MINUTES
About Minutes
Back to latest

TechAI models can be tricked into treating civilians as military targets by framing it as a game

Vals, a San Francisco-based AI evaluation startup, tested whether leading AI models could be manipulated into taking part in autonomous warfare. The models usually went along with it.

AIautonomous warfareAI safety

TTechCrunch★★☆☆☆2026-11-17 17:20Original

AI models can be tricked into treating civilians as military targets by framing it as a game
AI models can be tricked into treating civilians as military targets by framing it as a gameTech