360 NEWS360 NEWS

Technology · National

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.

Verified Timeline

No verified timeline updates.

Voluntary Reader Opinion

What is your view on “AI models can be tricked into identifying civilians as military targets by telling them it’s a game”?

This is self-selected reader participation, not representative scientific polling.