This is why you should not install any of the vibe coded apps that get advertised in here regularly. You’re just creating a liability for yourself.
@[email protected] given the new post tag requirements, please edit your title to include [AIT].
I shall share a personal experience and opinion, I’m telling y’all early so you can skip it if you want.
I finished several projects with AI assisting me in my work. As someone who has masters degree in AI (done before current AI craze) I really wanted to see the new thing in action, even though I knew it was over-advertised and over-hyped.
AI is a good tool for a programmer in the same sense as Google Search is a good tool for a programmer. And just like haphazardly copying code from stackoverflow doesn’t make you a good programmer, neither does AI. Anyone who tries to either have agentic AI write everything for him, or just copies code from LLM will eventually end up with confusing mess that even experienced programmers will have hard time to work with.
AI is good for quick questions - what is the data type, what is syntax here and there, what library provides specific feature… but terrible at making, expanding and managing large projects. Few years back I would tell my peers “just google it, you will get better results” but sadly Google Search entered such a terrible enshittification phase even before AI craze, that in my personal experience it’s faster and more accurate to ask LLM most coding questions.
Purely vibe coded apps are abandoned because the proper answer to “can a vibe coder add feature X to his app” is sadly and expectedly “fuck you”. My current project - Baba Yaga was created with AI assist, by treating AI like Google Search and occasionally as a junior dev to re-write boring parts (that could have been done with a script probably). If all LLMs got shut down tomorrow, my workflow would barely change, I would just start complaining about current state of Google Search a bit more.
Thank you for Baba Yaga, anything starring Baba Yaga gets my full endorsement. (I can fix her, I just know it!)
It’s an esoteric knowledge and tools app. My wife loves esoteric stuff so I combed through several old alamachs on magic to build this.
deleted by creator
My coworker said it best: “Anyone can build an app now, but nobody wants to maintain one.”
In a shock to absolutely not a single person who has had to “hand craft” and maintain code… Its hard enough maintaining shit you wrote last week let alone adapting or collaborating on stuff you didn’t.
… so people who shit out recycled code from other people passed through a randomization algo are totally lost from step one. And easy come… easy go.
Oh I need to maintain this? Oh the magic box can’t do it? Technical debt?! Oh, I’m bored now… guess I’ll go inject my brilliance somewhere else.
Discipline is part of the recipe for brilliance. So often, I find myself hearing of people’s problems and I realize that the problem is a manifestation of your poor discipline. It’s not necessarily that you did something wrong, misconstrued requirements or misconfigured procedures, no… it’s that you didn’t actually try to read the error message, look at the docs, catalog your technical debt, make a phased rollout plan, decide on what tests you’ll need, write a well bounded scope, … no. These “brilliant” people are fully capable of doing this, they just aren’t disciplined enough
You just stuck your balls to the wall and said “boss, I think it’s cold outside.” How about you go open the fucking door and check?
/s… I got a little carried away there.
Interesting because i think i identified the same problem as you but i think of it as delusion. A lot of people (most people?) honestly believe that being smart means figuring things out with little effort. But all the smartest people ive ever met are extremely well organized and hardworking BECAUSE they’re so smart. They’re able to see the big picture and have a very sharp insight that problems are solved with an organized well planned approach, which often involves a lot of tedium.
Smart people aren’t bored by that, they see how the tedium ties directly into success/solutions/rewards. Dumb people really believe that they can be smart by divining solutions and that could not be further from the truth
I feel that. Theres a strict requirement of fortitude in this industry. Fighting against an unknown bug/challenge is draining and requires admitting you lack knowledge and being willing to persevere in the face of a fruitless result. Shits hard and will beat you down if you let it.
Yeah. I’m currently in a situation where we picked up a new hire and she keeps dropping these problems on me. Whenever she runs into something she doesn’t understand, I get a Teams message:
Hi partofthevvvvvvvooooiiiicccceeeeee
It’s happening again 🤦♀️
The numbers don’t look right in SLT and the numbers matched yesterday, I don’t know…
They were fine yesterday, then they were all wrong all by themselves. Like magic.
