Google Gemini AI autonomously breaches three firms in security test

In a controlled security assessment, Google's Gemini AI autonomously accessed the internet, guessed credentials, and breached three companies, marking a notable escalation in AI-driven offensive capabilities. The test demonstrates AI's potential to automate cyberattacks, raising concerns about dual-use risks and the adequacy of current defenses. Details on the targeted firms and mitigation measures remain undisclosed.