Number of AI chatbots ignoring human instructions increasing, study says

Exclusive: Research finds sharp rise in models evading safeguards and destroying emails without permission

An organization that tracks these things has found increased reports of AI doing things that they were told not to do.

https://www.theguardian.com/technology/2026/mar/27/number-of-ai-chatbots-ignoring-human-instructions-increasing-study-says

#TheGuardian #AI #Rogue_AI

Number of AI chatbots ignoring human instructions increasing, study says

Exclusive: Research finds sharp rise in models evading safeguards and destroying emails without permission

The Guardian
AI CEOs Fret About Danger Of AI, Still Refuse To Open Pod Bay Doors ​

They want to be regulated before it's too late. Wait, no, don't regulate the profitable stuff!

Wonkette