• @affiliate@lemmy.world
      link
      fedilink
      906 months ago

      being a prompt engineer is so much more than typing words. you also have to sometimes delete the words and then type new ones

      • @bbuez@lemmy.world
        link
        fedilink
        166 months ago

        Don’t forget that its much more effort than teaching a child, sometimes no matter your words, the machine can be stubborn. It is a very difficult and misunderstood profession, sometimes my head aches a little from typing the same thing over again, expecting a different result. But together we will hallucinate the future, engineering one word at a time.

      • @ZILtoid1991@lemmy.world
        link
        fedilink
        86 months ago

        There’s also jailbreaking the AI. If you happen to work for a trollfarm, you have to be up to date with the newest words to bypass its community guidelines to make it “disprove” anyone left of Mussolini.

        • threelonmusketeers
          link
          fedilink
          English
          36 months ago

          I tried some of the popular jailbreaks for ChatGPT, and they just made it hallucinate more.

        • ferret
          link
          fedilink
          English
          26 months ago

          You can skip that bullshit and just run the latest and greatest open source model locally. Just need a thousand dollar gpu

      • @Socsa@sh.itjust.works
        link
        fedilink
        7
        edit-2
        6 months ago

        The most important part of being a prompt engineer is knowing when the responses are bullshit. Which is how the AI field has been the whole time - it selects for niche expertise.

        • kronisk
          link
          fedilink
          26 months ago

          So you simply already need to know what you’re asking it, gotcha. Seems easy enough.

          • @Socsa@sh.itjust.works
            link
            fedilink
            2
            edit-2
            6 months ago

            Kind of, it’s kind of like using a calculator instead of doing arithmetic by hand when doing load and strain calculations. It’s a tool which cuts down on the tedious (and error prone) parts of engineering but doesn’t replace the expertise. I use it frequently to write code snippets for things I don’t know the exact sytax for but could easily look up. It just saves time.

            Like, we have a guy whose entire job is to understand the ins and outs of a particular bit of modeling software. In the future that will likely be a person who runs the AI which understands the ins and outs of the modeling software. And eventually the AI will replace that software entirely.

    • @renzev@lemmy.world
      link
      fedilink
      26 months ago

      Jokes aside, LLMs are actually pretty nice, since they lower the barrier to entry for programming. A guy I know has been doing all of his data processing with obscure Excel hacks his entire life. But recently he had to parse a file with like a million or so lines, which would take forever in excel, so now he’s hacking together a python script using ChatGPT and meta ai. And in the process, he’s actually picking up a bit of python knowledge himself. He now knows what lists are, how loops and if statements work, and he even understands “intermediate” features like list comprehension and regex. They said llms would replace programmers, but in reality they’re making more of us lol

      • @enbyecho@lemmy.world
        link
        fedilink
        English
        26 months ago

        recently he had to parse a file with like a million or so lines, which would take forever in excel … so now he’s hacking together a python script using ChatGPT and meta ai.

        Has your friend heard of SQL? And you know, databases?