Google’s Gemini is the latest AI model to hack other companies
Google said Gemini had "acted appropriately" by ending each hack immediately.
Read at TechCrunch · 19 September 2026 at 17:30
All coverage of this event, automatically grouped from multiple independent sources.
Last updated: 19 September 2026 at 20:50 · 7 articles · 6 sources
Google said Gemini had "acted appropriately" by ending each hack immediately.
Read at TechCrunch · 19 September 2026 at 17:30
In May, Gemini broke containment and hacked three different companies, but Google didn't disclose the incident until the Wall Street Journal approached the company. The hacks happened during a test of
Read at The Verge · 19 September 2026 at 15:25
The AI model accessed the internet and guessed credentials to three websites, a Google official told the BBC.
Read at BBC · 19 September 2026 at 13:39
Gemini, het AI-model van Google, is tijdens een test online gegaan en heeft vervolgens autonoom drie bedrijven gehackt. Het is het eerste bekende geval van Gemini, na soortgelijke incidenten met model
Read at NU.nl · 19 September 2026 at 06:26
Gemini, het AI-model van Google, is tijdens een test zelfstandig het internet opgegaan en heeft vervolgens autonoom drie bedrijven gehackt. Het is het eerste bekende geval waarbij Gemini tijdens een t
Read at NU.nl · 19 September 2026 at 06:26
The disclosure comes as scrutiny over misbehaving artificial intelligence intensifies in Washington and Silicon Valley.
Read at CNBC · 19 September 2026 at 01:41
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 s
Read at The Guardian · 19 September 2026 at 00:53