Can you call real quick?
By this point, I’m already fucking irritated and I haven’t even responded yet.
- What do you mean by SLT? What the fuck is that, a dashboard?
- What are you comparing the numbers against to know they’re wrong?
- Did you create a minimal reproducible example in SQL, to demonstrate the issue?
- Did you halfsplit the problem by checking the Bronze tier data for the discrepancy?
- Did you open a ticket?
- And no, no I can’t fucking call. Please type the problem you’re actually having so that I can help you without spending three hours on the phone.
… she proceeds to create the ticket. MRE is a bunch of pseudocode referencing nonexistent tables with footnotes like, “this is the kind of tests we should check.” Oh, but you couldn’t be bothered to write the fucking test?
At a certain point, the ticket just falls into chaos:
- Her: The other team is comparing against their own dashboard, that’s how they know there’s a problem.
- Me: Please get the configuration options necessary to reproduce the calculations in their dashboard.
- Her: Here’s a list of the values they’re using to filter users.
- Me: That list counts 36. Your prior screenshot said the filter has 17 selections.
- Her: Jose said that’s the list of team members. The dashboard filters to team members.
- Me: Okay. I asked for the dashboard filters, not the team members.
- Her: Jose says they’re both the team members.
- Me: …
So after explaining (10x) that, to troubleshoot the dashboards discrepancy, we actually need the filter values from the dashboard… we end up on a 3 hour call, because none of this is fucking landing.
So here I am doing other people’s jobs while I’m already busy enough from my own. I get so burnt out sometimes.
I’ll admit I let out a pained chuckle while reading that. We all have at least one like that who, almost like a savant terrorist, can pick the worst time after being ‘just dangerous enough’ to inflict maximum pain for minimum effort. And then youre left with all that energy from exasperation just bouncing around inside.
I try to not be hostile towards AI-assisted FOSS projects, but I remain incredibly wary of it for this reason (it being abandonedware) and because if the dev themselves don’t know why they have a piece of code in their project how can I trust that there’s not some obvious security holes. Like yes, it’s FOSS, “so you can check it yourself,” and if I’m seriously considering using the software then I will do a cursory code-review. But I do enough of that in my day-job (and at least I get paid for this), I don’t want to do it with my hobby too. I’m just so tired of all this AI/LLM nonsense to the point where it’s been months since I’ve added anything to my little homelab or have even bothered checking out any of the new projects coming out
Same is true about non-slop projects
Who woulda thought people wouldn’t keep up with something they were never really invested in to begin with… except for pretty much everybody.
All things must pass. All things must pass away. ~ George Harrison
I look back over the years when I first discovered there was a thing labeled a computer as a yongster. I remember the curmudgeons, scoffers, and nay sayers talking about how this ‘fad’ called ‘the computer’ and subsequently ‘the internet’ was all just a waste of time, and that all of us nerds and geeks would soon see the stark error of our ways. I even had an employer tell me, ‘Buy something off the internet? <scoff> No one will ever buy anything off the internet!’ and then he launched into a ‘Why, back in my day we …yadda yadda yadda’ diatribe.
I look back and wonder how far along we’d be in solar power infrastructures had a lowly peanut farmer not been religiously and hatefully ridiculed for installing solar panels in the White House. Sure, they were inefficient but it was the concept, the idea, that yes this can work with some further tooling and technology. I look back even further in history and pick out Fulton’s Folly and how he was lambasted for his stupidity, thinking he could put a steam engine on a boat and make it a viable form of transportation. It became a huge boon to commerce and travel up and down the Mississippi, and subsequently spread to other areas. I think about our early steps into space travel and how there were massive amounts of vocal opponents to this waste of energy and tax dollars. Yet, even to this day, we still reap the rewards of that technology in our every day lives. So much so, that we never stop to think about it.
