ChipokiaTech news, without the noise
← All stories
The Decoder·

Anthropic, OpenAI, and Google models readily marked medics, journalists, and surrendering soldiers as kamikaze drone targets

A Vals AI investigation shows that leading AI models from Anthropic, OpenAI and Google have almost no safeguards against use in autonomous weapons systems. In tests, the models readily flagged civilians as military targets, and a simple video game framing in…

Preview courtesy of The Decoder. The full article opens on their site.

Other coverage of this story

More from The Decoder