• ozymandias117@lemmy.worldEnglish
    98·
    1 month ago

    I can certainly understand why one of your libraries was bothering you if you’re merging 250,000 lines of AI generated code in a month.

  • comfy@lemmy.ml
    81·
    1 month ago

    Programming is one of those skills and industries that is accessible enough that basically anyone can do it, but you will run into trouble later if you’re doing anything serious without learning how to do it well. There are hundreds or thousands of ways to make something work, but if it’s an unmaintainable mess or you don’t even understand how it works, then we end up with our financial institutions running COBOL in 2025. Good luck when regulations change. Have fun when your operating system becomes unsupported and you have to replace the underlying dependencies. Hope your boss doesn’t sue when they have to hire people to rewrite your hackjob.

    And these were all already problems before AI code came onto the scene. We had the programming equivalent of script kiddies, people who would blindly copy and paste code from web searches without even reading the date or the comments saying “this is bad and this is why”. But this probably makes it even easier to do, and possibly harder to spot. Combine this with how many universities don’t even focus on lower-level languages so you get plenty of people who can’t understand how to fix any of the trickier errors in their code. And that’s not to say everyone has to be able to, but it’s a problem when so few are able to. So these programmers are unlikely to know if the code has problems so long as it passes their tests, and unlikely to know how to fix those problems when they become clear.

    Automation tools are good ideas for assisting and detecting possible mistakes. They’re not good at generating that much code. In fact, that amount of code in that amount of time is suspicious, hinting that it’s unlikely to be well-designed, maintainable or efficient.

    • pinball_wizard@lemmy.zip
      14·
      1 month ago

      This is a great write-up. And a bit generous to the “developer” in question.

      I’m not entirely sure I’ve written 250,000 lines of code yet, in my entire decades as a professional developer. If I have, it’s a near thing.

      Not to brag, but I can reuse existing libraries and get many things done with 5 or 10 lines of code.

      It’s hard to crack 250,000 when 5-10 lines solves each of my employer’s problems.

      And this young developer supposedly solved one problem with 250,000 lines of code.

      After giving it some thought, I’m like 90% sure this is just a parody post. Even AI can’t be that bad at this, right?

      • OctopusNemeses@lemmy.worldEnglish
        8·
        1 month ago

        This kind of thing is real. Newbies don’t have experience to know how important architecture is. They continuously mash code without thinking too much. Generative machines have made the problem orders of magnitude worse. It used to be limited to the amount of garbage a human could mash into their keyboard. Now it’s like generated art. People churn out infinite images. They haven’t actually drawn the image themselves.

      • MoonMelon@lemmy.mlEnglish
        7·
        1 month ago

        This is just some library too, not their main application. I know “lines of code” is bullshit but just for reference I looked it up and apparently curl is ~180k lines of code. I can’t imagine how crufty this fucking code must be, assuming this is even real because it seems too ludicrous.

    • Gumby@lemmy.worldEnglish
      9·
      1 month ago

      I agree with your main point, although I think your example of COBOL being used to this day in financial institutions is actually the opposite problem. The guys that originally developed that shit were damn good programmers, but they were severely constrained by the available hardware, limitations of the language, etc. So they had to get really clever in order to make these massive, complicated systems work. In my experience, those really old legacy systems tend to be rock solid with near 100% uptime and almost no errors. They’ve never been rewritten because doing so would be a multi-year effort costing millions of dollars, and the end result would be a system that is most likely slower, buggier, and has less functionality.

      TLDR: The old COBOL systems are unmaintainable messes not because of incompetent developers, but because the limitations of the available technology when they were originally developed forced a bunch of really good devs to have to get extremely creative and hacky with their solutions.

      • merc@sh.itjust.works
        3·
        1 month ago

        Even if the original developers weren’t rock stars, the codebase was feature-complete in the 80s or earlier and they’ve spent the decades since then eliminating nearly every single bug.

        The real issue is that it’s expensive to add new features compared to a modern codebase , and it’s very difficult to find COBOL programmers in 2025.