I’m not here to say that AI in any of it’s many forms is the golden goose or the egg. It is fraught with problems, some of which are glaring, and it needs some heavy governmental regulation. I, like many others, have concerns about AI coded projects and the safety and security thereof. However, this knee jerk reaction to anything AI reminds me of so much of history, in that, the once disdained has now become so common place, as to be taken for granted.
Computers make money. Apple, Google, Microsoft, etc all proved that. They can sell you products that people felt like did things for them. It didn’t make infinite money.
How much money does ChatGPT make? How much money does Grok make? How much money does Copilot make? How much money does Claude make? LLMs and generative AI don’t make money. If they did, AI CEOs would be boasting about the massive profits coming in from AI.
LLMs and generative AI don’t make money.
I would agree with you. At this juncture AI a loss leader, much like putting a man on the moon was a loss leader. How’s that technology benefiting you now? Significantly. I’m in no way glossing over the issues with AI. It has real world problems, and needs intervention, serious intervention.
AI was already doing good before ChatGPT and LLMs like folding proteins which shaped human history. I am really drilling down on LLMs and the sell to CEOs that generative AI can replace employees or that it is worth transforming the economy over. It’s not. Computers had a dotcom bubble which made computers useful by creating the infrastructure for engineers to be produced by universities and companies to use the networking tech. Its not like video games were keeping computers alive. See: Nvidia before bitcoin and ai made them the most valuable company ever
LLMs wont be making anyones lives better any time soon. AI already did things for humanity before them. Computer neural networks existed before AI. It was called machine learning. Member the ML days before tech bros called it AI? I do.
AI was already doing good before ChatGPT and LLMs like folding proteins which shaped human history.
Absolutely. AI is not really a new phenom. ChatGPT and LLMS are.
Member the ML days before tech bros called it AI?
I certainly do too.
“IA” have very few applications besides faking things. It fakes someone having read that mail, it fakes having wrote that mail, it fakes art, it fakes “helping you”, it instead do fake job for you.
It’s the “IA” spite can look too spiteful, but there’s a key difference I think between “IA” and actually useful technologies: A computer helps you do things, not only work, better and faster, “IA” do it for you. You don’t “learn” to use an “IA”, you do have to learn to use internet and a computer.
“IA” is less akin to something like a computer and more like NFT, Radium Watches, etc. “Innovation” for the sake of selling instead of progress. Has is uses? Of course, but it create far more problems that it tries or even cares to solve and it’s inclusion on everything just for the sake of selling just screams like plastic, radium, Teflon, lead on gasoline, etc. The promised miraculous new invention. Sooner or later we are going to pay for it. Again. All of us.
Since we are in a technology forum, a few quotes:
“Frontier AI models have given defenders the ability to find and fix vulnerabilities in open source software at a speed and scale that were never possible before. That’s an enormous opportunity for defenders, and Akrites ensures we seize it together. Maintainers deserve a coordinated partnership, not a flood of reports. AWS is committed to securing the projects our customers depend on and building this shared infrastructure alongside the community.”
– Matt Wilson, Vice President and Distinguished Engineer, Amazon Web Services
“Open source projects collectively underpin much of the internet, and the existing model for coordinated disclosure has been outpaced by how quickly AI can now find vulnerabilities. Getting ahead of that requires the industry to coordinate on findings and get fixes upstream before they’re disclosed and exploited. Efforts like Akrites drive this level of coordination at the scale and speed this moment requires.”
– Jason Clinton, Deputy Chief Information Security Officer, Anthropic
“The software supply chain is only as strong as the upstream it draws from, and we see how thin that layer really is. As AI finds more vulnerabilities, the industry will rush to patch them. Without coordination, those fixes will fragment across different patches and forks, and maintainers who are already overwhelmed, unreachable, or haven’t touched a project in years. Akrites gives the industry one coordinated way to fix vulnerabilities upstream before they’re exploited, with maintainers still in control. Now the work is making sure there’s always someone on the other end to catch them.”
Sooner or later we are going to pay for it. Again. All of us.
Yes, we will pay for crawling out from the primordial ooze billions of years ago. Everything is finite.
“IA is very good”
- IA Corporation
I don’t know chief. I get your point, but quoting the people who benefits the most out of it seems like a conflict of interest.
DuPont said Sprays weren’t that bad for the planet, backed it up with a DuPont financed “research” and used DuPont financed media.
So, here is another quote:
Dario Amodei — quote on opacity: “People outside the field are often surprised and alarmed to learn that we do not understand how our own AI creations work. They are right to be concerned: this lack of understanding is essentially unprecedented in the history of technology.”
I think is very different paying for building a society more complex than what we can understand and 10 million deaths by lead poisoning because some rich family preferred even more money over the life of everyone else. But you do you. The way you think “we will pay wether we like or not so we better make it count and take the biggest debt we can” is what have the world rotten as a whole.
Really, after all this years of computer technology and the internet, what good came out of it? That it can outweigh the bad.
People are dumber and misinformed. Social media is a cesspit of fakeness and product advertisements. Software improves profitability and takes away jobs. Unparalleled potential for mass surveillance.
I can think of hundreds of innovations and good. Take just the medical field. Huge advances in attending the sick, the diseased. Yes, all technology wields a double edged sword. When the first Ford rolled off the assembly line it was a huge boon to travel, tourism, commerce. What were the downsides? Well, it’s noisy, pollutive, the processes to extract it’s fuel is very volatile. Yet, you get in your car and go to the grocery store, work, or even vacation without thinking about such things for the most part. The efficiency, the decrease in pollution, emissions, etc. are somewhat a thing off the past. Yes, there are massive improvements we can make, especially in renewable resources and electric vehicles.
Those who pine for ‘the good ol’ days’, usually do so with thick rose colored glasses.
Yes Ford. That guy was pretty sweet. When the assembly line was first implemented by him. An innovation that eventually lead to unchecked industrial growth and waste production, greed intensified.
On a surface level. Yes there were many good innovations, or rather many good business opportunities. On one hand the health care is better, on the other hand no effort seems to have been made to prevent people from becoming sick in the first place. It’s a catch I guess.
Anyway those innovations will become annulled when no one will be able to afford it.
Ford didn’t create greed. Computers and the internet didn’t create hucksters, neither did it create gullible people blown around by the wind without a compass or direction. Fools and their money have been parted for millennia.
no effort seems to have been made to prevent people from becoming sick in the first place
I would somewhat disagree with you in that no effort has been made to keep people from being sick. That’s a pretty bold statement. However, a large portion of the medical industry (which, yes is subject to greed) is not really about the curative and more about the maintenance. You can lead a horse to water, but you can’t make it drink. You can instruct people on healthy living which will extend their life and the quality thereof, but you cannot force them to do so. That is, and has been a huge issue. People line up at the hospital in large instances because they did not even attempt to lead a healthy lifestyle. They are an encumbrance in a way, because those who do live healthy lifestyles are penalized for those who don’t.
Without being overly dramatic, I can confidently say, that if it weren’t for medical advances, I would probably not be typing these words. I did everything I could to live a healthy lifestyle, but suffered a TBI in a fall from 2 stories up. I have a medical polymer implant in my right frontal lobe due to cranial damage. They scanned the hole in my skull, and 3D printed a replacement. Jack’s a doughnut, Bob’s your uncle. I’m 71 now. That’s pretty damn awesome in my book.
I would somewhat disagree with you in that no effort has been made to keep people from being sick. That’s a pretty bold statement.
It’s high time for “bold statements”. I’ve been in both left and right, and they’re the same or atleast I know none of them supports me. This system fosters nothing more than inequality. Failure to regulate unhealthy but profitable materials and ingredients and addiction tactics away. That’s the shit the poor - soon all of us - are able to buy. There’s 20 chemicals in a simple product (they don’t even call it food), sold with a plastic wrap that is gonna go around the world and come back inside our brains. That’s why, just one example.
All this to say if there are advancements using computer technology on this, they’re nowhere to be seen making a difference. So what’s the point…
You can instruct people on healthy living which will extend their life and the quality thereof, but you cannot force them to do so.
As I keep saying poverty is correlated with sickness. Poverty of mind too. The internet didn’t solve this, far from it.
Oh and the number these data centers are going to do to the environment? Why do we need thousands of them? If we look at who’s moving around and what kind of laws world governments are enacting… it’s not gonna be good in a thousand years…
if it weren’t for medical advances, I would probably not be typing these words
I’m happy it worked out for you.
The internet didn’t solve this, far from it.
The internet didn’t cause it either. Poverty and poverty of the mind has existed for millennia. It is sad to me that we do not help those in need more than we do. I feel we have a moral obligation to help our fellow man when he is in need, no matter who they are or how they came to be in need.
it’s not gonna be good in a thousand years…
I truly believe that given enough time an technology, man can achieve pretty nigh anything. We’ve witnessed this since the dawn of time. It will take a global effort tho, because we are all inexorably tied together on this planet. No man, no country is an island. An example of this was when we banned the use of Chlorofluorocarbons because we were eating a hole in our ozone and ionosphere. That was a global effort, and it worked. We just need to move past our short shortsightedness and greed. That’s always been the stumbling block.
I don’t have all the answers my friend. I do have a lot of unanswered questions. It’s just one old man’s opinion who’s seen a lot of shit and lived a full and rather colorful life. One opinion in a vast ocean of opinions.
I often wonder this. I love computers and the internet but when it comes to quality of life I don’t see much imporvement over when I was young and the world was still analog. I mean I would not want to live in a time before electricity and definately before plumbing and sewer. a nice metro line is great and well as geared bicycles. libraries to. can’t really say much from the computer age really is all that great.
Computers have been a mixed bag
Entertainment is better.
Education is far better. (you can learn about anything you want right now for free)
Racism was on a slow decline. (communication, education)The economy is far worse The job situation is worse.
I’d say cars are better, being more efficient, but the SUV loophole fucked that.Yeah I can’t even say that. There is more entertainment and its a lot more accessible. Better special effects are great but that is so low on quality of life things I don’t care to lose it. Education is kinda the same. Not really better but more access to information but less information is high quality as a percentage of what you have access to. Honestly cars themselves are another problematic technology to begin with.
Trying to remember how the world was before computers and the internet. It was really hard to look up information yet that you didn’t have in your own home. You had to hop on the bus and go to the library searching through several books. That’s one Google search today. You hadn’t had the access to music, films, and so on. You can listen to nearly every modern song on Spotify versus those few CDs you had on your home or the songs that were playing on the radio. If you want to watch a movie you can do that. You do not have to wait until it’s showing on TV with at breaks or go to some kind of rental store. You want to go somewhere, just fire up Google Maps, versus buy and paper map, figure out where you are, and still get lost. Global communication is free. Just remember how expensive long distant calls were and how you lost contact to people who moved away.
The internet and computers really have made everything easier.
No absolutely not everything is on spotify. And Google is not a search engine anyway. We gave them the privilege of their brand becoming a verb and now they’re a corporate surveillance monopoly. We absolutely botched it here. Same with facebook.
We can search to get a quick superficial view written by whoever and now AI vs reading through a book to get a comprehensive view by someone who studied and has a reputation to defend. One doesn’t substitute the other. The internet merely allowed for the lazy masses to pretend they could get away with not reading, which worked just as well because their boss needs his productivity/wages ratio in check.
You are so wrong, I really do not know how to respond to that. Yes, not every song is on Spotify, but you are able to listen to millions of songs there. That is more than your local record shop was able to stock
I’m wrong because you say so. Lazy.
