• josefo@leminal.space
    link
    fedilink
    arrow-up
    26
    ·
    6 days ago

    The tech lead at my team started using AI to do code reviews he can’t be bothered to properly do himself. His suggestions during reviews are now shit. I hate the future. I’m seriously thinking on taking a leadership position just because how much I hate this dynamic, to shield others and discourage AI usage from a higher ground.

    • CandleTiger@programming.dev
      link
      fedilink
      arrow-up
      2
      ·
      3 days ago

      You need to tell him that. Seriously. Pick some especially bad example to point at, and come to him with, “Hey Bob, I used to get real value from your review comments. I could tell you were thinking about what to say and it helped me to produce better code. Now it seems I am mostly seeing LLM-generated junk like this one that doesn’t help anybody. This isn’t an improvement, can you go back to the more helpful way you used to do things?”

      • josefo@leminal.space
        link
        fedilink
        arrow-up
        2
        ·
        2 days ago

        Eh, I get you, but the guy is my lead, and I’m a senior member. There is a bit of office politics involved here. My corporate-fu is not that good. Also there is a push to use AI tools from the top of the chain of command. I hate this, so much, but I need bring it in a more casual and friendly conversation.

        • CandleTiger@programming.dev
          link
          fedilink
          arrow-up
          2
          ·
          edit-2
          2 days ago

          Say it however you want that works for your relationship.

          What I meant to be saying there was — if nobody tells him his review comments aren’t helpful anymore, then he probably won’t know.

          I’m speaking from the perspective of somebody who spends like 1/2 their time or more doing code reviews, if I’m wasting people’s time I would want to know it

    • AnotherPenguin@programming.dev
      link
      fedilink
      English
      arrow-up
      4
      ·
      6 days ago

      Using AI just to be lazy is by far the worst use case. It should be a tool made for speeding up repetitive work, and its output (if important) should always be reviewed by humans.