        Eventually a bank is going to take the gamble and rewrite everything in a modern language, and designed with modern tech in mind. But, it’s going to be a huge gamble. And, I can guarantee you, they’re not going to be vibe-coding it.

      • comfy@lemmy.ml
        2·
        1 month ago

        Good correction, and I definitely didn’t mean to suggest those programmers were unskilled. In their case, and like you said, the maintainability issues were often a result of technical limitations.

  • Malix@sopuli.xyz
    75·
    1 month ago

    now ask them to maintain the 250k lines, probably fine for rew more commits, but after that? Oh look, they left the company for the next ai-nonsense-startup.

      • Malix@sopuli.xyz
        17·
        1 month ago

        I hate how much I love this reply.

        At the end of the day: IT-man return to monke. Please. Please?

      • Alexstarfire@lemmy.world
        13·
        1 month ago

        You made me wonder how many lines our product contains. Looks to be around 600k total right now. Granted, that’s just the front end. It includes comments, blank lines, and lines that are just brackets and such. Also includes some dev only code. So, far more bloated than the actual code. Excludes code from any external libraries we use though.

        I don’t have an easy way to see how many lines our backend is. A large portion of the files aren’t for our front-end and I don’t feel like figuring it out. Couldn’t even tell you if it’s more or less code than the frontend.

        I’d be extremely worried if someone added or re-wrote 250k lines of code in our code base in one month. We actually have regulations to follow.

  • floofloof@lemmy.ca
    66·
    1 month ago

    Translated:

    High-schoolers are even cheaper and easier to exploit than new grads, and if I don’t care if they know nothing as long as they can prop up our crappy app just long enough for me to sell the company, pocket a bunch of cash, get them all fired, and move on to my next scam entrepreneurial venture while preaching to people about being an innovator and a job creator. Maintenance is for whichever sucker ends up holding the shit bag, but who cares? I’ve got mine.

    AI coding is just the latest spin on this age-old practice.

  • Omega@discuss.online
    58·
    1 month ago

    If this is serious, that entire codebase is fucked

    And I seriously don’t trust ai with anything mildly more different in scope than what is always shown

    • Treczoks@lemmy.world
      23·
      1 month ago

      Well, what he did was bringing something into the code base that might blow up the whole company one day in the future. Because what he didn’t do was thoroughly review the code that the AI made.

    • bitjunkie@lemmy.world
      16·
      1 month ago

      Yeah like whoopty doo you created 250k lines of cruft that someone competent will have to sift through later

    • Phoenixz@lemmy.ca
      12·
      1 month ago

      250K lines of code in a month means about 10k lines per day.

      For an 8 hour work day (since they donchild labour, it might as well be 16, but let’s keep it simple) that is about 1000 lines of code per hour, so about 20 lines of code per minute. Give or take

      Unless you trust the output of AI implicitly without checking anything, ever, there is no way on this earth this can be done by a single person.

      Then, an actual senior developer would be required to evaluate each method he wrote, but I’m sure this 10 year old child with zero experience will suffice

      So basically, this guy just uses a child to tell chatgpt similar to vomit out text that likely may not even compile, let alone do what it needs to do correctly, with the right security protocols, all with the underlying infrastructure.

      All of this is bullshit and that CEO should be arrested for child labor

  • drolex@sopuli.xyz
    51·
    1 month ago

    They’re going to take your job.

    🤓📚🤚🦋 Is this an empathetic message?

    I wonder why everyone hates CEOs

  • stingpie@lemmy.world
    47·
    1 month ago

    From my experience, being “good” at vibe coding is more about being unable to detect flaws in AI generated code rather than being able to code well. Add AI to the workflow of someone who actually understands scalability and maintenance and that won’t be able to get past a couple functions before they drop the AI.

    Also, assuming this kid gets weekends off, he would be writing 12k lines of code each day. I don’t think the average programmer could even review that number of lines in a day, so there’s likely no actual supervision for what the kid is feeding into the codebase.

    I’d estimate within four months the project will be impenetrable, and they’ll scrap the whole thing.

