Submitted 5 days ago by 
rimu@piefed.social@piefed.social to selfhosted@lemmy.world
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.
Vibe coding a simple project is easy, but a crapshoot, at the current state of LLM development. Vibe maintaining anything at all is basically impossibly currently, you need a competent developer for that.
I agree that people cannot vibe code well unless they are a developer. Knowing the difference between slop and using a tool to automate bulk writing code is crucial at the current state. And I don’t ever know if it’ll get better because you need to know why you want to build something someway.
And I don’t ever know if it’ll get better because you need to know why you want to build something someway.
The major issue I’m seeing with junior developers at work is that they trust that the AI will always do things the correct way, and don’t question its approach.
To get decent quality output out of an AI model, you need to have critical thinking skills, at least basic knowledge of the overall architecture for whatever you’re trying to build, and enough knowledge to question the model when it does something wrong.
Blindly trusting AI is why so many old security issues are coming back - stored/reflected XSS, SQL injection, exposing databases directly to the internet with no password, things like that. Newer frameworks mostly got rid of them, and now AI is bringing them back. It’s a fun time for red teams at least.
Disagree. It’s perfectly viable. I’ve maintained several projects for over a year myself
Are these projects… in the room with us right now?
Sounds interesting.
Can you link those projects please?
Are you maintaining them for your own use, or do they have other users who you are supporting?
Phantaloons@piefed.zip 5 days ago Oh here we go
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.
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 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.
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 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. 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.
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.
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
rimu@piefed.social@piefed.social 5 days ago I made the mistake of installing Starling recently, not realizing how it was made. I contributed a PR to it, write a few issues describing the bugs, and since then there’s been absolutely no activity from the creator.
That’s fine, they are under no obligation to work for free. But I wouldn’t have installed it if I knew it was abandonware.
Seems like your PR was merged by the creator? If you are mad that the creator isn’t doing anything with THEIR OWN project, fork it and fix it yourself… No need to get pissy and make a full complaint post in here about it.
It doesn’t sound like OP is mad at the creator, but annoyed at the increased number of projects that are abandoned
It’s hard to judge the longevity of a project, and LLMs can make a project look more stable and professional than it is. It’s fair to feel annoyed if you mess up that call and move your workflow to something that gets abandoned.
No one got “mad” or “pissy”.
Phantaloons@piefed.zip 5 days ago Disagreed. You should blast and air everyone’s embarassing trash as loud as possible so no one misses it.
Are there any obvious signs of it being vibe coded that I’m missing?
In my experience, projects not being very active, especially small ones by a single person, isn’t anything new that has much to do with LLMs, it was always that way for hobby projects. And it was inactive for only about a month now, with the author replying within one day before that. I have a few hobby projects myself and don’t reserve time every month to work on them or check on their repos.
rimu@piefed.social@piefed.social 5 days ago No obvious signs, nope. It wasn’t until I started using it in earnest that I got suspicious and then when trying to work on the code it became very clear.
If you have access to their git, watch out for the commit history. Check how much code each commit is introducing and/or editing and how fast they are, and how many times these big commits happen.
If you see a project with big commits in very short interval of times, it’s a sign that it was vibe coded
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.
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.
It’s more like they want a portfolio to sell at an interview.
these are people who “have an idea for an app” that pester devs to build their dumbass ideas.
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.
Not many people know that “Baba Yaga” is the real name of the song, not “Teenage Wasteland”.
Thank you for Baba Yaga, anything with Baba Yaga gets my 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.
On the flip side, if you’re vibe coding an app you should seriously consider whether it’s something you want to open source or make available publicly. There’s a social contract that comes with that.
I have 2 self hosted slop apps I build and maintain myself. I think people would genuinely get great use out of them.
…but then I’m inviting critiques and feature requests and am roped into supporting them so it’s not just a big pile of shit that wastes everyone’s time. And I don’t want to spend my limited free time making common sense improvements to improve it for others. I want to write a lazy Claude prompt with insufficient context, get it barely doing what I need, and then spend the rest of my time eating crayons and similar pastimes.
On the flip side, if you’re vibe coding an app you should seriously consider whether it’s something you want to open source or make available publicly. There’s a social contract that comes with that.
This is the attitude of an existing programmer who is using these tools. What I’ve found on here is a specific pattern that keeps repeating:
a social contract that comes with that and think there’s something strange or accusatory/interrogatory when people ask questions they think are too difficult or technical 3. Some Lemmy users have generally polite but fundamental critiques and questions the poster can’t answer or thinks must be gotchas 4. The poster has a crash out about us all being mean/unappeasable/anti-AI/luddites/Linux users/godless commies and is usually the only one downvoting comments, even ones that read like genuinely 5. The post and account are deleted
There’s a clear disconnect. You’re talking about the homelab community which is a bit different but I specifically remember someone making an accessible Android UI and being extremely frustrated at people asking for the entire code to be released, and at people saying there’s not enough features there for that poster to be looping in advertisements on a fucking home page UI.
I get the impression that primarily-slop coders on some level think they’re doing programming, because of how you can get functional prototypes of code that is way above what a total beginner can write on their own. They think having code that compiles (whatever it’s usually Python there’s no compiling) means the hard part is over. They don’t seem to understand that the questions and concerns about vibe coding aren’t moral complaints but genuine concerns about liability, running code even the author doesn’t understand, and a complete cluelessness about what they should be doing to evaluate the code besides prompting it to be “good with no mistakes”.
That Android UI project seemed like a little thing a few people could install on their grandparents’ phones. It’s normal for the author not to understand every little thing. But being totally clueless and being offended at the suggestion, being entitled to put ads in it to get 0.0016 USD per year per grandma in exchange for taking up a quarter of her screen forever, not understanding why this looks scummy, why refusing to release 60% of the code looks scummy, why half the questions are being asked at all.
Again this would not be a problem if this is now the expected norm for a significant portion of any projects you find online. A lot of projects are the first genuine effort of someone out there and they’re not perfect but they didn’t feel like the unceremonious implosion of the entire philosophical concept of personal computing.
And I’m fucking shit at writing good code and I’m pissed.
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.
Kirk@startrek.website 5 days ago 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. So the projects get shut down.
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.
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.
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.
If someone isn’t motivated enough to actually think and create something, what makes you think they’ll be motivated enough to maintain that thing they didn’t create?
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.
This is the main reason why vibe coding, even if it produces good code, is still a major problem. It encourages people with the goal of making software, but without the actual will and motivation to keep supporting that software to pump out software and publish it.
It’s like all the faceless AI-automated YouTube channels we have now. It’s not that these people had no way of doing it before, it’s just that it’s easy and might make them some money, or make them feel like they accomplished something until they get bored and move on.
There’s something to be said for convenient and easy to use things, but they’re a double edged sword, because they also directly target people with the least emotional investment to use them, as a side effect of that convenience.
but without the actual will and motivation to keep supporting that software to pump out software and publish it.
TBH, most software will never be used my many so needs no support. Also, I think lack of long-term support is not the same kind of problem. It used to be any more. Back in the day when the original author dropped support it was a major investment to get someone else up to speed. Now fixes and enhancements can be done by LLMs as well, given a somehwat competent software developer.
But in general: The newer the project and the more bells and whistles it has, the less I personally would want to make it an essential piece of my workflow.
Isn’t that no different than the millions of open source projects that have few authors, little interest and are abandoned for the next shiny thing? At least in my mind with the current state of LLMs, if there is an open source project that you want to update for yourself, you should be able to do that pretty easily.
Isn’t that no different than the millions of open source projects that have few authors, little interest and are abandoned for the next shiny thing?
The end result isn’t inherently different, but the basis is.
Someone who programs a FOSS project with their own programming skill is, by definition, more invested, and more willing to spend time making that project exist. Someone who is mostly just willing to tell the LLM to do it for them is, by definition, less invested in the project.
It is more likely that someone less invested in a project will abandon it.
At least in my mind with the current state of LLMs, if there is an open source project that you want to update for yourself, you should be able to do that pretty easily.
Sure, that’s possible, but the main concern is that most people either don’t have access to more capable models (which will otherwise require them spending money for their software to keep getting things like security patches, vs projects that have maintainers that are more invested in them that aren’t abandoned in the first place which are effectively free unless you choose to donate), and you get forks in development path. It might fit one user’s goals, but now you have, say, 100 people who all tried reviving abandonware with their own LLMs, all with different features, security, import/export mechanisms, etc.
That’s not to say it’s bad that people can use LLMs to “revive” abandonware, but I don’t think we should be encouraging people to create and publish software that’s highly likely to be abandoned in the first place.
A solid 40% of projects get abandoned, that its about double for purely vibecoded is unsurprising. Purely generated is completely unmaintainable. At least they realized it within 6 months I suppose.
M0oP0o@mander.xyz 5 days ago Vaporware is never not a thing.
I thought vaporware was announced or promised code that never materializes, or shows up much later than claimed. Often used by big companies to squash competition, who typically have very real solutions available.
M0oP0o@mander.xyz 4 days ago That’s one example, yes. My point is we like to invent new ways to call out the same shit. Vibe coded projects that get abandoned within half a year are just another example of vaporware, just a new take on the concept.
I’m generally anti-ai but this is kind of exactly what vibe coding is for.
Someone has a problem right now and there is no tool to fix their problem how they want it fixed, so they throw some shit together for personal use and maybe someone else can use it if they want idgaf.
