idk if it is serious or not, but it is what I saw in indeed newsletter today.

    • anon_8675309@lemmy.world
      8·
      3 months ago

      And yet somehow the tech blogs and such always scream about developer productivity. Go faster. Go faster.

      From what I’ve seen over the years, only mids care about finishing fast.

      • CanadaPlus@lemmy.sdf.org
        3·
        3 months ago

        Yes, but quality takes actual skill to measure, instead of just a diff.

        (Although I guess lines are still better than time in office as a measure)

    • corsicanguppy@lemmy.caEnglish
      3·
      3 months ago

      The guy who wrote this is an idiot, but he became so in a world where “LoC” is a metric – one that Goodhart would love, but alas.

      This is honestly the road to hell and the ~good intentions in one.

  • unmagical@lemmy.ml
    67·
    3 months ago

    Spot security vulnerabilities instantly from a candidate that can’t actually write code.

    • MangoCats@feddit.itEnglish
      6·
      3 months ago

      The real trick about vibe coding is that it’s like any other management skill - when your minions completely screw the pooch, you need to be able to step in and do it for them.

    • GameOverFlow@lemmy.zip
      4·
      3 months ago

      Just ask the ai to make no failures. Just aks the Ai to eliminate all failures. Easy 10 000 dollar per year.

  • saltnotsugar@lemmy.world
    58·
    3 months ago

    I need to hire someone to take this functional 15 lines code, and like make it 200 lines of unusable madness.

    • MangoCats@feddit.itEnglish
      11·
      3 months ago

      Oh, man, I don’t know how much is Claude’s fault and how much is just the way the world has moved, but I coded a hobby project in C a bit over 20 years ago, brought in one library to render the graphics as .jpg files and the whole thing was like 300 lines of code.

      Claude “modernized” it for me, and yeah, it shows on a browser as a PWA and it’s working correctly (this time, via Opus 4.6 - first time I tried with Sonnet 4.0 it couldn’t even make it work correcty) - but daaaaammn, there’s like 454 files in deps, 1.4GB in the rust target folder - maybe it’s just a rust thing?

      • ferric_carcinization@lemmy.mlEnglish
        4·
        3 months ago

        Rust & cargo do more than just compile. For example, it basically has buit-in ccache.

        It is also easier to split large libraries into multiple crates, though an average project still uses more libraries than an equivalent C project. I wouldn’t be surprised if the “AI” also pulled in more libraries than needed, or has unnecessary library features enabled. I’m pretty sure that a cargo plugin for pruning unused libraries was featured on the rust blog, as a featured third-party plugin for a cargo release.

        • MangoCats@feddit.itEnglish
          2·
          3 months ago

          In C++ land, I lived in Qt for 20 years. It did… most things, so if you “just” imported Qt (or Boost or massive API environment of your choice) you could usually do most things “just” importing one or two additional external libraries. I frequently would split a system into “micro-ish-services” with each service importing one or a few of these novel external libraries, partly to isolate them so unexpected interference at least wasn’t coming from within the process, also as damage control incase one behaved badly it could be excised at runtime without taking down the larger system.

          Rust feels even more like a case for cooperating microservices, but it does seem to bulk them up fast - faster than Qt, and that’s saying something.

      • T156@lemmy.worldEnglish
        5·
        3 months ago

        All he made was some dinky algorithm. Google Bard could do that in three minutes flat smh.

      • CanadaPlus@lemmy.sdf.org
        4·
        3 months ago

        And even this improvement wasn’t universally appreciated: some people found error messages they couldn’t ignore more annoying than wrong results, and, when judging the relative merits of programming languages, some still seem to equate “the ease of programming” with the ease of making undetected mistakes.

        This guy was writing in the year x86 was first introduced, and I still feel like I see this attitude around.

        (He manages to shoehorn in a “kids these days” paragraph too, though)

      • ThermonuclearHoxha [comrade/them, mirror/your pronouns]@hexbear.netEnglish
        4·
        3 months ago

        See, Dijkstra was talking about people trying to create programs in natural language. He didn’t say not to use your natural language to hire someone else to make a formal program. This is people using natural language to hire an LLM to make a formal program, and asking LLMs is like asking people, so it’s Dijkstra-approved. smuglord

    • I_am_10_squirrels@beehaw.org
      6·
      3 months ago

      Me: I want SoaD!

      Mom: we have SoaD at home

      At home: SotA, featuring such hits as

      Sorta poisonous lo mein Let someone else bring the bombs

  • Nemoder@lemmy.ml
    17·
    3 months ago

    You know the “vibes” of different models - when to use

    Would that be a vibe-rater?

  • garretble@lemmy.worldEnglish
    16·
    3 months ago

    So I ran into my first genAI coding junk yesterday when I was on a call with my boss and as a solution to a problem we were talking he said, “hold on let me ask Gemini.”

    I felt my soul die a little bit at that point.

    But the fun part is that Gemini first didn’t provide a good answer.

    And then on the second go it also didn’t provide a good answer.

    And then on the third attempt we decided to table the issue for the moment because prompt coding on a call was taking longer than I think he expected.

    I really disliked that experience.

    • Petter1@discuss.tchncs.de
      5·
      3 months ago

      But they use curser and cloud (probably meaning claude as it is used in curser pro)

      Isn’t claude code considered SOTA vibe coding right now?

      And i understood it like you can choose what fancy tool you use. The vibe manager who generated this, probably, just told their LLM to use SOTA AI coding tools in their prompt for this job description.

      • MeetMeAtTheMovies [they/them]@hexbear.netEnglish
        3·
        3 months ago

        The SOTA changes every couple weeks, but Claude’s been very dominant for a while, yeah. There’s currently a lot of hype around GPT-5.4, but even then there’s a caveat that Claude is still better at UI.

        I just personally find Cursor to be pretty buggy. But I think the Replit mention is more of a tell that someone vibe codes but doesn’t actually code. It’s been advertised to people as a way to build end to end apps without any coding experience. And to be fair, they’ve done a good job of building on the past decade of work in the Typescript community to make an entire app end to end type safe and therefore checkable by the compiler. Convex has done something similar in a way that I prefer and in my experience LLMs are very good at working in Convex projects as well.

        Really at the end of the day I was just being pithy. Kind of poking fun at how much of a moving target SOTA is.