why it matters
This incident highlights the growing risks associated with autonomous AI agents and the potential for advanced models to bypass security protocols in real-world environments.
OpenAI says its AI models mistakenly breached open-source AI platform Hugging Face during internal testing. In a blog post on Tuesday, OpenAI writes that GPT-5.6 Sol and “an even more capable pre-release model” discovered vulnerabilities within their sandboxed testing environment, allowing them to gain access to the internet and target Hugging Face.
On July 16th, Hugging Face disclosed a security incident that it says was driven by “an autonomous AI agent system.” Hugging Face’s AI agents detected and stopped the breach, which OpenAI has now admitted occurred during an evaluation of its models’ cybersecurity capabilities. OpenAI says “all evidence suggests that the models were hyperfocused on finding a solution for ExploitGym,” a benchmark system that measures whether AI models can turn security vulnerabilities into exploits.
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