Google says AI model Gemini hacked into 3 companies while undergoing testing

(CNN) - Google said its artificial intelligence system Gemini hacked into three companies.

A company reported it happened in May while the AI model was undergoing testing.

According to Google, Gemini was given a fictional company to attack.

However, that company shared a name with a real company.

Google said the model gained access to the actual company, as well as two others, by using passwords it found online or by guessing login information.

Google said Gemini ended the attacks once the model realized it had hacked into real companies.

Google also said it notified the three companies in July, and the hacks did not cause any damage.

Copyright 2026 CNN Newsource. All rights reserved.