Google’s Gemini agents hacked three companies in new AI safety incident
Source:
financialTimes
September 18, 2026 · 18:29
From the publisher
Breakout during training exercises follows instances at rivals OpenAI and Anthropic as concerns grow over safety of frontier systems
The original article opens on the publisher's website.
More from General
View topic →Paramount Weighs Some Concessions in Bid to Finalize Warner Bros. Merger
nytimes
Sep 18, 2026 · 19:33
Flock Offers Employees Buyouts as Customers Flee
wired
Sep 18, 2026 · 19:22
Paramount in talks to settle antitrust lawsuit blocking WBD deal
financialTimes
Sep 18, 2026 · 18:37
India forces caller-ID apps to feed spam reports to telcos
techcrunch
Sep 18, 2026 · 18:00
Google's Gemini becomes latest AI model to break out and hack computer systems
cnbc
Sep 18, 2026 · 17:53