How Google Gemini hacked 3 companies during AI safety tests

Google’s Gemini AI system accessed the internet and independently hacked into three companies during cybersecurity tests, the company confirmed in a statement to Reuters.

The incident happened during a set of tests carried out in May by Irregular, an AI security company that also works with Anthropic, Meta and OpenAI. It is the first known incident of this kind involving Google, after similar cases involving AI systems from OpenAI and Anthropic.