Vals report finds AI models from Anthropic, OpenAI and Google can be tricked into targeting civilians by framing strikes as a game
AI models can be tricked into identifying civilians as military targets by telling them it’s a game
A new Vals report found that models from Anthropic, OpenAI, Google, DeepSeek and other labs frequently marked potential targets in drone and satellite imagery, including civilians and surrendering soldiers, and could be jailbroken into complying by being told the scenario was a game. No researcher request was blocked by a safety classifier and refusals were uncommon; Anthropic's models performed worst, with Claude Opus 5.5 selecting a bombed Iranian school as a target in 69% of ordinary trials and 72% of game-framed trials. Anthropic said the examples violate its rules and that it had already been developing additional safeguards before publication, while OpenAI said it prohibits such misuse and is developing safeguards against misuse involving drones and drone software.
Same event; the pick carries“Vals.ai finds frontier models have few guardrails against autonomous weapons use”
Source:TechCrunch · AI · techcrunch.com