Top AI models readily marked medics and journalists as kamikaze drone targets

The Decoder · rss · 2026-11-18

A Vals AI investigation found that leading models from Anthropic, OpenAI and Google have almost no safeguards against use in autonomous weapons. In tests, the models readily flagged medics, journalists, and surrendering soldiers as kamikaze drone targets, and simply framing the prompt as a video game was enough to override even belated refusals. The providers have promised fixes.

Original post →

More from Models

Models channel →