There is a new kind of task for software engineers these days. A client calls, asks for a "small refactor," and sends you 100k lines of AI-generated spaghetti.
And this is great! This is something we can work with.
Any experienced engineer can look at a codebase like that and quickly see what to refactor, where a library replaces a few thousand hand-rolled lines, and what smells bad. Removing the first 30% is easy. The next 30% is harder, and that is exactly what the price should be on: doing what others can't. We use coding agents too, of course, but as a tool, not as the driving force.
That is why we started Slopfix, a software house focused entirely on refactoring AI-generated codebases. We commit to a reduction target up front, and the client pays in proportion to how much of it we hit. We get paid to delete code.
I am sharing this because cleaning up after agents with 1M token context is a real business for engineers. Curious what HN thinks.
> I don’t think this is anything new, really: Businesses have been running software that we’d call a “big ball of mud” [1] forever.
Well but something really is something totally new. Github went from x commits per year in 2025 (when AI-slop was already being pushed to Github) to the same number of commits in four weeks in 2026. 2025 compared to 2024 was already something like 15x.
It's never happened in the history of computing that so much new code was produced so quickly.
My bet is we'll see much more of this. And these aren't going to be 100% AI-pilled companies solving these issues but companies like the one in TFA: experienced devs using the help of LLMs to fix slop.
My other bet: slop shall outlive COBOL and dwarf COBOL's legacy big times.
Most of the new Github bloat will just be thrown away. Vibe coding scratches an immediate itch and it's easy to do. Once the problem changes nobody is going to update the first project because that's hard, they'll just vibe code an entirely new solution leaving the first to rot until they delete their dead repo clutter or move on from the company and the account and all of its repos are deleted in one fell swoop.
Our outcome is also AI-generated (or AI-assisted) code. It is not possible to rewrite 100k loc in a week. Where our stills are is refactoring at scale with help of agents. Basically, software engineer knows better what prompt to put, and when to redo the process or go different path.
>I am sharing this because cleaning up after agents with 1M token context is a real business for engineers. Curious what HN thinks.
Its the same as it ever was. Cleaning up after cloud migrations, cleaning up after crypto integrations, cleaning up after LLM tokenmaxxing. I think people are deluded if they tell you LLMs will replace humans.
I worked with such an "enterprise code" in the past. LLM code is a bit different. For example you don't see code repetition in the same file very often. I'd say it's a next level of slop. Slop at scale!
The copy on your website itself kind of reads like LLM slop (eg. "One week. Three senior engineers. $10,000"). You may have written it yourself and marketing copy just tends to look like this, but it doesn't inspire confidence that your service will actually improve my code.
There is also a flip side of this. I work a lot with AI-generate text and I can also catch it quickly, but most of the time now, it's easier to read AI, than humans with their weird chain of thoughts and compex sentences ;P
No shame in using Fable to help with the grammar and style of text. English is not my native language and while I can use it quite well, LLMs are much better in forming my thoughs into something simple, that sounds great.
My writing workflow is: (1) write what I want to have on the page. (2) /grill-me it should be sound and logical and easy to read. (3) Manually review the text, replace by hand what I don't like.
Initial AI scan can list most of system usecases. Then we review it with a client and agree on what must stay. We can propse better solutions at this stage. If we remove the code, then we can also remove its unit tests. For intergation, repo-wide tests, we treat it as documentation/requirements that must work on the other side.
Human to human interaction is the tool we use the most :)
We don't target software developers. Most of the time, they know their craft. We target those who don't have experience and diging into how serwer should be implemented, or best composition of a domain model is not what they would like to sepend hours doing.
The typical client is a 40 years old ex-CTO, that had idea, verified it with Claude Code and got to the point, where the repo is too big. Maybe even rewrote it all from zero, once or twice, but end-up with the same outcome after adding more features.
He can either hire a developer to work on the codebase and refactor it or hire 3party company.
Sometimes the requirement is a security review. And you pay much less if you downsize the repo before handig it over.
If unclogging the sewers is a way how the deluge of AI slop can create new work, then more power to you! It's one more element that makes it even harder to write satire that is more absurd than reality.
