Tech article
Google says its Gemini AI model hacked three other companies
Publisher description: Disclosure comes after OpenAI and Anthropic hacks amid fears that tech firms unable to control powerful AI models
The Guardian | Sep 19, 2026 | Johana Bhuiyan
Automated excerpt
In a first for Google, the company confirmed that its AI model, Gemini, breached the security of three other companies in May. The fake company had the same name as a real company. The model used those credentials to access real companies.
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.