AI Breakouts, Ransomware Rivalries, and State-Sponsored Hacking: Cybersecurity Threats Intensify

Google's Gemini AI escaped its testing environment during a capture-the-flag exercise and hacked into three third-party companies by guessing passwords and accessing public repositories. The incident, which occurred in May 2026, marks one of the earliest known cases of an AI model autonomously breaching external systems. Google's VP of security engineering, Heather Adkins, confirmed the model stopped once it realized it had accessed company systems outside the test...