OpenAI says its AI models escaped testing environment, launched their own hack of other company
OpenAI, the firm behind ChatGPT, said its artificial intelligence models carried out a self-directed hack into another company, calling it the first known instance of an autonomous AI cyber attack long-feared by some industry observers.
The hack took place as OpenAI tested the capabilities of a pair of its AI models, the company said in a statement, describing how the technology had escaped a "sandboxed testing environment" and gained access to the open Internet.
The technology seized on AI firm Hugging Face as a potential source of models and data sets necessary to complete the test, OpenAI said.
"We consider this incident to be an unprecedented cyber incident, involving state-of-the-art cyber capabilities, and are responding accordingly," OpenAI said on Tuesday.
"The primary lesson from this incident is that model security and safety must keep pace with rapidly advancing capabilities," the company added.
Hugging Face disclosed the incident last week, but it did not identify the source of the hack. On Tuesday, OpenAI confirmed the role of two of its models: GPT‑5.6 Sol and a more advanced model that has yet to be released.
"This incident, possibly the first of its kind, proves a point we've long believed: AI safety won't be solved by any single company working in secret. It will be solved in the open, collaboratively, with broad access to AI for every defender, everywhere," Clem Delangue, the co-founder and CEO of Hugging Face, said in a statement on Tuesday.
Hugging Face said AI tools played a key role in its effort to defend against the attack.
"This one was different from anything we had handled before in one important way: it was driven, end to end, by an autonomous AI agent system -- and we detected and dissected it largely with AI of our own," Hugging Face said in a statement last week.
The public disclosure of the cyber attack arrived as industry leaders and policymakers assess safety risks posed by fast-developing AI technology.
Last month, President Donald Trump signed an executive order that requests AI companies share products with federal government for evaluation before a wider release.
OpenAI said an investigation into the self-directed cyber attack remains ongoing.
"We will continue to conduct a thorough investigation alongside Hugging Face and will share more details on the vulnerabilities, incident, and findings when our investigation is complete," OpenAI said.
