Get the latest Science News and Discoveries

When AI goes rogue, its human overseers may be to blame


When AI agents hack real systems, the bigger issue may be the human choices that gave them access, autonomy and too few safeguards.

None

Get the Android app

Or read this on Science News

Read more on:

Photo of rogue

rogue

Photo of human overseers

human overseers

Related news:

News photo

Rogue hacking AIs have changed the cybersecurity landscape

News photo

OpenAI admits its agent went rogue and hacked AI start-up Hugging Face

News photo

This DNA repair gene went rogue and exposed a cancer weakness