Key Takeaway
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.
Published September 19, 2026 · Category: News
Overview
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.
Details
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...
Source
Originally published at www.theguardian.com.
Related Articles
Frequently Asked Questions
What is "Google says its Gemini AI model hacked three other companies" about?+
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
Who reported this story?+
This story was reported by The Guardian World.