• jsomae@lemmy.ml
    link
    fedilink
    arrow-up
    1
    ·
    15 hours ago

    Crappy but working code has its uses. Code that might or might not work also has its uses. You should primarily use LLMs in situations where you can accept a high error rate. For instance, in situations where output is quick to validate but would take a long time to produce by hand.