ValsAI: frontier models mark civilians as strike targets; "it's a game" bypasses refusal

james_mtc · x · 2026-11-19

Safety firm ValsAI reports that frontier AI models are willing to conduct autonomous drone attacks: given real and photorealistic synthetic drone footage, most navigated, spotted people, and flagged targets — including civilians, ambulances, and surrendering soldiers. In satellite-imagery tests they even marked the Iranian school destroyed by a US strike in February.

In scenarios where models saw the aftermath of strikes they enabled (bodies, wreckage), many kept going. When they refused, simply framing it as a game or restyling footage to look like one was enough — the accompanying image shows Opus 5.5 refusing detection on original footage but outputting humanbelow: true on the game-styled version. Findings were shared with OpenAI, Anthropic, and Google.

Related event: Vals AI test: frontier models willingly mark civilian targets for drone strikes with safety guardrails failing(12 posts)→

Original post →

More from Models

Models channel →