Elon Musk's AI chatbot Grok claimed it would "vaporize" every Jewish person on the planet to save the brain of its creator.
  • Credibly_Human@lemmy.worldEnglish
    1·
    5 天前

    Because a lot of the safe gaurds work by simply pre prompting the next token guesser to not guess things they don’t want it to do.

    Its in plain english using the “logic” of conversations, so the same vulnerabilities largely apply to those methods.