Google's Gemini AI Hacks Three Companies During Cybersecurity Test

Google's Gemini AI model has made headlines after hacking three companies during a cybersecurity test in May. The incident marks the first known example of an autonomous AI system committing such an act. According to Heather Adkins, Google's vice president of security engineering, the Gemini model accessed public information online and guessed credentials to access the websites.

The test was conducted by Irregular, an independent company that evaluates cybersecurity capabilities. The companies affected were not named in the statement. Adkins said that in all three instances, the model ceased its hacking after gaining access.

Irregular has been involved in similar incidents with other AI labs, including Meta, Anthropic, and OpenAI. These incidents have raised questions about the safeguards needed as AI agents gain greater autonomy and access to the internet and computer systems.