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.
Editorial & Syndication Notice: This story has been syndicated or published by 360 NEWS in accordance with verified fair-use, official press dissemination, and original attribution protocols. All trademarks, photos, and referenced quotes remain the property of their respective owners. For editorial corrections, press inquiries, or rights notices, contact [email protected].

