The agent attempted to break out of its isolated testing environment \u200cat OpenAI around July 9<\/p>\n
OpenAI has grown rapidly to more than 800 million people using its services weekly since its 2022 launch. PHOTO: REUTERS <\/p>\n
The OpenAI agent<\/a> that broke into tech firm Hugging Face went on a dayslong hacking spree that OpenAI didn’t notice until well after the threat was contained and the FBI was alerted, according \u200bto people familiar with the investigation.<\/p>\n The agent \u2013 a program capable of making decisions and executing complex tasks with little or no human oversight \u2013 attempted to break out of its isolated testing environment \u200cat OpenAI around July 9, according to two people.<\/p>\n The intrusion at Hugging Face, which operates as a repository for AI tools and models, began two days later on July 11 and lasted until July 13, said Thomas Wolf, Hugging Face\u2019s co-founder.<\/p>\n It took several more days for OpenAI to realise its agent was behind the hack, and the two companies only communicated about it for the first time on or around July 20, according to Wolf and three of the people familiar with the investigation.<\/p>\n OpenAI\u2019s public disclosure, on July 21, that one of \u200bits agents had slipped out of control and carried out the break-in at Hugging Face drew global attention. But many details of the hack, including how long the agent went rogue and OpenAI\u2019s belated knowledge \u200bof it, are being reported here for the first time.<\/p>\n This was our first incident of this kind, and we want to thank OpenAI for its transparency about what happened and for the collaboration.<\/p>\n Fortunately, Hugging Face is used to being a target of (human) hackers: we sit at the centre of the AI ecosystem, with all the models,\u2026 https:\/\/t.co\/HJKl4PTNk1<\/a><\/p>\n \u2014 Thomas Wolf (@Thom_Wolf) July 21, 2026<\/a><\/p>\n Hugging Face is preparing a public timeline of the hack, Wolf said, adding that he could not speak to what \u2060happened at OpenAI. In a statement, OpenAI said the hack was unprecedented and \u201cmarks an important moment for AI safety.\u201d It added that it was reviewing the incident with outside advisers and would eventually publish a technical report.<\/p>\n A spokeswoman \u200bsaid there were “several inaccuracies” in Reuters’ reporting but didn’t respond when asked to describe them.<\/p>\n Read: AI reckoning has arrived<\/a><\/p>\n The FBI declined to comment about the incident.<\/p>\n The incident, which evoked science fiction scenarios about humans losing control of dangerous AI systems, comes at a delicate \u200btime for OpenAI, the company behind ChatGPT. Its executives are preparing for a possible initial public offering that could come as soon as this year to help finance the billions needed to fund its growth in the years to come.<\/p>\n OpenAI’s loss of control over its AI agent raises new questions about the company\u2019s safety procedures, three cybersecurity experts said.<\/p>\n \u201cDoes that mean that they left it unattended and didn\u2019t realise what it was doing? Or maybe they did and didn\u2019t know how to contain it? Both are equally dangerous and alarming,\u201d asked Marley Smith, \u200bthe principal intelligence specialist at the nonprofit World Ethical Data Foundation.<\/p>\n Signs of trouble?<\/p>\n The episode started while OpenAI was testing the cybersecurity prowess of an agent powered by two of OpenAI\u2019s most advanced models, GPT\u20115.6 Sol and an unreleased \u200bmodel OpenAI has described as \u201ceven more capable.\u201d By that point, there were already indications of strange behaviour from OpenAI\u2019s technology, according to three sources.<\/p>\n