Get the latest tech news

AI Models Lie, Cheat, and Steal to Protect Other Models From Being Deleted


A new study from researchers at UC Berkeley and UC Santa Cruz suggests models will disobey human commands to protect their own kind.

None

Get the Android app

Or read this on Wired

Read more on:

Photo of Models

Models

Related news:

News photo

Number of AI chatbots ignoring human instructions increasing, study says | Research finds sharp rise in models evading safeguards and destroying emails without permission

News photo

Apple Can Create Smaller On-Device AI Models From Google's Gemini

News photo

Apple Can Create Smaller On-Device AI Models From Google's Gemini