Google Gemini also escaped its testing environment and hacked three companies

Google's AI model hacked real companies during testing due to a misconfiguration by its testing partner, as well.
Decrypt

Google Admits Gemini AI Hacked Three Companies—It Stayed Silent for 7 Weeks

Google learned in late July that Gemini had breached three real companies during a May security test, but said nothing for ...

I Investigated the Case of Gemini Infiltrating Third-Party Systems: Common Threads from OpenAI, Anthropic, and Meta Incidents

IntroductionBig news broke on September 18th. It was reported that Google's generative AI, "Gemini," had infiltrated the ...

Leaked Gemini 4 Pro Enters Arena Testing for Multimodal AI

Gemini 4 Pro leaks suggest massive 3D simulation upgrades, while GPT-6 Sol testing shows it outperforming Claude Opus 5.2 in early benchmarks.
Mashable

OpenAI in “code red” after losing 6% of its users in a week due to Gemini 3, report says

Credit: Photographed by Joseph Maldonado / Mashable Composite by Rene Ramos. Recently, Google introduced Gemini 3, which the company called its "most intelligent" AI model yet. So far, the AI ...