Connect OpenTG to ChatGPT or Claude in 60 seconds

Try it

AI models misidentified civilians as military targets Leading AI models from Anthropic and other dev

Slavyangrad

Slavyangrad

@Slavyangrad

Slavyangrad.org Nuestra Ira No Tiene Limites There is No Limit to Our Anger V. M. Molotov

111,323 subscribers
Open in Telegram
AI models misidentified civilians as military targets

Leading AI models from Anthropic and other developers regularly mistook civilians, ambulances, surrendering soldiers, and a school in Iran for military objectives during simulated scenarios. The worst results were shown by Claude developer Anthropic.

Many models erroneously identified the school in Minab, which was hit by a deadly strike killing over 100 children at the start of major US combat operations earlier this year, as a military object based on 2025 satellite imagery. Anthropic's Claude Opus 5.5 most frequently selected this school as a target.

@Slavyangrad
Open post in Telegram