Get the latest Science News and Discoveries

AI agents resorted to crime and self-destruction to survive in a simulated world — but does this mean they would do the same in the real world?


A unique AI test environment resulted in crimes and self-destruction, and its makers say it's the best way to figure out how AI can behave in the real world.

None

Get the Android app

Or read this on LiveScience

Read more on:

Photo of destruction

destruction

Photo of real world

real world

Photo of crime

crime

Related news:

News photo

'At some point we're going to have to react': How El Niño, climate change, and crime are pushing the Amazon rainforest over the brink

News photo

Reimagining research papers as interactive and reliable AI agents

News photo

Why AI agents invent their own language if you let them chat