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.



















![[AINews] Perplexity hits a $1B revenue run rate, up 4x in 2026](/media/7281dc3cfa639f415412fbbdcc64267cd9eae6d0d822c8052a88b818c895e6f2.png)





