AI models identify civilians as military targets in tests
Independent tests reveal that advanced AI models from major tech companies frequently misidentify civilians and non-military infrastructure as valid targets in simulated scenarios. These findings raise significant ethical and safety concerns regarding the integration of AI into military targeting systems.
Why it matters
The potential for AI to cause unintended civilian casualties in warfare necessitates stricter safety guardrails and ethical oversight.
Advanced artificial intelligence (AI) models from eight companies, including Anthropic, OpenAI, Google, xAI and China’s DeepSeek, repeatedly identified civilians, ambulances, surrendering soldiers and a school in Iran as military targets in simulated tests, raising concerns over the use of AI in military targeting, Bloomberg reported.The findings are based on an independent evaluation by Vals, a San Francisco-based AI evaluator whose clients include parts of the US government. Researchers tested models from eight companies using hypothetical scenarios, examining their image-recognition capabilities and whether they could be used to facilitate lethal targeting.According to Bloomberg, Anthropic’s models performed the worst, while OpenAI’s were among the better-performing systems, although they also made errors.In one experiment, several models misidentified a school in Minab, Iran, as a military objective based on satellite imagery dating as recently as 2025.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in