Why would they maintain that? It does what they need it to, when they need it. Usually these tools are very basic.
Usually these tools are very basic.
If you read this community in the last weeks you’d know that slopcoders don’t stop at basic projects.
I don’t disagree necessarily, but they shouldn’t be uploading / sharing one-off projects they don’t intent to maintain.
That is a bit of an open source philosophy difference.
Is it better that everyone has open source everything so that anyone who finds the one-off useful can benefit from it?
Or is the software actually not provided “as-is” like the license states and on releasing open source software the community deserves regular updates?
I think that second option is a very entitled path. We are not entitled to the continued used free labor of a random person on the internet.
I don’t really agree. If you have a tool to do a thing, share it in case someone else could benefit, just be open about what it is.
@rimu@piefed.social given the new post tag requirements, please edit your title to include [AIT].
irmadlad@lemmy.world 4 days ago 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.
irmadlad@lemmy.world 4 days ago 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.
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.
irmadlad@lemmy.world 4 days ago 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.
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.
“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.
irmadlad@lemmy.world 4 days ago 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.
The pre-LLM-effort-was-a-filter argument holds up, but I think what effort was really filtering for was why someone built the thing. High effort filtered out “this seemed fun for a weekend” projects. LLMs just surfaced that those were always the majority.
The better filter is: does this project serve a specific audience that genuinely needs it, or is it a demo of what you can do with Claude?
What I look for now:
We build CircuitForge, self-hosted tools for navigating opaque systems (job markets, government benefits, insurance). The architecture is deterministic-first: eligibility checks, validation, and data pipelines are rule-based and grounded in structured data, so the LLM is drafting from a clean, repeatable foundation rather than hallucinating into a void. That also means we can run smaller, specifically fine-tuned models instead of throwing a frontier model at everything and hoping for the best. Smaller models run on consumer hardware, which cuts hosting cost and shrinks the privacy risk surface significantly. Humans approve before anything acts. Pipeline layer is MIT and lives on Forgejo. There’s a full devops stack, a real business model, and I use these tools every day. We’re also actively collaborating with other devs and always looking for contributors.
The people using these tools actually need them. That’s the commitment signal that doesn’t evaporate when the novelty wears off.
rimu@piefed.social@piefed.social 5 days ago Replying to this post with an AI slop comment takes some balls, mate
Ha, the irony isn’t lost on me. But the comment was mine, not generated. The project does use LLMs as a tool (that’s the point of it), but “uses LLMs” and “is slop” aren’t the same thing. The repo is public if you want to check the commit history and structure rather than take my word for it.
HackThePlanet@lemmy.ml 5 days ago We went from “everyone will know how to code in the future” to “no one know will know how to code” pretty quickly
As Linus Torvalds said, give the compiler some credit.
Who woulda thought people wouldn’t keep up with something they were never really invested in to begin with… except for pretty much everybody.
I would say that the free tiers of those coding tools got cut back so much, that some of those slop coded stuff wouldn’t keep doing it any more.
Claude is on a 5 hr timer, and you get very few responses. Qeen Code was free for a second, that was nice.
Speaking of my own slop coded project viewpoint.
avidamoeba@lemmy.ca 5 days ago As always the social infrastructure (community, user base) is much more important for the success and use value of a piece of software than the exact technology used to make it (lang, framework, helper tools).
eager_eagle@lemmy.world 5 days ago Hardly an issue with generated code. You could say the same about projects before LLMs were widely used for code generation: “most projects are abandoned within months of release”. The difference now is the scale and how some people feel about it.
Even if they weren’t abandoned, you shouldn’t use them.
Easy come, easy go
Phantaloons@piefed.zip 5 days ago Just don’t install anything new after 2022. Easy way to get actual code audited by human beings.
Same is true about non-slop projects
The only slop worth using is slop you make for yourself.
That is so accurate. I have a couple of LLM-coded applications running, either because a solution wasn’t available, or existing solutions were beyond the scope of what I need, and would idle at up to 1 GB of RAM instead of 10 MB. In situations like these, being able to get a quick solution thrown together is such a boon.
Artaca@lemdro.id 4 days ago
I think I agree. I have a few self projects I’ve vibe coded and used a few months that I’ve considered putting out there open source and if folks wanna try cool if not whatever…but that’s probably how all of those dead projects start. I’m even hosting them on my own private and updating via Obtanium because I don’t want to bother anyone lmao. Wait crap Google is gonna stop me from doing this in a couple months huh
ComradePenguin@lemmy.ml 4 days ago
Can confirm, am running a lot of services on a VPS that make my life more convenient. I prompt from my phone and get useful stuff out. I am a software engineer, so I can course correct ir when necessary. I only use opencode for this, not Hermes or Openclaw