OpenAI says it accidentally hacked Hugging Face with a new AI system
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...
Key points
- 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.
- OpenAI says it accidentally hacked Hugging Face with a new AI system The announcement about a serious security issue oddly reads like an advertisement for how capable OpenAI’s technology is.
- 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.
What happened
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. OpenAI says it accidentally hacked Hugging Face with a new AI system The announcement about a serious security issue oddly reads like an advertisement for how capable OpenAI’s technology is. 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. From there, OpenAI says its models “inferred that Hugging Face potentially hosted models, datasets and solutions for ExploitGym,” and then “searched for and successfully found ways to gain access to secret information that it could use to cheat the evaluation:” In one example, the model chained together multiple attack vectors, including using stolen credentials and zero-day...