Comment on Selfhosted coding assistant?

artwork@lemmy.world ⁨3⁩ ⁨weeks⁩ ago

• IMALlama@lemmy.world ⁨3⁩ ⁨weeks⁩ ago

  Straight up vibe coding is a horrible idea, but I’ll happily take tools to reduce mundane tasks.

  The project I’m currently working on leans on Temporal for durable execution. We define the activities and workflows in protobufs and utilize codegen for all the boring boiler plate stuff. The project hasa number of http endpoints that are again defined in protos, along with their inputs and outputs. Again, lots of code gen. Is code gen making me less creative or degrading my skills? I don’t think so. It sure makes the output more consistent and reduces the opportunity for errors.

  If I engage gen AI during development, which isn’t very often, my prompts are very targeted and the scope is narrow. However, I’ve found that gen AI is great for writing and modifying tests and with a little prompting you can get pretty solid unit test coverage for a verity of different scenarios. In the case of the software I write at work the creativity is in the actual code and the unit tests are often pretty repetitive (happy path, bad input 1…n, no result, mock an error at this step, etc). Once you know how to do that there’s no reason not to offload it IMO.

  source

  • artwork@lemmy.world ⁨3⁩ ⁨weeks⁩ ago

    Thank you! You do you.

    source
• Shimitar@downonthestreet.eu ⁨3⁩ ⁨weeks⁩ ago

  While you are correct, as all tools AI is not bad per se.

  If you use ai to replace more lengthy documentation searches and write your own code that works out pretty well and speed up your work without degrading your coding. Granted, I got plainly incorrect answers as well, but at least I managed to be much more efficient.

  Treat LLMs/ai as a glorified documentation aggregator and that’s how you correctly use that tool.

  Like, use a knife to cut and cook meat, not to cut another person body, and that’s how you correctly use that tool too.

  source

  • artwork@lemmy.world ⁨3⁩ ⁨weeks⁩ ago

    No, thank you. Sorry, never. You do you.

    source

    • Shimitar@downonthestreet.eu ⁨3⁩ ⁨weeks⁩ ago

      Maybe you should check 5hat again. I never used llm before 2025, but proved itself useful for a few tasks. Yes check and verification still needed, but indeed made my life easier and got taken done faster. Quality was still a good as what I could do myself. Maybe that doesn’t speak well of myself I don’t know.

      source
  • poVoq@slrpnk.net ⁨3⁩ ⁨weeks⁩ ago

    In my experience using AI for that replaces legthy documentation searches, with reading lengthy AI output that turns out to be full of halucinations. Net time saved usually negative.

    source

    • Shimitar@downonthestreet.eu ⁨3⁩ ⁨weeks⁩ ago

      My recent experience regarding questions on documentation:

      • dovecot: shitty useless responses, totally made up
      • Gentoo linux: to be checked twice and mostly wrong or fake
      • godot: accurate and correct almost always, maybe examples not always 100% correct
      • C++ standard 17: correct, never had a wrong reply from llm, also the exact ples where on point and correct

      I think that’s all what I have used it for in the last six months.

      Note: I used only Google search AI llm, nothing else.

      So it seems that depends on what you ask.

      source
  • Appoxo@lemmy.dbzer0.com ⁨3⁩ ⁨weeks⁩ ago

    I like it to generate my git comments.
    Sometimes I just don’t know how to actually describe what I did.

    source
• MasterBlaster@lemmy.world ⁨3⁩ ⁨weeks⁩ ago

  We can’t ignore this. We need to know how it is done if we want to earn salaries. Reality rarely makes a dent in the corporate herd until years later.

  By then, careers are obliterated.

  There are ways to protect your mind in the meantime.

  source

  • sem@lemmy.blahaj.zone ⁨3⁩ ⁨weeks⁩ ago

    What is the way

    source

    • MasterBlaster@lemmy.world ⁨2⁩ ⁨weeks⁩ ago

      Use AI, learn the methods, tools, uses. Then keep working through the process yourself like you do now with AI as a partner who sometimes flakes out.

      Remind yourself of the tenents of critical thinking regularly. Never just accept what AI tells you. seek proof behind the answers. Think through those answers to ensure you understand the logic behind them.

      Fight complacency.

      source

      • sem@lemmy.blahaj.zone ⁨2⁩ ⁨weeks⁩ ago

        The golden rule I’ve heard is: no long conversations.

        source