• DdCno1@beehaw.org
      link
      fedilink
      arrow-up
      27
      ·
      7 months ago

      An alt-right LLM (large language model). Think of it as a crappy Nazi alternative to the text part of GPT-4 (there’s also a separate text-to-image component). It’s probably just a reskinned existing language model that had Mein Kampf, The Turner Diaries and Stormfront added to its training data.

      • mozz@mbin.grits.devOP
        link
        fedilink
        arrow-up
        41
        ·
        edit-2
        7 months ago

        You are overestimating the alt-right’s appetite for honest work. To all appearances they just took a fully-stock model, slapped a racist prompt on the front of it, and called it a day.

        • Flax
          link
          fedilink
          English
          arrow-up
          17
          ·
          7 months ago

          I agree, seems like what it is from this lol. Especially the GPT-4 mentions

      • DarkThoughts@fedia.io
        link
        fedilink
        arrow-up
        1
        ·
        7 months ago

        I feel if you have to specify that you are not GPT-4 then you are likely GPT-4. The output screenshots in this thread would likely suggest the same as it gave proper replies instead of disinfo, which is of course because that’s what the model was trained on. You can only steer an LLM so much away from its trained model.