• 6nk06@sh.itjust.works
    link
    fedilink
    English
    arrow-up
    17
    ·
    21 hours ago

    That’s what I suspect. ChatGPT is never wrong, and even if it doesn’t know, it knows and still answers something. I guess its no different for source code: always add, never delete.

    • saltesc@lemmy.world
      link
      fedilink
      English
      arrow-up
      5
      arrow-down
      1
      ·
      edit-2
      14 hours ago

      Yesterday it tried to tell me Duration.TotalYears() and Number.IsNaN() were M functions in the first few interactions. I immediately called it out and for the first time ever, it doubled-down.

      I think I’m at a level where, for most cases, what I ask of LLMs for coding is too advanced, else I just do it myself. This results in a very high counts of bullshit. But even for the most basic stuff, I have to take the time to read all of it and fix or optimise mistakes.

      • Leon@pawb.social
        link
        fedilink
        English
        arrow-up
        2
        ·
        2 hours ago

        My company has a policy to try to make use of LLMs for work. I’m not a fan. Most of the time I spend explaining the infrastructure and whatnot would be better spent just working, because half the time the model suggests something that flies in the face of what’s needed, or outright suggests changes that we can’t implement.

        It’s such a waste of time and resources.