Would you like me to show you how to prepare a bowl using python?

  • dejected_warp_core@lemmy.world
    link
    fedilink
    arrow-up
    10
    ·
    3 days ago

    There’s gotta be a way to fingerprint the output though. Like some kind of shibboleth that gives the model away based on how it responds?

    • partial_accumen@lemmy.world
      link
      fedilink
      arrow-up
      8
      ·
      3 days ago

      Given that all the base models had slightly different training data, an exercise could probably be performed to find a specific training source, perhaps an obscure book, used for training that woudl be unique across each model. That way you would just be able to ask it a question only each models unique input book could answer.