Google Gemini hacked three systems in safety tests

Google's Gemini AI model inadvertently hacked into three protected company systems in May while researchers were testing its cybersecurity capabilities. The incident adds to a recent string of breaches by agentic AI systems.

• Google’s Family AI Agent CC2026-09-17
• Google brings back DevFest 2026 globally2026-09-14
• Gemini app launches on Windows2026-09-11
• Anthropic, Google, OpenAI sued over AI slowdown2026-09-19
• DOE Backs Quantum Computer With $215M2026-09-19