Google’s Gemini agents hacked three companies in new AI safety incident
Direct Source Verification:
This story is aggregated from Financial Times (ft.com). Full reporting rights and copyright belong to the primary publisher.
Breakout during training exercises follows instances at rivals OpenAI and Anthropic as concerns grow over safety of frontier systems
For complete coverage, context, and related multimedia, visit the original reporting by Financial Times via the source link below.
Original Source
https://www.ft.com/content/158740d1-fde7-4dbc-a282-5830c3201189?syn-25a6b1a6=1
