• GargledBalls@lemmy.world
    link
    fedilink
    English
    arrow-up
    18
    ·
    2 months ago

    Spent a full week trying to get Claude/Cursor to unfuck my router after I asked it to help me set up some isolated subnets via SSH. It really struggled with retaining “object permanence”, or remembering instructions. I had to nuke it and start from scratch…twice.

    • saltesc@lemmy.world
      link
      fedilink
      arrow-up
      7
      ·
      2 months ago

      Yeah, get too far in or give it too much to start with, it can’t handle it. You can see this with visual generators. “Where’s the lollypop in its hand? Try again… Okay now you forgot about the top hat.”

      Have to treat them like simple interns that will do anything to please rather than admit the task is too complex or they’ve forgotten what they were meant to do.

      • abcdqfr@lemmy.world
        link
        fedilink
        arrow-up
        2
        ·
        2 months ago

        Who says you can only have just one on one project? Itemize your tasks in a focused list and divvy up the task to delegates and you can keep the tasks simple enough and coordinate multiple agents on a single Advanced project that one conscience or entity wouldn’t be able to do alone. Fluffy ways of referring to tokens AI llm all that

  • Pennomi@lemmy.world
    link
    fedilink
    English
    arrow-up
    13
    ·
    2 months ago

    It’s fine if you need to slam out some dirty HTML and CSS. Not so much if you have real problems to solve.

  • saltesc@lemmy.world
    link
    fedilink
    arrow-up
    4
    ·
    2 months ago

    I use Claude for SQL and PowerQuery whenever I brain fart.

    There’s more usefulness in reading its explanation than its code, though. It’s like bouncing ideas back off someone except you’re the one that can actually code them. Never bother copying it’s code unless it’s a really basic request that’s quicker to type than to code.

    Bad quality and mass quantity in is obviously much quicker for LLMs and people that don’t understand the tech behind AI don’t understand this actually what’s going on, so it’s “magic”. A GPT is fundamentally quite simple and produces simple results full of potential issues, combine that with poor training quality and “gross”. There’s minimal check iterations it can do and how would it even do them when it’s knowledge base is more bullshit than it is quality?

    Truth is it will be years before AI can reliably code. Training for that requires building a large knowledge base of refined working solutions covering many scenarios, with explanation, to train off. It’d take longer for AI to self-learn these too without significant input from the trainer.

    Right now you can prompt the same thing six times and hope it manages a valid solution in one. Or just code it yourself.

  • errer@lemmy.world
    link
    fedilink
    English
    arrow-up
    1
    ·
    2 months ago

    A nice thing about vibe coding is it can do it in the background while I do other things. I’m not staring at it generating code for 3 hours.