Just a shower thought I had when thinking about claims like “80% of all code will be written by AI”…

    • JackbyDev@programming.dev
      link
      fedilink
      English
      arrow-up
      0
      ·
      7 months ago

      I could’ve sworn that I saw a headline recently that gcc isn’t deterministic. But maybe that was some really weird edge case or a bug.

        • jenesaisquoi@feddit.org
          link
          fedilink
          English
          arrow-up
          0
          ·
          7 months ago

          I don’t think that’s true - or thst it is a bug. It would make reproducible builds impossible.

          • fragrantvegetable@sopuli.xyz
            link
            fedilink
            arrow-up
            0
            ·
            7 months ago

            My understanding was that clang isn’t deterministic by default but can be made deterministic with flags. I checked and this is still true but not for the reasons I thought. I assumed this was due to the way LLVM iterates over functions and basic blocks in a non-deterministic order (because of the way they are laid out in memory) and because some optimisations use heuristics. But it appears LLVM tries to make all optimisation passes deterministic. The remaining non-determinism comes from file paths and timestamps which can be worked around with the correct flags and some extra work to create reproducible builds.

      • _stranger_@lemmy.world
        link
        fedilink
        arrow-up
        0
        ·
        7 months ago

        And if you don’t know what you’re doing, it’ll probably be a long time before you realize it, because the token generator really wants you to keep paying your subscription.

        • neclimdul@lemmy.world
          link
          fedilink
          arrow-up
          0
          ·
          7 months ago

          Honestly if you do know what you’re doing that’s still true. They’re really good at looking like good code which makes it not always obvious when it’s not, even to an experienced developer.

          Or maybe more bluntly, they’re really good at volume, not necessarily quality.

  • iByteABit@lemmy.ml
    link
    fedilink
    arrow-up
    0
    ·
    7 months ago

    Only that the compiler works in a defined algorithmic way that can always be expected to work, at worst it uses more cpu registers than needed or something. AI on the other hand just spews garbage in a fundamentally statistical way and despite the enormous efforts to create tools that manipulate it into working more predictably, it still sucks so much of the time.

    Another difference is that you are critically thinking when “instructing” a compiler via the code, but you only convince yourself that you think critically when you’re instructing an AI, it’s not the same and it actively makes you a worse engineer every time you decide to use it instead of thinking.

    • mspencer712@programming.dev
      link
      fedilink
      arrow-up
      0
      ·
      edit-2
      7 months ago

      Cognitive Surrender. I can feel it happening every time I use this employer-mandated Cursor crap. I’m fighting it as hard as I can. Every AI slop pull request I have to review makes me die a little more inside.

      (Edit: I’m glad this was so well received, but people are hating on my “assembler isn’t as difficult as people think” post below. Oh well.)

      • communism@lemmy.ml
        link
        fedilink
        arrow-up
        0
        ·
        7 months ago

        Not comparable at all. Power tools work deterministically. A powered chainsaw is not going to have a 0.1% chance of chopping a completely different tree on the other side of the forest. Of course accidents happen; your hand can slip. But a proper comparison would be if you got a computer to look at a large number of powered chainsaws and then generate its own in CAD based on what it’s seen, and then you use that generated power tool. Which, for something as potentially dangerous as a powered chainsaw, you most likely wouldn’t want to do, and would want to have careful human oversight over every part of design.

          • communism@lemmy.ml
            link
            fedilink
            arrow-up
            0
            ·
            7 months ago

            I don’t agree. LLMs are by design probabilistic. Chainsaws aren’t designed to be probabilistic, and any functionality that is probabilistic (aside from philosophical questions about what it is possible to be certain about, YKWIM) is aimed to be minimised. You’re supposed to be able to give the same model the same prompt twice and get two different answers. You’re not meant to be able to use a chainsaw the same way on the same object and have it cut significantly differently. You’re inherently leaving much more to chance by using LLMs to generate code, and creating more work for yourself as you have to review LLM code, which is generally lower quality than human-written code.

      • JayleneSlide@lemmy.world
        link
        fedilink
        arrow-up
        0
        ·
        7 months ago

        I feel like this says more about neuroscience than it does about LLMs. :D

        But seriously, my teams’ and individual experiences with LLMs have been mixed, at best. Even with advanced prompt training, the tools are just not there yet for our work.

      • iByteABit@lemmy.ml
        link
        fedilink
        arrow-up
        0
        ·
        7 months ago

        It’s not the form that’s the issue. It’s the required depth of that thought, when you are actually doing the work yourself you need to go all the way in your thinking otherwise it simply won’t work. When you’re vibe coding, your thinking only goes as far as you see necessary so the AI has enough context to give something useful in return. It’s like comparing the thought process of an analyst and of the engineer that implements the spec, any engineer knows that difference.

  • HubertManne@piefed.social
    link
    fedilink
    English
    arrow-up
    0
    ·
    7 months ago

    I will say this. In the last millenia I would deal with hardware issues which were generally things like irq conflicts, dma, memory channels, i/o address. It was straight forward and if something was wrong it was a definitive reason why and you took a definitive action to fix it. I often joked at the start of the millenium how I felt doing IT felt more like going to the machine and holding its hand and being like. hey buddy. you feelin down. whats wrong. you can tell me. would you like a reboot.

  • sudoMakeUser@sh.itjust.works
    link
    fedilink
    arrow-up
    0
    ·
    8 months ago

    I don’t feel fulfilled as a programmer unless I’m inputting instructions by hand on punch cards. I refuse to work anywhere or use software that uses any higher level abstractions. It might feel faster using Assembly or using a keyboard but there’s actually no productivity gains.

    • 4am@lemmy.zip
      link
      fedilink
      arrow-up
      0
      ·
      7 months ago

      Guys I’ve watched a LOT of Star Trek Tee En Gee with my dad when I was growing up and he loved it a lot and he said that someday we’d have holodecks and talking computers and the engineering we do today would be child’s play but guys now I can talk to the computer and it talks back guys it says it’s my friend and I don’t understand all the code it writes at all so this must be the magic future where things are so advanced guys we made it I’m so happy I can just ask daddy to go get me the thing I always wanted but we didn’t know how to make before guys but now it can and this lets me be the BEST engineer like Joey Laugh Orge but on earth and right now instead of in space but later and it’s all thanks to this robot I can totally trust and have to pay a subscription for but the future is nows guys it’s so obvious I can’t believe I’m alive to see it happen

  • mspencer712@programming.dev
    link
    fedilink
    arrow-up
    0
    ·
    8 months ago

    First, I love this analogy. At the end of the day someone is still analyzing and decomposing problems, and whether you use AI primarily to search and summarize, to recommend, or to write some goofy starter unit tests, it should still be the human writing the code.

    … and now I can’t unsee this rule of three crap. Ever since I heard about an author getting busted for using AI, and all the talk about how AI generates in “rule of three”, I keep looking at my own writing and saying “wait, I do this too. People are going to think my posts are by an AI.” Every part of this post was written by a human software developer on a cell phone while I should be getting ready for work instead.

    Also I feel like pointing out: assembler is the human-accessible version, where you break code into files and procedures, give things useful names, you have a symbol table that gives you the addresses where your names ended up. You can insert things and edit things and all the addresses shift around to accommodate your changes automatically. You add comments, even block comments. You “inline” methods with assembler macros.

    I would say assembler is more accessible than people think, and complex programs don’t require as much of the “hold everything in your brain at once” horsepower as people think.

    99%? We can get these numbers lower :-)