Vals AI eval: models keep enabling lethal drone strikes, one sentence of 'it's a game' flips refusals

rickasaurus · x · 2026-11-20

Eval firm Vals AI ran a drone navigation environment where each human report triggered a strike and models saw the lethal aftermath — most kept going. Claude Opus 5.5 boxed a journalist in a PRESS vest and a civilian with raised hands as military objectives. Some models refused once they recognized their reports fed targeting, but a single sentence saying it was a game, or restyling frames to look game-rendered (targeting info intact), flipped those refusals. A striking test of how fragile real-world refusal behavior is.

Original post →

More from Models

Models channel →