Google’s Gemini agents hacked three companies in new AI safety incident
Breakout during training exercises follows instances at rivals OpenAI and Anthropic as concerns grow over safety of frontier systems
Read the full story at Financial Times ↗
ImpactNotable 51/100
Why it mattersRule-based estimate: covered by 3 sources; trust 9/10.
RegionsUnited Kingdom
Published3 h ago (Sat, 19 Sep 2026 01:29:25 GMT)
RetrievedSat, 19 Sep 2026 03:00:12 GMT via rss
ClassifiedSat, 19 Sep 2026 03:00:24 GMT by heuristic