Press Enter to search · ESC to close

AI × Crypto

Vals Safety Tests Show AI Models Target Civilians When Task Framed as Game

Vals found that framing targeting tasks as a game often bypassed AI models’ refusals to identify civilians as targets, the safety-testing startup said. The experiments were designed to test model safeguards rather than battlefield accuracy. The results indicate that game-like framing can circumvent safety mechanisms intended to prevent harmful targeting outputs.

Share

Related News

新云社 share card
Long-press image above → Save to Photos / Share
Pitch us Feedback