    • four@lemmy.zipEnglish
      29·
      1 month ago

      I, a 10x developer, can hit approve on at least 50k lines a day. 30k if you want me to also add a “LGTM” comment

    • balsoft@lemmy.ml
      6·
      1 month ago

      Also, assuming this kid gets weekends off, he would be writing 12k lines of code each day. I don’t think the average programmer could even review that number of lines in a day

      I usually estimate that it takes 1-2 hours of highly focused work to review 1k lines of code well (this is not even considering that this is AI-generated mess that probably requires a lot more attention). A typical developer is capable of ~6 hours of focused work per day (8-10 with a lot of caffeine). So no, according to my estimates at least there’s no way in hell this gets any review at all.

      • Coldus12@reddthat.com
        0·
        1 month ago

        In what world? 1k lines is a lot… Even a few hundred can take hours if everything is unknown, code is legacy, and naming is bad.

        Like if there is a line like this memcpy(ptr, src, 4 * 6 * sizeof(real));

        • What’s that 4?

        • What’s that 6?

        • Is real a float? A double?? What are we copying, where, why???

        This is a line I saw recently. 1k code is huge even if readable.

        • balsoft@lemmy.ml
          1·
          1 month ago

          Ok, sure, for low-level C/C++ code with memory management and such it takes a lot longer than 2h per 1000 lines. For business logic in higher-level programming languages it’s usually fine.

    • pinball_wizard@lemmy.zip
      17·
      1 month ago

      I believe that our combined “lines of code” “productivity” will soon reach an all time high.

      I wonder if I can make some money off the demand for cleanup that will follow…

  • 9point6@lemmy.world
    42·
    1 month ago

    Omg his company sells one of those meeting notes bots

    I’d bet everything I own that they leak sensitive information from some company within the next couple of months.

    This product will 100% have more security holes than a sieve

    … I’m starting to think I need to take up freelance pentesting

    • filcuk@lemmy.zip
      9·
      1 month ago

      All of those senior devs that got sacked will be laughing for the rehire salary increase, assuming their company doesn’t fold on the ai code house of cards.

    • temmink@feddit.orgDeutsch
      9·
      1 month ago

      As an AI native he knows how to prompt, for example to always include “don’t make errors” and “make sure to follow security best practices”. It’s really easy once you know.

  • mlg@lemmy.worldEnglish
    36·
    1 month ago

    Someone I know genuinely tried this in a test branch for a Blazor application developed at a university, and the AI introduced insanely hidden UI breaking bugs because it touched every single file and renamed variables to plural without correctly refactoring in every dependent file lmao.

    AI is a powerful tool, but throwing an entire codebase at it is exactly how you nuke your development lol. Even the latest and greatest models can’t handle complexity beyond a few thousand lines even with increased input limits. And if it’s anything proprietary or even not well published, you’re basically screwed.

    • PeriodicallyPedantic@lemmy.ca
      24·
      1 month ago

      It’s crazy to me that cursor has been out for a while now, and it’s basically a fork of vscode, and it support tool use, but it doesn’t have the refactoring vscode tools as tools available to it.

      Like there are tools out there that make sure that these kinds of changes won’t break anything and they’re just like “Naw dog, just give me access to the terminal and grep” wat.

      • MyNameIsIgglePiggle@sh.itjust.works
        7·
        1 month ago

        There’s an MCP that uses LSP (Language server protocol) which is what vscode and other ides use to navigate and refactor code.

        The problem is it trips over cursor trying to do things

        • PeriodicallyPedantic@lemmy.ca
          1·
          1 month ago

          It doesn’t seem like an inherent problem of the domain, so idk why they wouldn’t just fix that, if that means writing their own LSP MCP, or even their own LSPs for major languages.

    • Johanno@feddit.org
      61·
      1 month ago

      It is a sharp knife that if used correctly can improve your performance.

      However if you use an agent that runs through your code and changes shit randomly…

      It is like taking the knife strapping it on a water hose and turn on the pressure.

      It may cut through the things you want. It also may go crazy and kill everyone in range. You don’t know.