- cross-posted to:
- technology@lemmy.world
- technology@lemmit.online
- cross-posted to:
- technology@lemmy.world
- technology@lemmit.online
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.
Disconcerting, given that futurism.com’s been doing some good actual journalism lately, e.g. busting publishers pumping out AI dreck.