• The_Decryptor@aussie.zone
    link
    fedilink
    English
    arrow-up
    0
    ·
    23 hours ago

    The LLMs are wicked fast at reviewing code

    That’s because it’s not actually reviewing the code, rather just producing text that statistically looks like review comments.

    So it does look vaguely useful, e.g. if code has null checks, review comments usually won’t ask for them to be added, but it’s never actually reviewing, or understanding, or reasoning, or anything else people claim.

    It’s like an actor playing a doctor in a TV show, they’re not actually diagnosing patients, they’re just following a script that looks like it.

    • MangoCats@feddit.it
      link
      fedilink
      English
      arrow-up
      1
      ·
      17 hours ago

      Doctors “humanity” kills a lot of people, every day, that wouldn’t have died if they did a statistical matching of their symptoms to the available research literature.