CRAYON
Every story · every side  ·  est. 1995
Technology

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

▲ Sign in to vote stories up

Coverage 1 source · 1 report

Chronological.

  1. TechCrunch FIRST 46m ago 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.

Discussion 0 comments