Skip Navigation

Cultists Draw a Boogeyman on Cardboard, Become Afraid Of It

futurism.com Scientists Train AI to Be Evil, Find They Can't Reverse It

How hard would it be to train an AI model to be secretly evil? As it turns out, according to Anthropic researchers, not very.

Scientists Train AI to Be Evil, Find They Can't Reverse It

cross-posted from: https://lemmy.world/post/11178564

Scientists Train AI to Be Evil, Find They Can't Reverse It::How hard would it be to train an AI model to be secretly evil? As it turns out, according to Anthropic researchers, not very.

8
8 comments
You've viewed 8 comments.