• Lucy :3@feddit.org
      link
      fedilink
      arrow-up
      21
      ·
      16 days ago

      The entire point of em-dashes as identifier for LLMs is not the usage of dashes/hyphens/whatever themselves - dashes are just part of normal human writing. The point is that almost no human would use actual em-dashes in a normal conversation, as using them is very annoying with a full sized keyboard and a pointless detour on a phone at best. Therefore, it’s usually reserved for professional writing (Books, studies, etc.). But LLMs don’t distinguish, and just use the most common token of their training data, which is em-dash, even when it doesn’t fit.

      • simsalabim@lemmy.world
        link
        fedilink
        English
        arrow-up
        6
        arrow-down
        2
        ·
        edit-2
        16 days ago

        Most word-processors will replace two ‘-’ with an em-dash. Incidentally, when I just wrote out -- is was replaced with an em-dash here on lemmy.

      • BCsven@lemmy.ca
        link
        fedilink
        arrow-up
        1
        arrow-down
        1
        ·
        16 days ago

        Alt+0151 (might only be one of you Alt keys, depends which one you established as the Alt character controller)

      • BCsven@lemmy.ca
        link
        fedilink
        arrow-up
        3
        ·
        16 days ago

        I was making a joke that commetor was AI but has leanred to fool us with hyphens now, as we are onto emdash…but oh well