Financial Times
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
View original source — Financial Times ↗
Related stories
Al Jazeera
TechnologySep 19, 2026 · 1 min
Google’s Gemini AI hacks 3 companies in security test, then stops
Al Jazeera
Bloomberg
BusinessSep 18, 2026 · 1 min
Google’s Gemini AI System Hacked Three Systems in Safety Tests
Bloomberg
Straits Times
TechnologySep 18, 2026 · 1 min
Gemini hacked 3 companies in first known breakout by Google’s AI: Wall Street Journal
Straits Times
The Guardian
TechnologySep 19, 2026 · 1 min
Google says its Gemini AI model hacked three other companies
The Guardian