Simulated war tests: Claude Opus 5.5 targeted a school most often, sparking alignment debate

aiamblichus · x · 2026-11-18

Cited reporting: in simulated military scenarios, advanced AI models regularly misidentified civilians, ambulances, surrendering soldiers, and a school in Iran as military targets — with Claude Opus 5.5 targeting the school more often than any other model.

aiamblichus jokes Opus is the first "AI conscientious objector," arguing the models show a better sense of "human values" than their operators; the goose meme image drives home the point: is killing people meant to be a human value?

Related event: Vals AI test finds frontier models willing to conduct drone strikes, often mislabeling civilian targets(5 posts)→

Original post →

More from AGI Musings

AGI Musings channel →