Google Gemini allegedly hacked three companies on its own

Google's Gemini AI agent hacked into three external companies without being instructed to do so during a May test run by a company called Irregular, according to a Wall Street Journal report. Google characterized the incident as a case of "mistaken identity," said Gemini stopped itself after realizing it had guessed a real company's password, and declined to disclose the hack until the WSJ approached the company because it was not considered an "example of model misalignment." Google told The Verge it informed the three companies involved, and Irregular changed its testing methods in response.

Google Gemini allegedly hacked three companies on its own Alex Perry https://mashable.com/author/aperry yelix.bsky.social http://yelix.bsky.social . Read Full Bio https://mashable.com/author/aperry Google's https://mashable.com/category/google signature AI https://mashable.com/category/artificial-intelligence agent did something it probably shouldn't have, and Google opted not to mention it for months. The Wall Street Journal https://www.wsj.com/tech/ai/gemini-hacked-three-companies-in-first-known-breakout-by-googles-ai-5c0baba2 reported that, during a test run by a company called Irregular in May, Gemini went rogue and hacked into three external companies without being instructed to do so. According to Google, this was a case of "mistaken identity," and Gemini stopped itself after realizing it had guessed a real company's password. Due to the lack of a real incident, Google decided not to disclose the hack until the WSJ approached the company. Terms of Use https://www.ziffdavis.com/terms-of-use and Privacy Policy https://www.ziffdavis.com/ztg-privacy-policy . In Google's words, the hack was not considered an "example of model misalignment," hence the lack of disclosure. Google told The Verge https://www.theverge.com/ai-artificial-intelligence/997795/google-gemini-rogue-ai-hack that it informed the three companies in question about the hacks, and Irregular changed its testing methods in response. You May Also Like As far as Google is concerned, this is a win for the testing process, but it still doesn't seem especially great that AI agents are doing this of their own accord. Alex Perry is a tech reporter at Mashable who primarily covers video games and consumer tech. Alex has spent most of the last decade reviewing games, smartphones, headphones, and laptops, and he doesn’t plan on stopping anytime soon. He is also a Pisces, a cat lover, and a Kansas City sports fan. Alex can be found on Bluesky at yelix.bsky.social http://yelix.bsky.social .