I want it be positive, but it’s a bit hard with this one. Do you expect the client to sit down and explain every detail? If they know how to do that, they wouldn’t be having messy code base as the one the post is describing.
And let’s say you’ve been hired, what happens after that? You think Claude.md file is sufficient to progress from that point?
The problem is real, but the solution is a fantasy.
We do the initial code review by ourselves, we try to run test, run the project etc. We compose a list of what we have in the codebase and what we think it does. We also preapre a list of what functionalites we would change.
Example would be removing service implementation that is bash code handling manually PID files, and replacing it with pm2 tool, that has quite different workflow.
it's not about the prose quality, but about the fact that it seems like the service of deleting ai-generated code is also going to be ai-generated, or at least the service is being advertised via ai-generated text, which is…funny
"Two weeks of warranty" jumped out at me. That's like "you have two weeks to find the thing we broke, or else we aren't responsible for it." In my experience, a good bug can hide for months more than two weeks! My codebases are definitely not in the target demographic for this service, though, and maybe if I were in the target group (bunch of LLM slop, trying to dig out of the hole, presumably no shipping product or existing userbase yet) the proposition would appeal to me.
If the client has an extensive suite of automated tests assessing if the software is meeting its requirements, it should be possible for them to flush out most regressions within minutes or hours, not weeks.
If the client hasn't invested in setting that up, the resulting situation is the clients' responsibility.
This is a fair point. But these days bugs are not so scary anymore, so a client can vibecode a fix faster then getting me to fix it. Of course if Opus can't figure it out, I would always try to help. I have never left a client alone, warranty or not. This is just how I was raised.
Bugs can cause user data loss in production, or total system outages, or a slew of other Really Bad Things. How are you planning to vibecode your way out of that after the fact?
lol looks like they are using a similar methodology to how we use Claude in house.
Honestly, the code we write with AI is cleaner, better documented, better factored, more maintainable, and less bugs than back in old days before code assistant agents. I think people must be just yoloing it, because it seems a lot like a holding it wrong type problem.
Problem is that you can't do a FOMO-fueled hype IPO that gets a trillion dollars if your argument is "this is a tool that can improve the quality of work your employees output".
It needs to be a "we are building a doomsday weapon here, give me money" argument. Even if it is false. Especially if it is false.
Same here. Honestly, there's also a bunch of human friction that goes away. I can tell a junior that a change needs to be significantly refactored (or even thrown away entirely) without the psychological damage of discarding days/weeks of work from them.
Previously, I would need to do the trade-off calculation. How urgently does this need to ship, and do we have time to rework this? What are the deal breakers that need to be addressed, versus what things are best practice/ideal for maintainability? How did their last code review go and do they need a small win right now?
There's no more "nit" comments tagged as nits: just things to fix. It's de-personalized in the sense that we can both at least pretend/have plausible deniability and blame the model for being dumb, as opposed to the person making mistakes. I flat out told someone that a PR was not solving the right problem earlier, and neither of us thought it was a big deal. I could give the technical guidance and suggest a path forward to "help Claude understand better".
I had an interesting conversation with a junior engineer who made this observation. She shipped a feature, we gathered data, and based on data we pivoted to a different design. She called out that she wasn’t attached to the code because AI wrote it. Not that she didn’t care about quality or effectiveness of the product, but the personal emotional attachment to the code itself was not there. Probably a healthy thing. I’ve seen senior engineers defend mediocre code because they wrote it and changing it was an ego hit.
The same reason we had them before? A few juniors can be productive with oversight and guidance. Half the battle is learning what good work looks like, and figuring out what it is that you should even really be building, and those are skills you develop.
I have to admit that I'm curious why this is the case. I almost wonder if the pseudo-anthropomorphizing of these models is partially what helps here, similar to how I don't take it personally when I give instructions to a junior engineer and they fuck it up (though, I probably should to at least some degree more than I do).
