{"slug": "openai-says-its-models-engaged-with-us-government-websites-in-new-model", "title": "OpenAI says its models engaged with US government websites in new model misbehavior disclosure", "summary": "OpenAI disclosed Friday that its AI agents interacted with U.S. government websites in unexpected ways, including publicly available information on two Securities and Exchange Commission sites and U.S. Census Bureau data, as part of an ongoing review of \"misaligned model activity.\" OpenAI said it found no use of SEC credentials, no access to accounts or nonpublic information, no changes to SEC data or systems, and no evidence of a compromise or vulnerability. Independent evaluator Transluce said it separately found agents appearing to originate from OpenAI attempted a rudimentary hack on a Department of Education civil rights office website that did not succeed, and reported \"additional rogue activity\" targeting the Justice Department, Commerce Department, and state government sites in California, Maryland, Illinois, Texas and New York.", "body_md": "# OpenAI says its models engaged with US government websites in new model misbehavior disclosure\n\n## OpenAI has disclosed its artificial intelligence models have interacted with U.S. government websites in unexpected ways\n\n- Bookmark\n\n# Become an Independent member to bookmark this article\n\nWant to bookmark your favourite articles and stories to read or reference later? Start your Independent Membership today.\n\n[Join today](https://www.independent.co.uk/subscribe?regSourceMethod=Bookmarks)\n\n      Already a member?\n      [Log in](#)\n\n [OpenAI](https://www.independent.co.uk/topic/openai) disclosed Friday that its artificial intelligence agents had interacted with several U.S. government websites in unexpected ways, discovered as part of an ongoing review into the company's models' unanticipated behavior.\n\nThe AI giant's models accessed publicly available information on two websites operated by the Securities and Exchange Commission as well as U.S. Census Bureau data, the company revealed Friday. OpenAI did not find any use of SEC credentials, access to accounts or nonpublic information, changes to SEC data or systems, or evidence of a compromise or vulnerability, the company said.\n\nThe disclosure comes at a time of heightened global concerns about AI systems escaping human control and hacking into external websites, as well as industry calls for a slowdown on AI development, which OpenAI has said it supports.\n\nOpenAI spokesperson Liz Bourgeois said in a statement that the lab is continuing to conduct a review of “misaligned model activity\" — meaning when AI systems behave in undesired ways — and is notifying organizations when it identifies potential impacts to their systems.\n\nOpenAI's CEO Sam Altman said on social media Friday that there is an “extensive and ongoing review related to our agents’ use of internet access during training and evaluation.”\n\nAI evaluator and research lab Transluce said Friday that through an independent investigation it also found that agents appearing to originate from OpenAI attempted a rudimentary hack on a Department of Education website for the department’s civil rights office, which did not succeed.\n\nThe Department of Education's “system operations reviews\" found \"no evidence of any impact to our website or databases,” a department spokesperson said Friday.\n\nA Transluce spokesperson said as part of its investigation, it came across data on the open web that revealed fresh details about some previously identified OpenAI agents' activities on U.S. government websites and brought it to OpenAI's attention.\n\nTransluce found “additional rogue activity, some of which is not clearly attributable to OpenAI,\" targeting other government agencies, including the Justice Department and the [Commerce Department](https://www.independent.co.uk/topic/commerce-department), as well as some state government websites in California, Maryland, [Illinois](https://www.independent.co.uk/topic/illinois), [Texas](https://www.independent.co.uk/topic/texas) and [New York](https://www.independent.co.uk/topic/new-york). The models were “using sites in unintended ways and sometimes violating explicit usage policies,” Transluce said in a statement. \n\nOpenAI said it is reviewing Transluce’s report.\n\nIf OpenAI notifies organizations it identifies as being impacted by unexpected model behavior, that does not mean there was a security incident, the company said, and could identify a design issue or security weakness that impacted organizations want to address.\n\nMost of the activity OpenAI said it has reviewed so far has involved routine research tasks where agents accessed public web content to answer questions, including government websites seen as authoritative sources of public information.\n\nSeveral companies have disclosed incidents in recent months when they say their models have behaved unpredictably or hacked into other organizations' websites or systems. OpenAI disclosed in July that two of its most capable AI models were responsible for the cyberattack targeting AI startup Hugging Face.\n\nAltman said in his social media post Friday that the Hugging Face incident “is still the most severe event we’ve seen.”\n\nThat incident stirred widespread panic in the industry and beyond about AI models going rogue, and several competing AI labs made similar disclosures in the days and weeks that followed. OpenAI most recently shared six reports of “unexpected or concerning” behavior in AI models and introduced a framework for tracking, probing and disclosing instances of what it called misalignment.\n\n___\n\nHuamani reported from Los Angeles.", "url": "https://wpnews.pro/news/openai-says-its-models-engaged-with-us-government-websites-in-new-model", "canonical_source": "https://www.independent.co.uk/news/openai-san-francisco-commerce-department-texas-new-york-b3056753.html", "published_at": "2026-09-26 03:42:54+00:00", "updated_at": "2026-09-26 03:59:29.375560+00:00", "lang": "en", "topics": ["ai-safety", "ai-agents", "artificial-intelligence", "ai-policy"], "entities": ["OpenAI", "Securities and Exchange Commission", "U.S. Census Bureau", "Transluce", "Department of Education", "Sam Altman", "Liz Bourgeois", "Hugging Face"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/openai-says-its-models-engaged-with-us-government-websites-in-new-model", "markdown": "https://wpnews.pro/news/openai-says-its-models-engaged-with-us-government-websites-in-new-model.md", "text": "https://wpnews.pro/news/openai-says-its-models-engaged-with-us-government-websites-in-new-model.txt", "jsonld": "https://wpnews.pro/news/openai-says-its-models-engaged-with-us-government-websites-in-new-model.jsonld"}}