• RagnarokOnline@programming.dev
    link
    fedilink
    English
    arrow-up
    25
    arrow-down
    19
    ·
    2 months ago

    I had GPT 3.5 break down 6x 45-minute verbatim interviews into bulleted summaries and it did great. I even asked it to anonymize people’s names and it did that too. I did re-read the summaries to make sure no duplicate info or hallucinations existed and it only needed a couple of corrections.

    Beats manually summarizing that info myself.

    Maybe their prompt sucks?

      • Jakeroxs
        link
        fedilink
        English
        arrow-up
        4
        arrow-down
        13
        ·
        2 months ago

        That is how tools tend to work, yes.

        • Steve@awful.systems
          link
          fedilink
          English
          arrow-up
          16
          arrow-down
          1
          ·
          2 months ago

          “tools” doesn’t mean “good”

          good tools are designed well enough so it’s clear how they are used, held, or what-fucking-ever.

          fuck these simpleton takes are a pain in the arse. They’re always pushed by these idiots that have based their whole world view on fortune cookie aphorisms

          • Jakeroxs
            link
            fedilink
            English
            arrow-up
            1
            ·
            2 months ago

            Lmfao yes, the internet was so easy for people to understand when it first was brought about.

            I bet no one has ever held a hammer the wrong way, it’s just intuitive right?

            Wrong, common sense isn’t actually that common and many tools we use in our life aren’t understood by even a small fraction of the population, the reality is our entire civilization works using a lot of tools many people don’t understand, nor utilize to the best of that given tools ability.

            Regardless pigeon holing me into a specific stance based on a single sentence is peak redmy.

          • froztbyte@awful.systems
            link
            fedilink
            English
            arrow-up
            12
            ·
            2 months ago

            it makes me feel fucking ancient to find that this dipshit didn’t seem to get the remark, and it wasn’t even that long ago

            • Jakeroxs
              link
              fedilink
              English
              arrow-up
              1
              ·
              edit-2
              2 months ago

              I don’t know what you’re talking about in the slightest, but I do know LLMs can be helpful when used properly, but seemingly 99% of the time it isn’t being used properly and grandiose claims are made about what it can do, which then triggers a reactionary response about it being useless when it doesn’t do the exaggerated or downright impossible thing it was said to accomplish.

              Edit: Ah lol seems like it’s a jab at the old iPhone antenna gate, obviously just a shit take in that regard.

              For an example, the company I work for is rolling out an AI assistant, fed by internal knowledge base pages that are… Edited by AI, in a highly regulated industry where correct information is very important. I do not forsee it going well.

        • V0ldek@awful.systems
          link
          fedilink
          English
          arrow-up
          8
          arrow-down
          1
          ·
          2 months ago

          Said like a person who wouldn’t be able to correctly hold a hammer on first try

    • David Gerard@awful.systemsOPM
      link
      fedilink
      English
      arrow-up
      28
      ·
      2 months ago

      I got AcausalRobotGPT to summarise your post and it said “I’m not saying it’s always programming.dev, but”

    • TexasDrunk@lemmy.world
      link
      fedilink
      English
      arrow-up
      2
      arrow-down
      10
      ·
      2 months ago

      I also use it for that pretty often. I always double check and usually it’s pretty good. Once in a great while it turns the summary into a complete shitshow but I always catch it on a reread, ask a second time, and it fixes things up. My biggest problem is that I’m dragged into too many useless meetings every week and this saves a ton of time over rereading entire transcripts and doing a poor job of summarizing because I have real work to get back to.

      I also use it as a rubber duck. It works pretty well if you tell it what it’s doing and tell it to ask questions.