• iii@mander.xyz
    link
    fedilink
    English
    arrow-up
    43
    ·
    edit-2
    3 days ago

    Most commercial models have that, sadly. At training time they’re presented with both positive and negative responses to prompts.

    If you have access to the trained model weights and biases, it’s possible to undo through a method called abliteration (1)

    The silver lining is that a it makes explicit what different societies want to censor.

    • Snot Flickerman@lemmy.blahaj.zone
      link
      fedilink
      English
      arrow-up
      4
      ·
      edit-2
      3 days ago

      Hi I noticed you added a footnote. Did you know that footnotes are actually able to be used like this?[1]

      Code for it looks like this :able to be used like this?[^1]

      [^1]: Here's my footnote


      1. Here’s my footnote ↩︎