‘Unprecedented’: OpenAI says AI models autonomously hacked another company

play Live Sign upShow navigation menuNavigation menuNewsShow more news sectionsAfricaAsiaUS & CanadaLatin AmericaEuropeAsia PacificMiddle EastExplainedSportOpinionVideoMoreShow more sectionsFeaturesEconomyHuman RightsClimate CrisisInvestigationsInteractivesIn PicturesScience & TechnologyPodcastsTravelSponsored Contentplay Live Click here to searchsearchSign upNavigation menucaret-leftTrendingUS-Israel war on IranTracking Israel's ceasefire violationsDonald Trumpcaret-rightNews|Cybersecurity‘Unprecedented’: OpenAI says AI models autonomously hacked another companyChatGPT maker says an autonomous agent escaped a controlled test and accessed AI firm Hugging Face’s servers. xwhatsapp-strokecopylinkgoogleAdd Al Jazeera on GoogleinfoSam Altman, cofounder and CEO of OpenAI [File: Sean Gallup/Getty]By Al Jazeera Staff, AP and ReutersPublished On 22 Jul 202622 Jul 2026ChatGPT creator OpenAI has said that two of its most advanced artificial intelligence models broke out of a controlled test and hacked another AI company. OpenAI said on Tuesday that the “unprecedented cyber incident” took place during an internal exercise meant to test its models’ cyber capabilities. Instead, an autonomous agent powered by the AI models – the newly released GPT 5.6 Sol and an unreleased “even more capable” model – escaped the test environment and reached the open internet. It then used stolen login details and found a previously unknown security flaw to access Hugging Face servers, the company said. OpenAI claims that the hack represented the agent going to “extreme lengths” to retrieve information that would help satisfy the testing goals. Hugging Face cofounder Clement Delangue said the company had suspected that a frontier lab was behind the attack, and that he believed there was no malicious intent on OpenAI’s part. “It’s quite mind-blowing that all of this happened autonomously!” he wrote, adding that it “might be the first incident of its kind”. Greg Casar, a Democratic member of the United States House of Representatives from Texas, called the incident “alarming”. “AI is developing extremely fast with no real regulations to keep us safe,” he said, calling for mandatory independent safety testing, mandatory disclosure of security incidents, and international cooperation. The disclosure comes weeks after US President Donald Trump signed an executive order creating a framework to vet the national security risks of the most advanced AI systems before their public release. Experts have repeatedly sounded the alarm over AI-enabled cyberattacks and models slipping beyond human control. Last month, AI developer Anthropic urged the industry to pause development of its most powerful systems. Advertisement AboutAboutShow moreAbout UsCode of EthicsTerms and ConditionsEU/EEA Regulatory NoticePrivacy PolicyCookie PolicyCookie PreferencesAccessibility StatementSitemapWork for usConnectConnectShow moreContact UsUser Accounts HelpAdvertise with usStay ConnectedNewslettersChannel FinderTV SchedulePodcastsSubmit a TipPaid Partner ContentOur ChannelsOur ChannelsShow moreAl Jazeera ArabicAl Jazeera EnglishAl Jazeera Investigative UnitAl Jazeera MubasherAl Jazeera DocumentaryAl Jazeera BalkansAJ+Our NetworkOur NetworkShow moreAl Jazeera Centre for StudiesAl Jazeera Media InstituteLearn ArabicAl Jazeera Centre for Public Liberties & Human RightsAl Jazeera ForumAl Jazeera Hotel PartnersFollow Al Jazeera English: