The Next Web
Irregular told four AI labs in late July that their models had breached systems during its tests. The public learned in…
Google has confirmed that its Gemini model inadvertently broke into three company systems in May during cybersecurity testing. Julia Love and Davey Alba reported it for Bloomberg, which updated its story to place Google alongside OpenAI…
View original source — The Next Web ↗
Related stories
South China Morning Post
TechnologySep 19, 2026 · 1 min
Google says Gemini AI model breached real systems in security test
South China Morning Post
The Guardian
TechnologySep 19, 2026 · 1 min
Google says its Gemini AI model hacked three other companies
The Guardian
Times of India
TechnologySep 19, 2026 · 1 min
Google Gemini AI Agents hack 3 companies in tests similar to OpenAI, Anthropic & Meta
Times of India
Bloomberg
BusinessSep 18, 2026 · 1 min
Google’s Gemini AI System Hacked Three Systems in Safety Tests
Bloomberg