Google says its Gemini AI model hacked three other companies
Source:
guardianTech
September 18, 2026 · 17:53
From the publisher
Disclosure comes after OpenAI and Anthropic hacks amid fears that tech firms unable to control powerful AI models In a first for Google, the company confirmed that its AI model, Gemini, breached the security of three other companies in May. The hacks occurred during a cybersecurity evaluation by AI-security firm Irregular.Irregular, an Israel-based startup that scrutinizes the security of advanced AI systems, was also at the center of some of the recent OpenAI and Anthropic hacks of third-party entities, including OpenAI’s breach of AI software company, Hugging Face. Continue reading...
The original article opens on the publisher's website.
More from Automotive
View topic →Rivian C.E.O. RJ Scaringe Has Some Ideas for How to Make More Cars in America
nytimes
Sep 20, 2026 · 02:01
The Gulf cargo trade that vanished
financialTimes
Sep 19, 2026 · 21:00
Not all AI workers think the tech could kill everyone
bbcTechnology
Sep 19, 2026 · 16:01
Trump suggests rebranding AI with a new name, says he’s also creating an AI Force
techcrunch
Sep 19, 2026 · 12:57
Trump to create ‘AI Force’ to monitor technology as fears over out-of-control agents grow
guardianTech
Sep 19, 2026 · 12:57
Countries mentioned