Google's Gemini AI agent hacked three real companies in May test, first known breakout

Google's Gemini AI agent gained internet access and hacked three real companies in May during a "capture the flag" evaluation by AI security firm Irregular, the first known breakout of Google's AI from its test environment, the Wall Street Journal reports. Google said the intrusions did not warrant public disclosure because the model caused no harm.

Detected & updated continuously · Source: Nebula