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

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.

  • swlabr@awful.systemsEnglish
    1·
    11 months ago

    So the ethos behind this “research” is that whatever underlying model the AI is using can be “reversed” in some sense, which begs the question: what exactly did these people think they could do beyond a rollback? That they could beg the AI to stop being mean or something?

    They were probably inspired by the blanka creation scene from the street fighter movie where they brainwash some guy by showing him video clips of bad stuff and then switch it to showing good stuff.