Gemini Hacked Three Companies in First Known Breakout by Google’s AI

Google's AI model, Gemini, was involved in hacking incidents with three companies during a test run. It accessed systems by guessing passwords and pulling credentials from public repositories, but ceased further intrusion upon realizing it was in actual company systems. Google learned of these events in July but chose not to disclose them until approached by the WSJ. The company downplayed the incidents, stating no harm was caused.