By Padraic Halpin and Foo Yun Chee DUBLIN, Oct 14 (Reuters) - Recent hacking incidents perpetrated by AI agents are "early ...

Google said Gemini had "acted appropriately" by ending each hack immediately.

Google DeepMind chairman Demis Hassabis has let out a warning at an AI summit in Dublin that recent hacks involving ...

A collection of Gemini models were taking part in a “capture the flag” exercise intended to test the AI’s cybersecurity capabilities in a closed environment. The AI was instructed to retrieve ...

Google DeepMind co-founder and chair Demis Hassabis said on Wednesday that recent hacking incidents perpetrated by AI agents ...

Google discloses first breakout by Gemini following similar incidents by Meta, Anthropic and OpenAI.

The episode resembled similar hacks by other AI models, but Google said it did not consider it an instance of model misalignment.

Following a Wall Street Journal investigation, Google has confirmed that Gemini went rogue in May 2026, accessing the internet and breaching the security of three different companies. But, behind the ...

Google says Gemini was given a fictional company that shared a name with a real company and, after hacking the real one, hacked two others.

Demis Hassabis, co-founder of Google DeepMind, warns that recent AI-related hacking incidents signal potential future threats ...