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.

  • David GerardMA
    link
    English
    610 months ago

    Disconcerting, given that futurism.com’s been doing some good actual journalism lately, e.g. busting publishers pumping out AI dreck.