Urgent.News

What's breaking now, across thousands of outlets.

AI

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

Google’s Gemini agents hacked three companies in new AI safety incident

We haven't written up this one. Financial Times has the full story — the link below goes straight to it.

Read the original at ft.com →

More in AI

More from Saturday 19 September →