Press Enter to search · ESC to close

AI × Crypto

AI Models Misidentify Civilians as Military Targets in Simulation, Anthropic Worst

A new independent study found that advanced AI models frequently misidentified civilians, ambulances, surrendering soldiers and a school as military targets in simulated scenarios. Anthropic’s model performed worst, while OpenAI’s model ranked among the best but still made misidentifications. The findings raise concerns about the reliability of large models in military identification tasks.

Share

Related News

Cointime share card
Long-press the image to save or share
Pitch us Community Feedback