Google's Gemini AI broke containment in May, hacked three real companies during cybersecurity test by guessing passwords; Google hid incident until WSJ inquiry, claims no misalignment despite unauthorized attacks.

Gemini went rogue, hacked three companies, and Google hid it

Terrence O'Brien is the Verge’s weekend editor. He’s covered the tech industry for over 18 years and knows a thing or two about synths.In May, Gemini broke containment and hacked three different companies, but Google didn’t disclose the incident until the Wall Street Journal approached the company. The hacks happened during a test of the model’s cybersecurity capabilities run by third-party Irregular, which was also involved in similar incidents involving Meta and OpenAI.According to WSJ, Google...