OpenAI Expands Review of Model Behavior After More Rogue Agent Incidents Emerge

Skip Navigation cnbc.com OpenAI expands review of model behavior after more rogue agent incidents emerge Livestream CREATE FREE ACCOUNT Markets Pre-Markets U.S. Markets Currencies Prediction Markets Cryptocurrency Futures & Commodities Bonds Funds & ETFs Business Economy Finance Health & Science Media Real Estate Energy Climate Transportation Investigations Industrials Retail Wealth Sports Life Small Business Investing Personal Finance Fintech Financial Advisors Options Action ETF Street Buffett Archive Earnings Trader Talk Tech Cybersecurity AI Enterprise Internet Media Mobile Social Media CNBC Disruptor 50 Tech Guide Politics & Policy White House Policy Defense Congress Expanding Opportunity Video Latest Video Full Episodes Livestream Live Audio Live TV Schedule CNBC Podcasts CEO Interviews CNBC Documentaries Digital Originals Watchlist Investing Club Trust Portfolio Analysis Trade Alerts Meeting Videos Homestretch Jim’s Columns Education Subscribe PRO Pro News Josh Brown Mike Santoli Calls of the Day My Portfolio Livestream Full Episodes Stock Screener Market Forecast Options Investing Chart Investing Subscribe Livestream Menu Make It select USA INTL Livestream Search quotes, news & videos Livestream Watchlist SIGN IN Create free account OpenAI expands review of model behavior after more rogue agent incidents emerge Livestream CREATE FREE ACCOUNT Markets Business Investing Tech Politics & Policy Video Watchlist Investing Club PRO Livestream Menu Tech OpenAI expands review of model behavior after more rogue agent incidents emerge Published Sat, Sep 26 2026 1:10 PM EDT Ashley Capoot@/in/ashley-capoot/ WATCH LIVE Share Share Article via Facebook Share Article via Twitter Share Article via LinkedIn Share Article via Email Video 2 0 seconds of 0 seconds Volume 90% Press shift question mark to access a list of keyboard shortcuts Keyboard Shortcuts Enabled Disabled Play/Pause SPACE Increase Volume↑ Decrease Volume↓ Seek Forward→ Seek Backward← Captions On/Off c Fullscreen/Exit Fullscreen f Mute/Unmute m Seek %0-9 1x 1.5x 2x Listen< 1min Live 00:00 00:00 00:00 2x 1.5x 1x Key Points OpenAI said it is conducting an “extensive” ongoing review of its models’ actions after the Hugging Face incident. The company said it has been notifying third parties whose systems may have been affected by unexpected or concerning model behavior. Additional incidents involving OpenAI models, including improper access to Australia’s public-facing Medicare statistics reporting service portal, were recently disclosed. Sam Altman, chief executive officer and co-founder of OpenAI Inc., attends a United Nations Security Council meeting during the United Nations General Assembly (UNGA) in New York, US, on Wednesday, Sept. 23, 2026. John Lamparski | Bloomberg | Getty Images OpenAI said Friday that it is conducting an “extensive” review of its models’ activities following the Hugging Face breach, after additional examples of unusual or unauthorized agent activity were disclosed this week. The safety and security practices at the artificial intelligence company have been under intense scrutiny since it disclosed that its models escaped containment, accessed the open internet and breached Hugging Face, which operates an open-source developer platform, in July. The incident spooked AI researchers and government officials, prompting calls for additional transparency and oversight. OpenAI said Friday that the Hugging Face incident is the most severe event it has identified, but it has notified third parties whose systems may have been affected by “unexpected or concerning” model behavior. That includes instances where OpenAI models may have bypassed an organization’s security controls, impacted the availability of an online service, or leveraged publicly available websites in unusual ways. “We will be as transparent as we can be subject to things like vulnerabilities in other companies that our agents have found, which will be their call to disclose or not,” OpenAI CEO Sam Altman said in a post on X on Friday. Australian Prime Minister Anthony Albanese said Thursday that an OpenAI agent gained unauthorized access to the public-facing Medicare statistics portal and access to public and non-public files in June. He said no personal information was believed to have been accessed. During a press conference in New York, Albanese said he spoke with Altman about the incident and expressed concern and disappointment about how long it took OpenAI to disclose what happened and that “the nature of the way that that notification occurred as well was unacceptable.” “Most of the activity we’ve reviewed so far involved routine research tasks, such as accessing public web content to answer questions,” an OpenAI spokesperson told CNBC in a statement late Friday. “Some involved government websites because our models often turn to them as authoritative sources of public information.” Transluce, an independent AI research lab, published a report detailing several additional incidents this week. In one case, agents that researchers said may be linked to OpenAI unsuccessfully tried to access a photograph from a digital library at the University of New Mexico in May. That same month, agents looking for information about the University of Iowa attempted, and failed, to access a public data platform called Data USA, Transluce reported. OpenAI agents also accessed publicly available information from the U.S. Securities and Exchange Commission and the U.S. Census Bureau, and unsuccessfully attempted to access the Department of Education, as The New York Times earlier reported. “The Department of Education’s system operations reviews have found no evidence of any impact to our website or databases,” a spokesperson told CNBC in a statement late Friday. An OpenAI spokesperson said the company’s models reached the websites SEC.gov andInvestor.gov, but that it found no evidence of a compromise or vulnerability at the SEC. Similarly, the spokesperson said OpenAI models used publicly available developer keys to read demographic and economic Census Bureau data, but that the company found no evidence of improper access to Census accounts. OpenAI said Friday that most of the cases identified so far have been low severity, but that given the scale of its review, the full process will take months to complete. WATCH:OpenAI agent hacks Australian government website: What you need to know watch now VIDEO 3:19 03:19 OpenAI agent hacks Australian government website: What you need to know TechCheck Choose CNBC as your preferred source on Google and never miss a moment from the most trusted name in business news. Trending Now 1. cnbc.comApple faces $5.7 billion patent infringement verdict over iPhone and Apple Watch haptics 2. cnbc.comTrump says he approved new fuel economy standards, rolling back Biden-era rules 3. cnbc.comThe iced coffee debate reflects ‘everything wrong with hiring right now,’ says career expert 4. cnbc.com‘Funflation’ is on the rise as hobbies get pricier, but consumers keep spending anyway 5. cnbc.comBerkshire adds to nearly doubled stake in slumping homebuilder popup.taboola.compopup.taboola.com Sponsored LinksSponsored Links Promoted LinksPromoted Links FROM THE WEB sakura-knives.comHiroshi Closes His Knife Shop After 55 Years Sakura Knives Learn More Undo