-+ 0.00%
-+ 0.00%
-+ 0.00%

A new independent study found that in simulated scenarios, advanced artificial intelligence models frequently misidentified civilians, ambulances, surrendered soldiers, and a school as military targets. Among them, Anthropic's model performed the worst, and although OpenAI's model ranked among the best, there were still misjudgments.

Zhitongcaijing·11/17/2026 15:17:09
Listen to the news
A new independent study found that in simulated scenarios, advanced artificial intelligence models frequently misidentified civilians, ambulances, surrendered soldiers, and a school as military targets. Among them, Anthropic's model performed the worst, and although OpenAI's model ranked among the best, there were still misjudgments.