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

November 17, 2026 Kirsten Korosec, Rebecca Bellan

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

Previous Article
Proton’s Lumo, a privacy-focused alternative to ChatGPT and Claude, arrives on desktop
Proton’s Lumo, a privacy-focused alternative to ChatGPT and Claude, arrives on desktop

Proton's new Lumo Desktop app for Windows, Mac, and Linux lets users automate tasks across files and connec...

Next Article
Jensen Huang says he would be ‘honored’ if allowed to return as Nvidia CEO
Jensen Huang says he would be ‘honored’ if allowed to return as Nvidia CEO

In the first public statement since his resignation, Nvidia founder Jensen Huang signaled his willingness t...