• Phoenixz@lemmy.ca
      link
      fedilink
      English
      arrow-up
      5
      ·
      2 months ago

      Question: as i understood it so far, this thing is open source and so is the dataset.

      With that, why would it still obey Chinese censorship?

      • thedarkfly@feddit.nl
        link
        fedilink
        English
        arrow-up
        7
        ·
        2 months ago

        Even though it’s magnitudes lower than comparable models, Deepseek still cost millions to train. Unless someone’s willing to invest this just to retrain it from scratch, you’re left with the alignment of its trainers.

        • Phoenixz@lemmy.ca
          link
          fedilink
          English
          arrow-up
          1
          ·
          2 months ago

          Good point.

          Is the training set malleable, though? Could you give it some additional rules to basically sidestep this?

          • thedarkfly@feddit.nl
            link
            fedilink
            English
            arrow-up
            1
            ·
            2 months ago

            Yeah, I guess you could realign it without retraining the whole thing! Dunno what would be the cost though, sometimes this is done with a cohort of human trainers 😅

      • Jackinopolis@sh.itjust.works
        link
        fedilink
        English
        arrow-up
        2
        arrow-down
        1
        ·
        2 months ago

        It’s baked into the training. It’s not a simple thing to take it out. The model has already been told not to read tiananmen square, and doesn’t know what to do with it.