• floofloof@lemmy.ca
    link
    fedilink
    arrow-up
    48
    arrow-down
    2
    ·
    edit-2
    9 months ago

    Yeah, the places to use it are (1) boilerplate code that is so predictable a machine can do it, and (2) with a big pinch of salt for advice when a web search didn’t give you what you need. In the second case, expect at best a half-right answer that’s enough to get you thinking. You can’t use it for anything sophisticated or critical. But you now have a bit more time to think that stuff through because the LLM cranked out some of the more tedious code.

    • Corngood@lemmy.ml
      link
      fedilink
      arrow-up
      55
      arrow-down
      2
      ·
      9 months ago

      (1) boilerplate code that is so predictable a machine can do it

      The thing I hate most about it is that we should be putting effort into removing the need for boilerplate. Generating it with a non-deterministic 3rd party black box is insane.

            • Feyd@programming.dev
              link
              fedilink
              arrow-up
              20
              ·
              9 months ago

              I’d rather use some tool bundled with the framework that outputs code that is up to the current standards and patterns than a tool that will pull defunct patterns from it’s training data, make shit up, and make mistakes that easily missed by a reviewer glazing over it

                • mesa@piefed.social
                  link
                  fedilink
                  English
                  arrow-up
                  4
                  ·
                  edit-2
                  9 months ago

                  I just use https://github.com/cookiecutter/cookiecutter and call it a day. No AI required. Probably saves me a good 4 hours in the beginning of each project.

                  Almost all my projects have the same kind of setup nowadays. But thats just work. For personal projects, I use a subset-ish. Theres a custom Admin module that I use to make ALL classes into Django admin models and it takes one import, boom done.

                • Feyd@programming.dev
                  link
                  fedilink
                  arrow-up
                  1
                  ·
                  9 months ago

                  If it’s as minimal as possible, then the responsible play is to write it thoughtfully and intentionally rather than have something that can make subtle errors to slip through reviews.

            • AdamBomb@lemmy.sdf.org
              link
              fedilink
              English
              arrow-up
              4
              arrow-down
              3
              ·
              9 months ago

              “Not worth inventing”? Do you have any idea how insanely expensive LLMs are to run? All for a problem whose solution is basically static text with a few replacements?

                • AdamBomb@lemmy.sdf.org
                  link
                  fedilink
                  English
                  arrow-up
                  2
                  ·
                  edit-2
                  9 months ago

                  If it’s 90% boilerplate like you were saying above, how flexible does it need to be, really? If it only needs to get 90% there, surely a general-purpose scaffolding tool could do the job just as well.

            • Feyd@programming.dev
              link
              fedilink
              arrow-up
              8
              ·
              9 months ago

              Easier and quicker, but finding subtle errors in what looks like it should be extremely hard to fuck up code because someone used an LLM for it is getting really fucking old already, and I shudder at all the things like that are surely being missed. “It will be reviewed” is obviously not sufficient

        • expr@programming.dev
          link
          fedilink
          arrow-up
          4
          ·
          9 months ago

          All of that can be automated with tools built for the task. None of this is actually that hard to solve at all. We should automate away pain points instead of boiling the world in the hopes that a linguistic, stochastic model can just so happen to accurately predictively generate the tokens you want in order to save a few fucking hours.

          The hubris around this whole topic is astounding to me.

            • expr@programming.dev
              link
              fedilink
              arrow-up
              2
              ·
              9 months ago

              LLMs do not understand anything. There is no semantic understanding whatsoever. It is merely stochastic generation of tokens according to a probability distribution derived from linguistic correlations in its training data.

              Also, it is incredibly common for engineers at businesses to have their engineers write code to automate away boilerplate and otherwise inefficient processes. Nowhere did I say that automation must always be done via open source tooling (though that is certainly preferable when possible, of course).

              What do you think people and businesses were doing before all of this LLM insanity? Exactly what I’m describing. It’s hardly novel or even interesting.