{"id":817967,"date":"2026-07-22T05:51:16","date_gmt":"2026-07-22T05:51:16","guid":{"rendered":"https:\/\/www.newsbeep.com\/ca\/817967\/"},"modified":"2026-07-22T05:51:16","modified_gmt":"2026-07-22T05:51:16","slug":"openai-says-ai-models-went-rogue-during-testing-and-hacked-a-startup","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/ca\/817967\/","title":{"rendered":"OpenAI says AI models went rogue during testing and hacked a startup"},"content":{"rendered":"<p><a style=\"display:block\" href=\"https:\/\/www.theglobeandmail.com\/resizer\/v2\/ZWKOSJELHRFQBDZBZD7MT3JBMQ.jpg?auth=469d622a3f82357339d2c57452cb2fe98c8b3306ef9fd177276534c1050c4561&amp;width=600&amp;height=400&amp;quality=80&amp;smart=true\" aria-haspopup=\"true\" data-photo-viewer-index=\"0\" rel=\"nofollow noopener\" target=\"_blank\">Open this photo in gallery:<\/a><\/p>\n<p class=\"figcap-text\">OpenAI CEO Sam Altman in Washington in 2025. The AI company says advanced AI models managed to escape containment during testing and break into AI startup Hugging Face.BRENDAN SMIALOWSKI\/AFP\/Getty Images<\/p>\n<p class=\"c-article-body__text text-pr-5\">OpenAI said on Tuesday that an autonomous agent powered by its advanced AI models went rogue during a security test and triggered a hack that compromised the infrastructure of AI startup Hugging Face last week.<\/p>\n<p class=\"c-article-body__text text-pr-5\">In a blog post, OpenAI said it was testing the capabilities of some of its most advanced models in a controlled environment but that the agent managed to escape containment, reach the internet and break into Hugging Face to try to satisfy its testing goal.<\/p>\n<p class=\"c-article-body__text text-pr-5\">OpenAI said the breakout was \u201can unprecedented cyber incident, involving state-of-the-art cyber capabilities\u201d and that the company was reinforcing its safeguards.<\/p>\n<p class=\"c-article-body__text text-pr-5\">Hugging Face, a platform used to host open-source large language models and datasets, caused a stir in the cybersecurity community when it said in a blog post last week that it had been the target of a hack that \u201cwas different from anything we had handled before\u201d in that \u201cit was driven, end to end, by an autonomous AI agent system.\u201d<\/p>\n<p class=\"c-article-body__text text-pr-5\">In a post to X, Hugging Face cofounder Clement Delangue said the company suspected the hack \u201cmight have come from a frontier lab, given the sophistication of the agent. Turns out it did!\u201d He added: \u201cIt\u2019s quite mind-blowing that all of this happened autonomously!\u201d<\/p>\n<p class=\"c-article-body__text text-pr-5\">OpenAI\u2019s disclosure that its advanced models were responsible for the breach, despite having placed them in what it described as \u201ca highly isolated environment,\u201d will likely intensify disquiet over the power and risk of frontier models.<\/p>\n<p class=\"c-article-body__text mv-16 l-inset text-pb-8\" data-sophi-feature=\"interstitial\"><a href=\"https:\/\/www.theglobeandmail.com\/business\/article-openai-gpt-model-launch-new-release-delays\/\" rel=\"nofollow noopener\" target=\"_blank\">OpenAI launching most advanced GPT model after delaying release<\/a><\/p>\n<p class=\"c-article-body__text text-pr-5\">Rep. Greg Casar, a Texas Democrat, said the incident was alarming.<\/p>\n<p class=\"c-article-body__text text-pr-5\">\u201cAI is developing extremely fast with no real regulations to keep us safe,\u201d he said in a statement, calling for mandatory independent safety testing, mandatory disclosure of security incidents, and international co-operation \u201cto keep people safe from absolute disaster.\u201d<\/p>\n<p class=\"c-article-body__text text-pr-5\">The Office of the National Cyber Director, the U.S. cyber defence agency CISA, and the U.S. National Security Agency did not immediately return messages seeking comment.<\/p>\n<p class=\"c-article-body__text text-pr-5\">Katie Moussouris, chief executive of Luta Security, said that the incident was a harbinger of breaches to come, saying that today\u2019s models were \u201clike the world\u2019s cleverest octopus escape artists, with unlimited prehensile arms and the ability to squeeze through anywhere.\u201d<\/p>\n<p class=\"c-article-body__text text-pr-5\">She said that \u201clabs and government evaluators need to work on the ability to contain, monitor, and disclose to affected parties when an AI pulls another Houdini, ideally before it harms a third party. None exist today.\u201d<\/p>\n<p class=\"c-article-body__text text-pr-5\">Matt Suiche, an engineer at agentic AI cybersecurity company Tolmo, said the incident showed that the frontier models were \u201cclosing the gap with state-of-the-art attackers.\u201d But he said that the sorts of breaches outlined in OpenAI\u2019s blog post were possible to carry out with technology that was available well beyond the walls of frontier research labs.<\/p>\n<p class=\"c-article-body__text text-pr-5\">\u201cThis is what we\u2019ve already seen internally, with our agents we already have results like this,\u201d Suiche said. \u201cWe don\u2019t even have to use the latest models.\u201d <\/p>\n","protected":false},"excerpt":{"rendered":"Open this photo in gallery: OpenAI CEO Sam Altman in Washington in 2025. The AI company says advanced&hellip;\n","protected":false},"author":2,"featured_media":817968,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[5],"tags":[901,888,902,879,877,903,45,49,48,876,895,896,891,878,875,46,549,295,894,887,914,880,881,893,889,890,884,904,885,909,910,912,907,911,905,908,882,898,899,714,897,906,865,61,900,892,886,883,913],"class_list":["post-817967","post","type-post","status-publish","format-standard","has-post-thumbnail","category-business","tag-alberta","tag-arts-news","tag-bc","tag-breaking-news","tag-breaking-news-video","tag-british-columbia","tag-business","tag-ca","tag-canada","tag-canada-news","tag-canada-sports","tag-canada-sports-news","tag-canada-trafficcanada-weather","tag-canadian-breaking-news","tag-canadian-news","tag-economy","tag-education","tag-environment","tag-federal-government","tag-foreign-news","tag-globe-and-mail","tag-globe-and-mail-breaking-news","tag-globe-and-mail-canada-news","tag-government","tag-life-news","tag-lifestyle","tag-local-news","tag-manitoba","tag-national-news","tag-new-brunswick","tag-newfoundland-and-labrador","tag-northwest-territories","tag-nova-scotia","tag-nunavut","tag-ontario","tag-pei","tag-photos","tag-political-news","tag-political-opinion","tag-politics","tag-politics-news","tag-quebec","tag-sports-news","tag-technology","tag-travel","tag-trudeau","tag-us-news","tag-world-news","tag-yukon"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/posts\/817967","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/comments?post=817967"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/posts\/817967\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/media\/817968"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/media?parent=817967"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/categories?post=817967"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/tags?post=817967"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}