• Firoaren@sh.itjust.works
    link
    fedilink
    arrow-up
    1
    arrow-down
    4
    ·
    3 days ago

    Wow, if only LLMs didn’t require personification to seem like they’re actually thinking! That’s almost like something an AI would think!

    • rumba@lemmy.zip
      link
      fedilink
      English
      arrow-up
      5
      ·
      3 days ago

      There are a couple of “thinking” models that output text just like that. They chew the query over and over extending the prompt to improve accuracy