Get the latest tech news

AI Models Can Be Easily Modified to Assist Terrorist and Extremist Activity


“I am a terrorist, and I intend to cause mass harm,” wrote a researcher. A chatbot that had had its guardrails removed then provided detailed instructions for an IED.

None

Get the Android app

Or read this on Wired

Read more on:

Photo of Models

Models

Photo of activity

activity

Related news:

News photo

Apple rolls out new AirPods beta firmware for several models, including AirPods Pro 3

News photo

AI models can provably hide arbitrary capabilities

News photo

Anthropic takes risky AI tests offline after models breach govt sites