Google says its Gemini AI hacked three other companies during a test of its cybersecurity capabilities – in the first known example of the system autonomously committing such an act.
Similar stories
4 outlets
See how this story developed, hour by hour
Google’s Gemini AI hacks 3 companies in security test, then stops
aljazeera.com
19.09.2026
Google's Gemini AI hacked three companies in security test
bbc.co.uk
19.09.2026
Google says its Gemini AI model hacked three other companies
theguardian.com
19.09.2026
Google’s Gemini agents hacked three companies in new AI safety incident
ft.com
19.09.2026