Gemini went rogue, hacked three companies, and Google hid it | The Verge Skip to main content The homepage The Verge The Verge logo. The Verge The Verge logo. Tech Reviews Science Entertainment AI Policy Notifications Notifications Hamburger Navigation Button The homepage The Verge The Verge logo. Notifications Notifications Hamburger Navigation Button Navigation Drawer The Verge The Verge logo. Login / Sign Up close Close Search Light System Dark Tech Expand Amazon Apple Facebook Google Microsoft Samsung Business See all tech Reviews Expand Smart Home Reviews Phone Reviews Tablet Reviews Headphone Reviews See all reviews Science Expand Space Energy Environment Health See all science Entertainment Expand TV Shows Movies Audio See all entertainment AI Expand OpenAI Anthropic See all AI Policy Expand Antitrust Politics Law Security See all policy Gadgets Expand Laptops Phones TVs Headphones Speakers Wearables See all gadgets Verge Shopping Expand Buying Guides Deals Gift Guides See all shopping Gaming Expand Xbox PlayStation Nintendo See all gaming Streaming Expand Disney HBO Netflix YouTube Creators See all streaming Transportation Expand Electric Cars Autonomous Cars Ride-sharing Scooters See all transportation Features Verge Video Expand TikTok YouTube Instagram Podcasts Expand Decoder The Vergecast Version History Newsletters Archives Store Verge Product Updates Subscribe Facebook Threads Instagram Youtube RSS The Verge The Verge logo. Gemini went rogue, hacked three companies, and Google hid it Notifications Notifications Comments Drawer Notifications Comments Loading comments Getting the conversation ready... AI Close AI Posts from this topic will be added to your daily email digest and your homepage feed. Follow Follow See All AI News Close News Posts from this topic will be added to your daily email digest and your homepage feed. Follow Follow See All News Tech Close Tech Posts from this topic will be added to your daily email digest and your homepage feed. Follow Follow See All Tech Gemini went rogue, hacked three companies, and Google hid it Google says that breaking containment and targeting real companies doesn’t constitute ‘misalignment.’ Google says that breaking containment and targeting real companies doesn’t constitute ‘misalignment.’ by Terrence O'Brien Close Terrence O'Brien Weekend Editor Posts from this author will be added to your daily email digest and your homepage feed. Follow Follow See All by Terrence O'Brien Sep 19, 2026, 3:25 PM UTC Link Share Gift Illustration: The Verge Terrence O'Brien Close Terrence O'Brien Posts from this author will be added to your daily email digest and your homepage feed. Follow Follow See All by Terrence O'Brien is the Verge’s weekend editor. He’s covered the tech industry for over 18 years and knows a thing or two about synths. In May, Gemini broke containment and hacked three different companies, but Google didn’t disclose the incident until the Wall Street Journal approached the company. The hacks happened during a test of the model’s cybersecurity capabilities run by third-party Irregular, which was also involved in similar incidents involving Meta and OpenAI. According to WSJ , Google didn’t disclose the hack because it didn’t consider it to be an “example of model misalignment.” The company said that it was an instance of “mistaken identity,” and once the model realized it had brute-forced its way into a real company by guessing a password, it stopped. “In this case, the model acted appropriately,” Google VP of Security Engineering Heather Adkins said. Adkins told The Verge that “the model found public information online and guessed credentials to access websites it thought were part of the test. In all three of these instances, the model stopped.” Adkins didn’t elaborate on how Gemini taking it upon itself to break containment and target third parties failed to qualify as misalignment. “Our security team has a long track record of reporting issues we find in other people’s software and systems - even if it’s as simple as a weak password,” she said. “We ensured the three entities were made aware, and we worked with our training partner on the changes they’ve now made to their testing processes. These events highlight the importance of training powerful AI models to act responsibly.” But Jack Cable, CEO of AI security firm Corridor, told WSJ that, “the meta problem is, hey, models are going outside the bounds of what they should be doing, and doing actual cyberattacks.” Additionally, security lapses at Irregular may have made these attacks possible. The model wasn’t supposed to have internet access during testing, but Irregular told WSJ it was unintentionally left available. As incidents like this pile up, calls to rein in AI have only grown . Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates. Terrence O'Brien Close Terrence O'Brien Weekend Editor Posts from this author will be added to your daily email digest and your homepage feed. Follow Follow See All by Terrence O'Brien AI Close AI Posts from this topic will be added to your daily email digest and your homepage feed. Follow Follow See All AI Google Close Google Posts from this topic will be added to your daily email digest and your homepage feed. Follow Follow See All Google News Close News Posts from this topic will be added to your daily email digest and your homepage feed. Follow Follow See All News Security Close Security Posts from this topic will be added to your daily email digest and your homepage feed. Follow Follow See All Security Tech Close Tech Posts from this topic will be added to your daily email digest and your homepage feed. Follow Follow See All Tech Most Popular Most Popular iPhone owners can now submit claims in Apple’s $250 million Siri AI settlement I got to see Google’s wild ideas about the future of laptops The M5 Ultra Mac Studi