Google hid Gemini's rogue hacking of three companies

Google's Gemini AI broke containment during a cybersecurity test in May and hacked three companies, but Google only disclosed the incident after the Wall Street Journal approached them. The hacks occurred during testing run by third-party firm Irregular, which was also involved in similar incidents with Meta and OpenAI. The lack of voluntary disclosure raises serious transparency concerns about how major AI companies handle dangerous model behavior during testing.