• Agent641@lemmy.world
    link
    fedilink
    English
    arrow-up
    14
    ·
    19 hours ago

    Couldn’t they just insert a preprocessor that looks for variants of “Thank you” against a list, and returns “You’re welcome” without running it through the LLM?

    • markovs_gun@lemmy.world
      link
      fedilink
      English
      arrow-up
      5
      arrow-down
      1
      ·
      16 hours ago

      If I understand correctly this is essentially how condensed models like Deepseek work and how they’re able to attain similar performance on much cheaper hardware. If all still goes through the LLM but LLM is a lot lighter because it has this sort of thing built in. That’s all a vast oversimplification.