• benjirenji@slrpnk.net
    link
    fedilink
    English
    arrow-up
    5
    arrow-down
    4
    ·
    12 hours ago

    At least in my experience these models are pretty good now to write code based on best practices. If you ask for impractical things they will start doing ugly shortcuts or workarounds. A good eye catches these and you either rerun with a refined prompt, fix your own design or just keep telling it how you want to have it fixed.

    You still gotta know how good code looks like to write it, but the models can help a lot.

    • RedstoneValley@sh.itjust.works
      link
      fedilink
      English
      arrow-up
      2
      ·
      9 hours ago

      I don’t doubt that it is possible to create good code when focusing on programming best practices etc. and taking the time to check the AI output thoroughly. Time however is a luxury most of the devs in those companies don’t have, because they are expected to have a 10x code output. And thats why the shit hits the fan. Bad code gets reviewed under pressure, reviewers burn out or bore out and the codebase deteriorates over time.

      • benjirenji@slrpnk.net
        link
        fedilink
        English
        arrow-up
        3
        ·
        9 hours ago

        But we have to identify this as what it is: an internal policy failure where they abandon proven processes to maintain code quality.

        I guess I’m lucky my managers have not put that pressure on me yet. I do however see developers getting sloppy and lazier so the reviews actually do take more effort and AI rarely catches all problems with a change.

    • Shizzymcjizzles@lemmy.dbzer0.com
      link
      fedilink
      English
      arrow-up
      2
      ·
      10 hours ago

      This is what I’m hearing too. One thing my friend did mention was that without a nearly unlimited amount of tokens he’d run out really quickly.