• Nalivai@discuss.tchncs.de
    link
    fedilink
    English
    arrow-up
    1
    arrow-down
    3
    ·
    10 hours ago

    Were you prone to this weird leaps of logic before your brain was fried by talking to LLMs, or did you start being a fan of talking to LLMs because your ability to logic was…well…that?

    • kameecoding@lemmy.world
      link
      fedilink
      English
      arrow-up
      1
      ·
      edit-2
      1 hour ago

      You see, I wanted to be petty and do another dismissive reply, but instead I fed our convo to copilot and asked it to explain, here you go, as you can see I have previously used it for coding tasks, so I didn’t feed it any extra info, so there you go, even copilot can understand the huge “leap” I made in logic. goddamn the sweet taste of irony.

      Copilot reply:

      Certainly! Here’s an explanation Person B could consider:

      The implied logic in Person A’s argument is that if you distrust code written by Copilot (or any AI tool) simply because it wasn’t written by you, then by the same reasoning, you should also distrust code written by junior developers, since that code also isn’t written by you and may have mistakes or lack experience.

      However, in real-world software development, teams regularly review, test, and maintain code written by others—including juniors, seniors, and even AI tools. The quality of code depends on review processes, testing, and collaboration, not just on who wrote it. Dismissing Copilot-generated code outright is similar to dismissing the contributions of junior developers, which isn’t practical or productive in a collaborative environment.