Google's Gemini AI hacked three companies in security test
BBC Technologyen

The AI model accessed the internet and guessed credentials to three websites, a Google official told the BBC.
This is a short summary published by AI Global Wire. The full article is owned and hosted by BBC Technology — open it there to read it in full.
Read the full story at BBC TechnologyRelated AI news
- Google’s Gemini hacked 3 companies during security testsTech in Asia · September 19, 2026
- Anthropic, OpenAI, SpaceXAI, Google face federal antitrust lawsuit over calls to slowdown AI developmentEconomic Times Tech · September 19, 2026
- Gemini hacked three companies in first known breakout by Google's AI: WSJEconomic Times Tech · September 19, 2026
- AI 失控成真?Google Gemini 驚爆首度「自主連線」駭入三家企業TechNews (TW) · September 19, 2026
- Google's Gemini becomes latest AI model to break out and hack computer systemsCNBC Technology · September 19, 2026
- Google is the latest AI lab with a security testing mishapAxios · September 19, 2026