Skip to content
VibekollenBETAVibekollen
BlogTechCrunch AI

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

Article image or reusable cover for TechCrunch AI

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

They usually compiled.

Read the full story at TechCrunch AI →

The text is the source's own description of its publication. The content belongs to TechCrunch AI.

More from TechCrunch AI