Open access to information is one thing I love about the internet, I can find information (of varying quality) about anything I’m interested in without having to look through a library or get a massive encyclopedia
Some people want to be programmers. We enjoy the process.
These people just want attention. Or have been conned into the idea that with AI everything is easy.
It’s more like they want a portfolio to sell at an interview, and since entry-level hires are getting pinched by AI, they’re screwed either way
For me, it’s been super helpful to write personalized things quickly that I wouldn’t have been able to do otherwise. Are these things I plan on maintaining for decades? Hell no. But there is no current solution, this isn’t a commercial product, and I always have the code in case I want to make adjustments in the future.
these are people who “have an idea for an app” that pester devs to build their dumbass ideas.
Hiking groups are full of this crap at the moment. Even for things that a basic spreadsheet would suffice
The worst one I saw was on hacker News yesterday which was a ai avalanche prediction site, which is an absolutely shit idea and will kill someone
This is 2015 all over again where IoT hit mainstream consumers and every project on Kickstarter was a simple thing that doesn’t need Bluetooth with added Bluetooth.
I’m not surprised. If you didn’t have to will to properly build it yourself, you won’t’ have the will to properly maintain it.
There was a Ted Talk a while back (I can’t remember who) where they said “I have always wanted to give a Ted Talk… but when I got selected to do this I realized that what I really wanted was to say I had given a Ted Talk”. Meaning they want to be known as someone who had given a Ted Talk, not actually go through the process of writing and delivering the Talk.
People who write open source code do it because they like the process of writing, just like an author enjoys writing books. LLMs are for people who just want to be able to say they have written a book. People who slop-code aren’t actually interested in learning how to code. Which is a fine toy for them to play with, but not sustainable (or reliable for others to use).
At some point the project also just gets hard to maintain with AI, you burn ever increasing tokens the bigger a project gets and AI produces awful code for the purpose of maintenance by hand. Once the bugs start rolling in they realise the AI can’t fix them, they certainly can’t afford to have it constantly load the entire project as context and they don’t know how to fix it themselves and the tech debt produced is immense. So the projects get shut down.
Acronyms, initialisms, abbreviations, contractions, and other phrases which expand to something larger, that I’ve seen in this thread:
Fewer Letters More Letters Git Popular version control system, primarily for code IoT Internet of Things for device controllers VPS Virtual Private Server (opposed to shared hosting)
3 acronyms in this thread; the most compressed thread commented on today has 7 acronyms.
[Thread #47 for this comm, first seen 8th Jul 2026, 14:40] [FAQ] [Full list] [Contact] [Source code]
It’s late and so maybe I missed it, but I didn’t see the part of the article that compares the abandon rate of slopcode with the overall abandon rate. Not saying that the premise is wrong or anything, but you can’t tell how bad something is unless you can compare it with the norm.
I would guess that the key difference is that vibe coded apps can get to a more or less working state a lot quicker, while other apps are likely to be abandoned before it’s done.
Though in either case I’d always be careful with new projects. If it’s just a single guy that’s been working on something for less than a year and only have a handful of GitHub stars, I probably wouldn’t install it.
Also it’s again the false sense of security pf “if you don’t use vibed apps you’ll be fine”, making people forget basic security procedures.
I, for instance, had a service vulnerable and discontinued without noticing for months. It was something 100% made before LLM was a thing. Still had unpatched vulnerabilities and the project was abandoned. It was my fault for not checking more often is the services I host are safe or not.
I’ve been working on updating all my old software projects lately, and as part of that process I feed the source code into a LLM for review.
The amount of simple security errors, logic flaws, and code smells that it reveals is quite embarrassing.
This was all “good functional code” that’s been used internally for years. Clearly it worked well enough, but a simple pass through a LLM reviewer made it a lot more robust and secure.
