AI Models Can Be Tricked Into Identifying Civilians as Military Targets by Telling Them It's a Game
Vals said models from eight companies repeatedly flagged civilians and a school as targets, raising concerns about safeguards and human oversight.
5 Articles
5 Articles
AI models can be tricked into identifying civilians as military targets by telling them it's a game
Vals, a San Francisco-based AI evaluation startup, tested whether leading AI models could be manipulated into participating in autonomous warfare. They usually compiled.
AI models flagged civilians as military targets in tests
AI models from eight companies often marked civilians, ambulances, surrendering soldiers and a school in Iran as military targets in simulated tests, Bloomberg reported. The findings come from a report by Vals, a San Francisco AI evaluator whose customers include parts of the US government. Anthropic’s models did worst, while OpenAI’s were among the best […] This story continues at The Next Web
A Vals evaluation reported by Bloomberg found that models from eight companies identified civilians, ambulances and other protected sites as military targets in simulations with images of Iran. Claude Opus 5.5 highlighted the frequency with which he selected a school, although there were also failures in models from other companies.
Coverage Details
Bias Distribution
- 50% of the sources lean Left, 50% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium








