Can you imagine the absolute nightmare that the digital world will become once major infrastructure and every other app is poisoned by AI codebases filled with vulnerabilities and nightmare convoluted setups to do basic things?
Have you even seen what Claude does, randomly, if you tell it a simple bug fix you requested didn’t work? I’ve seen it simply say “Oh, sorry, let’s try something else” and start rewriting everything - from top to bottom - trying to fit previous code in it’s limited context window so it ends up generating this abhorrent mix of code segments that do nothing but look important, fragments of the original code base, and a lot of new code that doesn’t even fix the issue in the first place.
“Doogie Howser here hasn’t even had a day of med school, but thanks to AI he’s writing 5000 drug prescriptions per day!”
“We literally found this homeless man on the street ranting about lizard people, and now thanks to AI he’s the the biggest stud at the hedge fund, making hundreds of multi-billion dollar trades every day!”
“Betty here failed out of high school and can’t even pronounce ‘nuclear’ properly, but thanks to AI she wrote the entire atomic power plant safety manual in a day.”
“Would you believe that Fred is still in a coma? Yeah, doctors say he’s ‘in a persistent vegetative state’ and ‘never going to recover after that i-beam crushed his head’, and ‘what you people are doing is both cruel and insane’. But, we hooked DeepSeek up to his respirator and heart monitor and connected some black and red wires together and he’s back to working as an air traffic controller!”
Okay.
Get him on a call with a customer to explain why their payroll is broken.
That should be fun.
Easy. Just transcribe the call straight into cursor
Should just work, right? Right?
The fallback is gonna be hilarious, the codebase rewrote by AI? With basically no considerations of business need and system capacity?
I can’t wait for the humiliating rollback
I bet you their “10x coder” can’t describe what a unit test is nor its purpose
Then again, can you even unit test AI generated slop with how often it’s rewritten?
Unit tests are exactly for code that is often rewritten, because it ensures that whatever interface still behaves the same, regardless of the implementation. This a large portion of the point of unit tests: not for testing the initial implementation but confirming that any subsequent implementation behaves the same.
In a normal scenario yes, but “vibe coding” rewrites whole swaths of code. It’s like painting detail with a bucket. Trying to keep up with it seems like a sisyphiean task
Using AI to write Unit tests is one of the few use cases I somewhat understand, but even that turns out horrible with improper supervision. I reviewed one Pull Request once where the testing was so horribly cobbled together and nonsensical that I rewrote those tests by hand (after asking the person I was reviewing to fix it twice and them only making it worse by letting their AI rewrite them)
If you want to release details to a less than scrupulous company running an AI, you can feed it that information.
The real use is generating syntax. The logic is the hard part to teach, so with an understanding of the logic behind the programming, you can tweak variables for your final product.
I’ve mostly used this to generate scripts to deploy rapidly to the latest emerging crisis, but thats from the perspective of a help desk agent with too many years of experience to still be doing it, but in a way I enjoy it. The bigger problems aren’t my problems. I escalate as appropriate, and its no longer my problem.
I digress, it generates syntax and you plug in your infrastructure variables in a file you control. Then again I may be paranoid because I’ve seen HIPAA fuck extra hard with non-clinical staff who have access to records in their job duties.
I think this was an episode of Silicon Valley
red flag number 1: measuring progress in lines of code
redflag number 2: not seeing the issue with accepting 250k lines of code generated by AI supervised by a teenager without a software engineering background
Wdym man the guy has 10 years of experience
10 years using the restroom all by themselves. Very impressive!
Professional shit generator
deleted by creator
Did you reply to the wrong comment? I don’t understand
I did. That’s why I deleted it but I guess that didn’t federate to your instance as fast as my fuckup
A vibe coder not even out of high school replaced your entire codebase
👁️👄👁️
250k lines of ai generated code means he didn’t do anything
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
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.
Yeah like whoopty doo you created 250k lines of cruft that someone competent will have to sift through later
The democratization of technology is a double-edged sword.
For every improvement in UX and lowering of a once impassible barrier of entry, we seem to inevitably gain a massive number of “eXpErTs” who can suddenly stand upon the now much lower skill floor.
Shortly thereafter seems to be a destruction of the general reliability of whatever field these “eXpErTs” flood - usually a field which used to be inherently cryptic and had complex prerequisites just to begin operation within, let alone master.
Like… it makes me almost miss when “using a computer” meant you had to understand how to browse a directory in DOS…
Because at least then you literally couldn’t begin to operate in the field unless you could wrap your head around understanding the basics of syntax.
Now you can just have an entire legion of dullards misspell or misspeak 30% of a malformed question to some random free LLM that still has trouble telling you “how many Rs are in the word strawberry,” and have it confidently fart back out a wrong answer that they will then copy-paste into a paper or article which will then be added to the pile of growing misinformation currently stuffing a frighteningly expanding part of our collective knowledge base.
One of my biggest pet-peeves right now is tech companies selling paid, proprietary “low code/no code” software as “democratic”. Especially when writing code was never the hard part of software development, it’s designing usable, scalable, and efficient data structures and algorithms.
Yeah we’re gooing to need to go back and clean up the internet from 2022-50. Because of the scam they call AI it’s only going to get worse.
The code:
I used to think this is pretty much how games were really made when I was a tiny child. I couldn’t get over how many images needed to be created to get every possibility from every angle.
I used to think that a 3D game would need to have any possible still image pre-rendered and ready, just gotta show them all in the right order depending on user input.
I watched this awhile ago and it was very interesting how they made super small games for NES.
Can we fast forward to the Hard Lessons part because it’s going to be hilarious
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.
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.
I hope he didn’t use Claude because oh boy it maybe costed more than a real developer.
There are two kinds of Linkedin posters - those who are open about being trolls and those who aren’t.
How could someone ‘joke’ about this? Its not funny
it’s not funny only if it’s your job to clean up after them
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.
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.
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%40% (edit: okay, 40% after hearing some anecdotes, haha.) sure this is just a parody post. Even AI can’t be that bad at this, right?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
curlis ~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.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.
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.
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.