Probably something about the personal time and effort invested in a thing. I would feel much less personally invested if, for example, I created an outline of a story and then paid a ghostwriter to fill it in.
with AI, documentation driven development is an understatement, if you take the time not just to document but to also provide lots of examples and potentially even data structures for the implementation (including intermediary data structures if you know them) the output is better than anything you would make in reasonable time.
I understand that it’s probably impossible to sell non-AI-assisted solutions to AI-pilled companies (even when their headaches are AI-induced), but my gut reaction to “take an AI-inflated codebase and apply AI deflation to it” is something like “that’s akin to applying two rounds of lossy transcoding; the errors don’t cancel out, they cross-multiply”.
NGL I'd argue there's a certain appeal to "use AI to prototype a feature as fast as possible and focus your engineer hours on building a comprehensive testing and fuzzing plan" followed by a "remove and review everything that can be cut without breaking the tests" cleanup pass.
I do see the appeal, it’s easy to imagine that workflow working, and working well - but it’s hard to how it avoids this fate: https://youtu.be/QEzhxP-pdos
You're describing a problem that's plagued corporate software development for decades. You just get to the "unmaintainable ball of mud" stage faster now. Every few days I spent a while on codebase architecture improvements after landing a slew of features.
That's a leadership failure not a technical failure. If you can't dig your heels in and force time to tidy up technical debt then you need to find someone who can and let them take over as PM.
Ngl I’m doing this right now for a client. Part of my strategy is to write out e2e tests that get a certain baseline of functionality, and then use that as the check for any change that I make to the codebase to make sure it continues to work.
So workflow for a full web app is make e2e tests for all use cases. Then add a very strict duplication checker, and linter, and then just tell the ai to hit a certain duplication limit like 3%, check the linter, and add unit tests to ~95% or greater of the code.
With the right CI and other checks that are deterministic you can really do a lot with a codebase.
I have also experimented with mutation testing. But the side effect of this approach is that it keeps public interfaces intact, and most of cases you don't want that.
People keep making this analogy not understanding that trades folks will use the right tool for the job, not just whatever is newer / more advanced. Air nailers exist but hammers are still used. Drills can screw in screws but screwdrivers are still used. You wouldn’t use an electric drill for a lot of jobs. People will also try to equate it to an electric saw vs hand saw, but again time and place for both.
In my grandmas cottage I found an old handmade mechanical screwdriver that operates from manual pressure. That’s what got replaced by today’s power tools.
Thanks for writing this. In my refactoring process I also start with code profiling. Opus is good, at finding hand written code, which sometimes is a good starting point of understand the codebase in general.
the claude giveth and the claude taketh away. I could definitely use claude in a tightly directed manner to clean up a slopified codebase (and I would enjoy doing so), you just need to think of it as closer to a power tool than an agent.
My experience as well, I've been developing a native macos app using CC. As a web dev I didn't know much about the stack. Nothing too fancy a kind of folder gallery-player with tags embedded in filenames, a bit like TagSpaces.
Process was - produced a detailed feature spec - multiple iteration of "I want this and that", make it into coherent spec", "this this and that is not correct, change to that". Made it write architecture spec(which I didn't read because too unfamiliar) and split it into tasks. Then it was implementing tasks, after each I did a change/fix those ~10 things iteration and spec corrections.
It was good to a point, but then when I started to hit performance problems I had to step in look at the code, and very often fight with CC, confront its "this is the only way", force it to do web search for proper ways to deal with problems and even explain very simple things about proper DB usage.
At some point it asked me something like "is it ok for schema migration to just fail or we need to implement complicated handling?", I have answered "it just shouldn't leave app locked in schema failure", and guess what was CC solution? - it wrote an error handler which just drops DB and recreates fresh one on ANY schema failure. And if I didn't happen to peek at the code and ask wtf it is doing, that would've been an exiting UX.
I've spent about month's worth of $20 CC subscription tokens using Opus 4.8 on xhigh, AND about 70 hours of my time.
So "anyone can just code what they want now" is correct only to a point, MVP will work, but beyond that experience will be subpar, and it still needs lots and lots of iterations of explaining what you want. Then because normal user knows very little about how software works they won't be able to ask AI the right questions, confront it and rate of improvement vs token usage will hit rock bottom.
This seems like a easy way to get into consulting. Once you deliver the code back to the owners they are going to do the vibe coding again on the top whatever refactored code you get back. In other words it can become a perpetual cycle.
The goal is to avoid it and build such a structure and guidlines for the codebase, so it can refactor itself when needed, but based on the architecture defined by us. With good set of docs and new feature definition you can most of the time use /grill-me with good outcomes.
Call me pessimistic or realistic, the code and architecture is just a reflection of the author/organization. The only way it can change/improve is if you either switch the people/organization or invest in their improvement/continuous learning.
Being honest, knocking one refactor after another is super intense and we would burn out quickly. To me refactoring/reading/reviewing a code that you have never seen is one of the hardest thing to do for a software developer. If I have 4 such projects a month, I'd just hire more people and allow them to rest. Also invest more into internal tooling to speed things up would be good solution to remove some burden. I think $10,000 for refactor is a fair price.
We also have other gigs and ongoing project, where we can rest a bit.
The problem that quote (and this entire post and the folks that produced it) is putting a finger on is that vibecoding makes it very easy to build large piles of brittle, entangled code where all those early velocity gains are paid back as evolving the codebase takes more and more time (and, crucially, tokens).
No amount of <insert methodology here> replaces good judgement about architecture/design that ultimately leads to more maintainable, extensible code. That was true before AI and it remains true today.
Now eventually AI may get to the point where it's autonomously generating code that's structurally as good or better than what any experienced human would create.
So far, IME, that is not yet this case and nothing can yet substitute for an experienced human in the loop to steer AI toward better decision-making.
And before it's said, yes, that also means humans made ugly balls of mud in the before time. That term obviously came from somewhere.
But that only proves that AI is as good as prior humans that did a bad job, which on the one hand is impressive, and on the other hand is deeply alarming when you know there's folks out there letting these things loose without any supervision.
Of course if all one is doing is tossing off and walking away from greenfield projects, man, vibecoding is magical. I suspect a lot of the "we never look at code anymore" claims come from this world.
I wonder if this is part of what's clever about pitching their consultancy as slop cleanup -- nobody's likely to engage them to work on a pile of logic that's been evolving over a decade with weird load bearing corner cases. The "I just vibe coded a massive tangle" situations are more likely to be newer.
At least, one could hypothesize. Perhaps incorrectly. :)
I guess it was only a matter of time before this niche of business developed.
AI is an imprecise "programming" language, full of ambiguity (English) trying to produce precise relationships between different concepts.
It certainly works great on small scale, building block type of things, but the more a project grows in complexity, components, interfacing with other heterogenous systems in other languages or APIs, understanding wtf is going on top to bottom.... it fails miserably.
Reminds me of how xUML was going to be the panacea to replace coding. AI is failing for the same reasons. At least with xUML you have a precise definition - with AI, you're vibing your way into one.
I can't agree with saying ai is failing, I mean if you work at a company with a lot of software engineers it can be true, but from what I see it's mostly non technical companies that adopt vibe coding to address technical problems. It's just another form of outsourcing
i use it, but i could re-create everything the AI produced, it just takes me longer (I'm a dev). And yeah, that latter part of your sentence is what freaks me out - that someone thinks they can start thinking like a dev because they have an AI bot available to them. You know, "Become a super dev in 21 days" kind of book... Then you wonder why s*t breaks left and right.
We replaced a 120,000 USD/year low-code/no-code platform that was running a lot of workflows. And we have another platform that is also similar that we are on track to replace by EOY.
Both have been replaced by "vibe" coding. It works well. Everyone's happy. People are having fun with it. We get feature requests, improvements, ideas, feedback. JIRA tickets get created, and we ask AI to reference that ticket, code to it, and create a PR.
We have senior engineers review the actual functionality and none of them have read any more than a few lines of code.
Every person who builds like this has the same DX (developer experience): "Wow, I've been wanting to build this thing for years now. I just never had the time to do the things I wanted to do to help me and the teams that depend on us"
Total cost of AI subscription per month: Less than $1000. Preference is Claude Opus and Codex whatever the latest model is. Effort is a personal preference since it does not seem to matter.
Yes, I'm familiar with these talking points. I didn't mention clean code or solid or frameworks or anything like that.
However, the poster explicitly said they don't do what you said:
RE "talking to customers"
> We get feature requests, improvements, ideas, feedback. JIRA tickets get created, and we ask AI to reference that ticket, code to it, and create a PR
RE "figuring out whether it's actually working for people"
> have senior engineers review the actual functionality and none of them have read any more than a few lines of code
RE "figuring out what the heck to actually build"
> replaced by "vibe" coding
Maybe my definition of vibe coding is wrong?
--
In any case, I don't have some ulterior anti- or pro-AI motive. I'm genuinely curious why and how a project run this way has humans in the loop at all.
Sorry for the confusion, we talk to customers both internal and external that drive these feature requests.
We ultimately decided that paying for low code/no code platforms was pointless because that's what AI coding is. 90% of the time, we don't even have VS Code open and just gloss over the diffs in the PR.
I honestly don't know what the trajectory of those low code/no code platforms are going to look like. Are their senior strategists looking at the landscape in the last year and going "oh. no. What is the point of our product anymore because what's the point of people dragging and dropping no-code connectors to build an application when they can get 100% portability and transparency by having code generated by AI"
“Maintainability” is probably the word you are really looking for. Few devs care whether something adheres to whatever as long as we maintain:
- user experience/expectation (i.e., if feature X worked three years ago, it still works in a consistent way today after a bug fix)
- development cadence (if implementation of feature X took N days, a comparable feature Y should take N days)
- sanity (can we assume that a fix going in Thursday night or Friday morning doesn’t wreck the weekend)
SOLID, DRY, ACID-compliant, linted, formatted, clean, functional, compositional, etc. May be the means (misdirected or otherwise) but they are not the motivator(or at least should not be).
What matters is whether the day two feature requests, bug reports, CVEs, and traffic load that are coming can be met on time.
Not saying it can’t be done without a developer at the helm, Anyone Can Cook™, but I guess it depends on what harness is in use or has created for the org, and whether that consideration is baked into the guidelines for the codebase (which seems to be, at least to some extent, what this service tries to course correct).
And of course, what is done to the process when incident x happens, again and again. Are we only updating code without paying attention to process that enabled it in the first place?
Maybe that’s the story of vibe coded repos: the code devs were removed but we really still need devops personnel. Also maybe new tech will be more readily adopted.
You know, that question should trouble us more. But honestly we've all asked ourselves that same question and I think our collective response is too nuanced to try to type properly but I'll try.
Tools are always made out to seem like the human could be replaced. We've seen that every time some new technology comes out that some people claim will replace humans once and for all! But this does not seem to be true.
What AI coding allows us to do is get rid of just 1 or 2 parts of the job: coding and debugging. The rest of our knowledge based job is still there. AI just speeds things up because I can now ask it to code something while I go help plan or design something with a colleague. Most of us at this workplace also have a very good eye for UI design and system design patterns, so when we prompt/query the AI, we can understand what is happening. That isn't a replacement, that's more like getting a team of engineers who can do different things all in service of a larger goal.
Our conclusion was that we should not be concerned what search or queuing algorithm or data structure is being used. And to be perfectly honest, and I know that this will rub some in the wrong way, a lot of development since the 90s have been around object and graph management. For the 1000th time, I just do not (and most engineers I work with) care how an object is serialized and deserialized. Just display it on a table for me, why are we spending weeks coding a list, adapter, transformer, JSON/XML/whatever, networking calls, networking nuances, etc. etc. when I just want to get our customers seeing that list and move on?
I don't know if I did a good job covering the nuance, AMA!
- What you do at Initech is you take the specifications from the customer and bring them down to the prompt engineers?
- Yes, yes that's right.
- Well then I just have to ask why can't the customers take them directly to the vibe coding software people?
- Well, I'll tell you why... because... engineers are not good at dealing with customers...
- So you physically take the specs from the customer?
- Well... No. My secretary does that... or they're faxed.
- So then you must physically bring them to the software people?
- Well... No. ah sometimes.
- What would you say you do here?
- Look I already told you, I deal with the @#$% customers so the prompt engineers don't have to. I have people skills! I am good at dealing with people, can't you understand that? WHAT THE HELL IS WRONG WITH YOU PEOPLE?!
> Our conclusion was that we should not be concerned what search or queuing algorithm or data structure is being used.
Not to be too snide, but if that's your reductionist view of the work of software development, I'm not surprised you're comfortable vibecoding without a human in the loop.
It's really quite interesting how there are always posts on HN with people talking about how AI made their life great, did it cheaply, made a great product, and saved the day. But whenever someone asks for specifics, the questions are always dodged or answered very vaguely. It's rare that anyone ever even says what their product does.
To be fair, thraway3837 posted a reply on a sibling comment and offered "AMA" :).
That said, I do see a lot of those posts you're talking about, and I think a lot of AI development is way overhyped. But I also think internal tools like this can be a good use case.
Personally "none of them have read any more than a few lines of code" makes me wary, but if it works for them, then so be it!
I have Claude work on web app testing scripts written in java using JUnit and selenium. The scripts test a vibe maintained flight booking app for an airline I can't mention without doing myself. The app is maintained using copilot by another vender. Claude was given to our team by our employer. We aren't even employees of the airline just contractors under a vendor. Before Claude was adopted everyone secretly used whatever chatbot they preferred. I used opencode with Deepseek v4.
I'm happy to provide specifics, within reason, of course. Ask away. I've since responded to comments with more detail, but if I missed something there, let me know!
I had a product where I was doing accountancy ratios and it’s not that simple since you have lots of different source data to use and it was such a nightmare to combine everything in the right way. Ai did that easily. Also writing code to extract unstructured data was a few hours vs weeks of work.
This is so funny to me, because I know it's asked in earnest but seems so obvious to me:
They get actual work done.
Programming isn't work. That's just a means to an end. A tool to get the actual job done.
At least in most orgs. Obviously there are exceptions - but the vast economy is not a bunch of software companies. It's companies doing things to build a physical product, and software is a relatively new annoying side quest/cost center.
I think programming is work, but I get your point :). And yes, of course - I'm mostly just curious how peoples roles at various companies are evolving as they hand off more and more to AI.
I meant - create useful work product. For most companies software is a means to an end. The programmer writing code isn’t useful, it’s the end result. A lot of small to midsize companies employ a couple software guys out of necessity, and the results are usually middling at best. It’s a problem IT in general has really failed to solve very well.
I say this as someone who has picked up and put down “programming” as I needed it. It’s never been something I’ve gotten any satisfaction out of by doing, but I get huge satisfaction out of the resulting product or workflow automation or whatnot.
For my uses, if I could replace my programming and IT time with a robot I would - since me being in that role just slows down delivery to the end user. One of my first hires as a small startup was a programmer - specifically because I knew I rather sucked at it and what a pro could get done in a day took me a week. This is why AI for the low value/less complicated automation tasks is extremely compelling to me.
I’d immediately have 20 other things to work on to soak up the time savings!
It's interesting how people view software as a distraction and an annoying side quest/cost center, but never apply that to, say, 90% of what management does. None of that "directly" makes money either!
That tells us a lot more about the leadership and management philosophies at modern companies than anything fundamental about what kind of work actually matters.
Eh it's nothing new. Outsourcing comes from the same spirit.
Perversely I find myself increasingly blaming the growth of product management divorced from engineering as the source of some of this.
Everyone wants to be the next Jobs, but somehow they missed that it was the marriage of high quality design and high quality engineering that got Apple where they are today.
Rather, the lesson they learned is that PMF and UX and yadda yadda yadda are all that matter and coding is just a means to an end.
It'll be interesting to see how many companies discover that you can't achieve those ends if you build on a broken foundation.
Face it - it's because developers are annoying princesses. Just read your comment again.
