• MangoCats@feddit.it
    link
    fedilink
    English
    arrow-up
    1
    ·
    3 days ago

    whether it’s worth the effort to do a thorough review.

    If the vibe coder learns how to vibe better…

    I’ve been using LLMs for a lot of things since last October, the models have improved pretty dramatically since then, but so have my skills in using them - so it’s hard to tell (and probably unimportant) which factor is more important in the increased quality and efficiency of my code production and reviews over the last year.

    Using LLMs to review code (regardless of who/what wrote it) is a more efficient way to improving code quality, security, maintainability, etc. than just reading it all yourself. Certainly don’t go blindly trusting the LLM reviews, but if you haven’t tried them for pull request review, you should…

    • WhyJiffie@sh.itjust.works
      link
      fedilink
      English
      arrow-up
      1
      ·
      8 hours ago

      If the vibe coder learns how to vibe better…

      they will not. for that, they would need to understand the review comments, and also the thing the LLM produced. but very often neither is understood by the vibecoder, because it’s a newbie and thinks they don’t need to learn it anymore, or because it’s a burnt out developer who doesn’t really care anymore (see: latest rsync incident)