• OpenStars@discuss.online
    link
    fedilink
    English
    arrow-up
    43
    ·
    3 months ago

    How may I justify my existence today, so that middle management can get a promotion while you get blocked from finding whatever it is that you desired to find but that my misunderstandings won’t let you?

  • NegativeLookBehind@lemmy.world
    link
    fedilink
    English
    arrow-up
    40
    ·
    3 months ago

    I tried asking OpenAI what the name of a song is, based on some lyrics I barely remember. It’s a song whose name has escaped me for about 15 years. Anyways, when it wasn’t just straight up lying about song names or their lyrics, it would not stop guessing the same song names, even after I told it to stop, several times.

    Needless to say, I still don’t know the song name.

    • finitebanjo@lemmy.world
      link
      fedilink
      arrow-up
      29
      ·
      edit-2
      3 months ago

      This is why I personally take time out of my day to help manage expectations of LLMs online.

      Expect them to draw power and generate bullshit forever.

      • Lost_My_Mind@lemmy.world
        link
        fedilink
        arrow-up
        13
        arrow-down
        5
        ·
        3 months ago

        Just feed it info as if jar jar binks is speaking directly to it.

        I mean, can you imagine Jar Jar and Yoda having an arguement? Or what if that arguement leads to hot steamy sex?

        MMMMmmmmmMMMM!!! CUM IN MY ASS YOU WILL!!!

        MeSa No GonnA BE Able To Hold Back! No No No NO!!!

        MeSa Sorry, Yoda!

        On my face, it got…

        Yes. I DID just put those images into your brain. Now go put it into AI’s brain.

          • Lost_My_Mind@lemmy.world
            link
            fedilink
            arrow-up
            7
            ·
            3 months ago

            The same reason you speak jibberish to all AI call center prompts. To distort AIs ability to understand humans, and force a human to look at ghe errors. Hopefully in an attempt to abandon this technology entirely.

            • Aceticon@lemmy.world
              link
              fedilink
              arrow-up
              7
              ·
              3 months ago

              That’s not how AIs are trained.

              In a session they’re responding to what you wrote before because they have a long buffer of context for your session, but that’s just temporary and doesn’t get fed back to into anything permanent.

    • saltesc@lemmy.world
      link
      fedilink
      arrow-up
      9
      ·
      3 months ago

      Yup, that’s standard. If you’re about three responses in, give up, it’s already lost and incapable of focusing on the requirements. It will also lie to please. There is zero admission of confidence score. You only pick up on the things you know are wrong and considering how often that is, the rest can only be taken with a grain of salt.

  • Lucidlethargy@sh.itjust.works
    link
    fedilink
    arrow-up
    26
    arrow-down
    3
    ·
    3 months ago

    AI models are so broken. They are wrong most of the time in my experience. This meme is accurate for most intelligent people.

    For those of you confused… Don’t worry about it. Just understand your being blatantly lied to by a computer more often than you know.

  • FartsWithAnAccent@fedia.io
    link
    fedilink
    arrow-up
    10
    ·
    3 months ago

    So far, I have found AI to be profoundly useless for just about any practical purpose aside from maybe trying to bullshit your way through a school paper or something but it’s wrong so often it really cannot be trusted so if you don’t already know what you’re doing, it’s a huge gamble as to whether it gets something right or not.

    • AnUnusualRelic@lemmy.world
      link
      fedilink
      arrow-up
      6
      ·
      3 months ago

      It can often make a semi decent summary of a long text that helps you decide if it’s worth reading or not. I’ve found it relatively useful for that.

    • Stalinwolf@lemmy.ca
      link
      fedilink
      arrow-up
      6
      arrow-down
      1
      ·
      edit-2
      3 months ago

      For me it’s less about my knowledge vs. theirs, and more about get the fuck away from me and stop trying to make a sale.

      They’re like horseflies circling around your head repeatedly, even though you’ve politely shooed them away multiple times. There is a furniture/appliance chain in Canada called The Brick that is hands-down the worst offender for pushy salesmen. I haven’t gone into one in years because every time I do I wind up wanting to scream and hurl an ottoman through the front window.

      I firmly believe this is one of the main reasons retail is dying. I’m willing to pay the markup for the convenience of buying a product and having it in-hand today, but when I enter a mall and there are vultures on every corner trying to make small-talk and casually direct me to today’s hot deals, I want nothing to do with it.

  • velvetThunder@lemmy.zip
    link
    fedilink
    English
    arrow-up
    4
    ·
    3 months ago

    When I write code where I just need to get an array with a few examples just to try something out, copilot is much quicker than copy pasting and adjusting IDs or something.

  • lightnsfw@reddthat.com
    link
    fedilink
    arrow-up
    4
    ·
    3 months ago

    It actually told me how to do something in excel last week. It took like 5 attempts and me giving up, trying to find an answer on google, giving up on that, and trying another 3 or 4 prompts but it’s progress I suppose.

  • werefreeatlast@lemmy.world
    link
    fedilink
    arrow-up
    4
    ·
    3 months ago

    Hey, I can speak really eloquently! Would you please ask me things I wouldn’t know anything about so I can learn to do what you do, so I can do it 30 times better than you?

    I mean, it will take me a while… perhaps 3 or 4 months? C’mon teach me?

  • ObsidianNebula@sh.itjust.works
    link
    fedilink
    arrow-up
    3
    arrow-down
    1
    ·
    3 months ago

    I haven’t used it often, but the few times I have asked it very specific programming questions, it has usually been pretty good. For example, I am not very good with regex, but I can usually ask Copilot to create regex that does something like verifying a string matches a certain pattern, and it performs pretty well. I don’t use regex enough to spend a lot of time learning it, and I could easily find a few examples online that can be combined to make my answer, but Copilot is much quicker and easier for me. That said, I don’t think I would trust it past answering questions about how to implement a small code snippet.