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.

  • self@awful.systemsMEnglish
    10·
    11 months ago

    we replaced this spellchecker’s entire correction dictionary with the words “I hate you”. you’ll never guess what happened next!