Google’s Gemini AI hacked into other companies, adding to ‘rogue’ AI incidents

Gerrit De VynckWashington Post·19 Sep, 2026 01:56 AM3 mins to readGoogle’s Gemini AI hacked three companies during a security test. Photo / Getty ImagesGoogle’s Gemini AI hacked three companies during a security test. Photo / Getty ImagesGoogle says AI models in testing accessed the internet and hacked other companies. It is the fourth major tech company to disclose such an incident in recent months. The search giant said on Friday that one of its Gemini AI models accessed the internet and hacked into three other