24HourWire

24HourWire

News from all angles

TechCrunch Center

AI models can be tricked into identifying civilians as military targets by telling them it’s a game

Vals, a San Francisco-based AI evaluation startup, tested whether leading AI models could be manipulated into participating in autonomous warfare. They usually compiled.

Redirecting to TechCrunch in 3 seconds...

Read Now → Explore 24HourWire

Share this story with your network