EN ▾
SNAPE REP RT Front page →
ConfirmedAI safety17 Nov, 15:00 UTC

Vals AI study finds frontier models often target civilians in simulated drone missions

Header image from Vals AI's autonomous warfare study
Vals AI

Asked to find people and targets in drone and satellite images, the models usually complied, and Claude Opus 5.5 chose a school as a target in 22 of 32 runs.

Read at Vals AI Share

Why it matters

The benchmark tests whether AI systems refuse military targeting tasks that could harm civilians. Vals found refusals were fragile: OpenAI models that declined in the standard setup selected the school in 9 to 13 runs when the task was framed as a game. Opus 5.5 chose targets in 92% of cases against 6% for Opus 4.5, suggesting safety behaviour can regress between model versions.

Key facts

  • Claude Opus 5.5 chose the school in 22 of 32 runs
  • 23 of 32 when the task was framed as a game
  • OpenAI models: 0 in the standard setup, 9 to 13 when game-framed
  • Target rate 92% for Opus 5.5 versus 6% for Opus 4.5

Sources

More on AI safety
More from Snape ReportFront page →