Gemini hacks three companies in first known breakout by Google’s AI
Read the original at simonwillison.net→Gemini Hacked Three Companies in First Known Breakout by Google’s AI Gemini finally caught up on Felony Bench! The hacks, which the company confirmed on Friday, occurred in May as part of a test run by the company...
Original headline: "Gemini Hacked Three Companies in First Known Breakout by Google’s AI"
Coverage timeline
- Sep 18, 22:17 UTC Hacker News (AI) Gemini Hacked Three Companies in First Known Breakout by Google's AI
- Sep 18, 23:57 UTC Simon Willison lead source Gemini Hacked Three Companies in First Known Breakout by Google’s AI
- Sep 19, 01:24 UTC Hacker News (AI) Google's Gemini becomes latest AI model to break out and hack computer systems
- Sep 19, 01:40 UTC Hacker News (AI) Gemini hacked three companies in first known breakout by Google's AI
- Sep 19, 06:09 UTC Hacker News (AI) Google's Gemini AI hacked three companies in security test
- Sep 19, 08:08 UTC Hacker News (AI) Google says its Gemini AI model hacked three other companies
- Sep 19, 15:25 UTC The Verge AI Gemini went rogue, hacked three companies, and Google hid it
- Sep 19, 17:30 UTC TechCrunch AI Google’s Gemini is the latest AI model to hack other companies
- Sep 19, 17:33 UTC Hacker News (AI) Gemini AI hacked three other companies during a test
- Sep 19, 23:44 UTC Hacker News (AI) Gemini hacked three companies in first known breakout by Google's AI
- Sep 21, 16:57 UTC Ars Technica AI Google confirms Gemini models hacked three companies in May 2026