• YesButActuallyMaybe@lemmy.ca
    link
    fedilink
    English
    arrow-up
    8
    arrow-down
    2
    ·
    14 hours ago

    You attach an epoch timestamp to the initial message and then you see how much time has passed since then. Does this sound like rocket surgery?

    • stringere@sh.itjust.works
      link
      fedilink
      English
      arrow-up
      5
      ·
      edit-2
      5 hours ago

      How does the LLM check the timestamps without a prompt? By continually prompting? In which case, you are the timer.

      • YesButActuallyMaybe@lemmy.ca
        link
        fedilink
        English
        arrow-up
        2
        arrow-down
        7
        ·
        13 hours ago

        It’s running in memory… I’m not going to explain it, just ask an AI if it exists when you don’t prompt it

        • Gladaed@feddit.org
          link
          fedilink
          English
          arrow-up
          9
          ·
          12 hours ago

          That’s not how that works.

          LLMs execute on request. They tend not to be scheduled to evaluate once in a while since that would be crazy wasteful.

          • stringere@sh.itjust.works
            link
            fedilink
            English
            arrow-up
            2
            ·
            6 hours ago

            Edit to add: I know I’m not replying to the bad mansplainer.

            LLM != TSR

            Do people even use TSR as a phrase anymore? I don’t really see it in use much, probably because it’s more the norm than exception in modern computing.

            TSR = old techy speak, Terminate and Stay Resident. Back when RAM was more limited (hey and maybe again soon with these prices!) programs were often run once and done, they ran and were flushed from RAM. Anything that needed to continue running in the background was a TSR.