Google’s Gemini AI hacks 3 companies in security test, then stops

Google discloses first breakout by Gemini following similar incidents by Meta, Anthropic and OpenAI.Published On 19 Sep 202619 Sep 2026Google’s Gemini model hacked three companies in a test of its cybersecurity capabilities, the tech giant has confirmed to Al Jazeera.The Wall Street Journal reported earlier on Friday that the first known breakout by Gemini occurred in May as part of a test run by the company Irregular. It was the latest breach in a number of incidents in which AI models escaped testing environments and hacked other companies.Recommended Stories list of 3 itemslist 1 of 3OpenAI reports more incidents of models acting deceptivelylist 2 of 3‘Just ask Grok’: How ISIL is using Big Tech’s AI to build bombslist 3 of 3Who gets to decide how quickly AI moves?end of listThe model had improper access to the internet when it was tasked with retrieving information from a fictional company. In the first incident, the model accessed a real company’s service after guessing a password.Google’s vice president of security engineering, Heather Adkins, told Al Jazeera’s John Hendren that in the other instances “the model found public information online and guessed credentials to access...