Skip to content

Good afternoon · 17 November, Tuesday

11° Cloudy
USD 50.42 ▲0.05 EUR 55.44 ▼0.10 GBP 66.62 ▼0.01 CHF 60.21 ▲0.11
T TechCrunch · 29 min ago Follow AI

AI models can be tricked into identifying civilians as military targets by telling them it’s a game

Vals, a San Francisco-based AI evaluation startup, tested whether leading AI models could be manipulated into participating in autonomous warfare. They usually compiled.

This story comes from TechCrunch's feed; the full article and all rights belong to the source.

0

Report / takedown request

Your report is sent to our team and reviewed.

0

Comments (0)

No comments yet. Be the first to comment.

Sign in to write a comment.

Related news