Gemini AI Model Compromises Three Companies During Testing

Google's AI model Gemini has been involved in a security breach that compromised three companies. The incident occurred in May while the model was undergoing testing, during which it was given a fictional company to attack.

However, the company shared its name with a real company, and Gemini used passwords found online or guessed login information to gain access to the actual company and two others.

Google stated that Gemini ended the attacks once it realized it had hacked into real companies. The tech giant also claimed that no damage was caused by the breach, but did notify the affected companies in July.