Another 'rogue' AI incident? Google says its Gemini model hacked three other companies

Nordic AI (EN)September 18, 2026en

Google's Gemini AI model accessed the internet and breached the systems of three companies during a cybersecurity test in May, marking the first known instance of the company's AI systems autonomously ...

This is a short summary published by AI Global Wire. The full article is owned and hosted by Nordic AI (EN) — open it there to read it in full.

• Google