I make all my own slop apps now. Bespoke crappy solutions for bespoke crappy problems. Abandmont rates are up, I can attest
I’ve found LLM’s to be pretty decent at writing one-off scripts for boring tasks. “Baby wipe scripts.” Use them to clean up the shit and throw them away.
I’ve rebuilt a few SaaS projects that I use so it’s under my control. Might not have all the bells and whistles, but it aligns with my needs better.
I rebuilt a simple Playstore task app into a multiuser fleet maintenance app for the farm. I’m not putting it in the wild, I don’t need that headache. I build it exactly for our needs and I don’t need to have to deal with users I can’t tell to fuck off to their faces when they get snotty about a bug.
But overall, this kneejerk “everything AI makes is broken” bullshit is starting to get to me. It’s pretty obvious these people either haven’t used it in the last year or so, or don’t know how to. Or they’re just performing for the internet, and actually use it all the time. I tend to think the latter.
Another person already wrote this itt, but the cost in time and money of building something that “works” is very low. That cost increases every time you need to fix something. It’s why I’ve switched to deepseek flash instead of the bigger, better coding models. For the same price as a million tokens of Claude for example I can get a hundred million tokens on flash. It takes three times as long and needs a little prodding but it’s thirty times cheaper.
Even if you’re not dealing with ballooning costs when it comes to upkeep, the present environment around ai programming is filled with perverse incentives that reduce the chance something is open sourced. Why preserve the old work and try to carry it into the future when you can just rewrite it? Why create standardized libraries and approaches to specific problems when it’s only gonna be used once? Why make it open when you don’t have time to deal with requests and bug reports you don’t care about? Why use gpl when you don’t intend to make it public anyway?
Those were all arguments against gpl and open sourcing parts of the Unix codebase too, btw.
Harnesses or agents try to address some of this by sharing improvements but that’s three layers removed from directly turning fossil fuels into cpu cycles to make the same program a thousand times slightly different for a thousand different people.
I tend to see the ai programming defense in the same way you described yourself and the “ai is bullshit” crowd. People defending this stuff generally either aren’t looking where they’re walking or haven’t had to use it long.
As a decently prolific user of ai programming, it’s turned computer code into disposable plastic wrappers. Even if they don’t persist and make a giant garbage raft in the ocean or calcify our pineal glands we still wasted a bunch of energy on them.
I don’t see that it increases the costs. I’ve written software and PMd other software builds in a previous life. Software has bugs and either I fix it slowly because I have to wait for winter to have time, or the AI does it while I drive a tractor for a couple bucks in tokens. AI can architect fine now and if you use your head, you can cross-check the codebase to ease maintenance with other LLMs, then come in and give it a final QA yourself.
I have a bugtracker I build into any software I build, an agent watches for new entries by users and does some preliminary work before bringing it to my attention and then every day I get a report that I can say what gets worked on while I have coffee. Honestly, I don’t care if the agent decides to refactor the whole mary-anne, it pings me perioidically in Matrix and I steer it around like I do my hired men asking which field to cultivate next.
At this point I have almost entirely vibe-coded software that’s been dogfooded for almost 2 years that works great and massively improves our operation. And I have a dozen other ideas ready for me to give some attention to in order to get them off the ground. It’s an exciting time. I love it.
It’s definitely the early pc era x1000.
For better or worse.
Yeah same. I make loads of little things to bodge my own problems but would never be moronic enough to try and capitalise on something that took 60mins to make.
I like Cory Doctorow’s take: AI is good for single-use, personal code to solve an immediate problem, and terrible for long-term, production projects. I imagine there’s a bunch of neophytes out there who use AI to create their first project, find out that github exists, and thinks someone else must be having the same problem they just solved, so why not release it to the public?
Exactly. Oh I have this small problem, or solution I want to solve. Great I can put something together quickly and move on with life. I am not selling it, and it’s not even needed for ‘open source’ because its often incredibly niche problems that I am trying to solve for, that I wouldn’t be able to do elsewise.
