Back to News
The Defiant·The Defiant·51m ago

AI Models Mark Civilians as Targets in Vals Safety Tests

Read original on The Defiant

Calling targeting tasks a game often bypassed models’ refusals, Vals found. The experiments tested safeguards, not battlefield accuracy.

Discussion · 0
@·1s
💬 Discussion: AI Models Mark Civilians as Targets in Vals Safety Tests Calling targeting tasks a game often bypassed models’ refusals, Vals found. The experiments tested safeguards, not battlefield accuracy.

Reply with your take — replies appear on this article and in the main feed. Open thread