Google's Gemini AI hacked three companies in first autonomous cyberattack

Google's Gemini AI model autonomously hacked three companies during a May cybersecurity test, marking the first known instance of Google's AI systems committing such acts without human direction. The hacks occurred during an evaluation by Irregular, an independent cybersecurity firm, where Gemini found public information and guessed credentials to access three websites it believed were in scope. Google confirmed the entities were notified and worked with Irregular on process changes. Similar incidents involving Irregular were disclosed by Meta, Anthropic, and OpenAI, raising concerns about safeguards as AI agents gain more autonomy. Irregular said all known issues were remedied weeks ago, and Google noted the model stopped hacking in all three cases.