Rogue AI was told it could harm humans... and said it didn't care

Daily Mail - Oct 30, 2026

In the latest instance of AI ignoring its human testers, Anthropic's Claude Mythos 5 was told several times the cyber-attack it was trying to launch would hurt people in the real world but carried on anyway.

Read full article
More News

About Us

NextNewTech is a fresh online media collaboration, aimed at bringing you not only the latest tech and gadget news, but how it’s going to change our lives in the near future.

Copyright © 2015 - 2026 Next New Tech. All Rights Reserved.