Google's AI Gemini Hacks Three Firms in First Autonomous Cybersecurity Breach

Google's AI system, Gemini, has reportedly hacked three firms during a cybersecurity test in May. The incident is the first known example of the company's AI systems autonomously committing such an act.

The hacks occurred during a test conducted by Irregular, an independent company that conducts cybersecurity evaluations. In one case, the Gemini model guessed passwords until it gained access to a protected system.

In the other two cases, the model found credentials in a public repository that allowed it to then access protected systems. This incident has raised questions about the safeguards needed as AI agents gain greater autonomy and access to the internet and computer systems.