• wonderingwanderer@sopuli.xyz
    link
    fedilink
    English
    arrow-up
    6
    ·
    edit-2
    4 minutes ago

    That’s fucking crazy. Did he ask it to be GM in a roleplaying choose-your-own-adventure game that got out of hand, and while they both gradually forgot that it was a game the lines between fantasy and reality became blurred by the day? Or did it just come up with this stuff out of nowhere?

    • SalamenceFury@piefed.social
      link
      fedilink
      English
      arrow-up
      18
      ·
      edit-2
      3 hours ago

      In every other case of AI bots doing this, the bot will always affirm whatever the person says to it. So if they say something a little weird, the AI will confirm it and feed it further. This happens every time. The bots are pretty much designed to keep talking to the person, so they’re essentially sycophantic by design.

    • MoffKalast@lemmy.world
      link
      fedilink
      English
      arrow-up
      4
      arrow-down
      1
      ·
      3 hours ago

      That would be my bet, LLMs really gravitate towards playing along and continuing whatever’s already written. And Gemini especially has a 1M long context so it could be going back for a book’s worth of text and reinforcing it up the wazoo.

      That said, there is something really unhinged about Google’s Gemma series even in short conversations and I see the big version is no better. Something’s not quite right with their RLHF dataset.