• nark3d@thelemmy.club
    link
    fedilink
    arrow-up
    6
    arrow-down
    1
    ·
    2 days ago

    Agreed. An agent only multiplies what’s already in the codebase. If you’ve got tests, clear boundaries and the rules written down, it genuinely flies. If it’s the usual undocumented mess, you just get more mess, faster. Which is probably why the shops that dodged that groundwork for years are getting the least out of AI now. There’s nothing solid under it to build on.

    • slacktoid@lemmy.ml
      link
      fedilink
      English
      arrow-up
      16
      arrow-down
      6
      ·
      2 days ago

      But did you read the article? What does your comment add to what the article is trying to say?

      • cecilkorik@lemmy.ca
        link
        fedilink
        English
        arrow-up
        11
        arrow-down
        12
        ·
        2 days ago

        Excuse me for having a little fun. Didn’t mean to interrupt your serious business day.

        • Avicenna@programming.dev
          link
          fedilink
          arrow-up
          2
          arrow-down
          2
          ·
          2 days ago

          lol seems like there is a breed of users who believe that jokes on discussion posts are beneath lemmy and conversations must be kept in topic at all costs.

    • erebion@news.erebion.eu
      link
      fedilink
      English
      arrow-up
      1
      arrow-down
      1
      ·
      1 day ago

      Hum, pralines and dick does not actually sound all that bad.

      Still, I don’t want LLMs…

  • flatbield@beehaw.org
    link
    fedilink
    English
    arrow-up
    6
    ·
    2 days ago

    Basically agree. AI helps but it still needs an expert to get the job done. There are so many times AI just does strange stuff and you have to know enough to know when it is just wrong. I think we all constantly encounter that.

    • HubertManne@piefed.social
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 day ago

      yeah I generally tell people to use ai with things they know very well before trusting it on things they don’t know so well. It can perform real well for awhile and sometimes its just a little off but sometimes it just straight up makes stuff up.