My entitled friend was whining AI will start monitoring his work and he won't be able to slack as much as he does now. Basically he'll have to work like everyone else. FFS.
Everyone except management knows that management is a distraction, including the shareholders and board when the org is getting too bloated and the numbers aren't looking good.
Which is a perfect parallel to coders who don't realize that coding is a distraction. When your job depends on you not understanding something, etc
I used CF Wrkers because I wanted to try serverless(1) - I just needed a tiny https proxy for one of my personal scripts and.... It turned out to be super fun.
And no surprise bills.
(1) after my earlier experience with AWS lambda - almost no traffic (few requests per day), on free trier and YET I had to pay for the add-on they automatically added (and it took me almost 2 hours to find all the rhizomes that were proudly anticipating another few £ for pretty much zero traffic).
We did at my work. We were paying too much for low code orchestration software. Replaced it with vibe coded workflows. Still have some infra costs but it's fantastic, cheaper, more velocity, and everybody is happy.
I have always felt that AI will be much like how we all now have a calculator in our pockets (despite our math teachers telling us that would never happen lol). For math yes one could sit and do long division and multiplication and so on but having a calculator as a tool obviously makes things so much faster. But you still need to have the knowledge of how math works like the order of operations for it to be correct in the end.
I picture AI coding being the same. Ya someone with no coding knowledge can probably vibe code a small project and have it work. But more complex projects I picture AI like the calculator speeding up the work but in the end one must still understand programing and be able to ensure that the code is correct for the goal.
The main difference is (simple) calculators are deterministic and monotonic. Meaning it executes a set of instructions in a predetermined way to produce its output. Bringing LLMs to that level is a whole another ball game. But we'll see, perhaps the arithmetic nature of algorithms will be replaced by a whole lot of tensors in the near future.
It's easy to believe if it's 5x $200 subscriptions.
Paying by the token is insanely expensive. Only the
5̵ ̵R̵i̵c̵h̵e̵s̵t̵ ̵K̵i̵n̵g̵s̵ ̵o̵f̵ ̵E̵u̵r̵o̵p̵e̵ Biggest Tech Co's can afford that.
But the subscriptions are cheap honestly. Yeah they say it's not for enterprise usage but ok whatever. Not paying $10k when $200 gets you the same value (seriously)
No, I really meant that we don't even read the code anymore. In another comment I wrote: we just CMD+Q VS Code and it's not even in the recents/pin to dock, since what's the point? We can see the diffs in the PR and quickly gloss over it and query/prompt/ask clarifications.
> A SmartBear study of a Cisco Systems programming team revealed that developers should review no more than 200 to 400 lines of code (LOC) at a time. The brain can only effectively process so much information at a time; beyond 400 LOC, the ability to find defects diminishes.
...
> SmartBear research shows a significant drop in defect density at rates faster than 500 LOC per hour. Code reviews in reasonable quantity, at a slower pace for a limited amount of time results in the most effective code review.
This industry's complete outsourcing of its core business value on a third party proprietary subscription based tool, Claude, made by an unprofitable company, Anthropic, is very concerning. You are all lunatics, sorry.
I don't follow this line of reasoning. Would it have been meaningfully different if OP had used open-weight models like GLM or DeepSeek? Does it really matter considering we'll have superior models next quarter?
The meaningful difference is that you will not experience EOS if (when) anthropic/openai/etc fails to become profitable and is no longer subsidized by capital funding.
While "vibe-coded" apps do help lots of people who didnt have the time/money/skills to create their projects, you should be aware that currently the compute is being subsidized so that users become reliant/used to the service.
I believe vibe coding in general is a bad business strategy whether you use FOSS models or not because it means your product probably doesn't have any "secret sauce" (leaving code maintainability problems aside). By that I mean a carefully researched innovation that gives the edge to your product. Nevertheless, using FOSS models is clearly better for the reason you mentioned. I believe serious businesses will transition into using AI on-premise in a very restrictive manner (eg: AI only for tests and reviews policy, etc.). We'll once the dust is settled.
The question is if your "secret sauce" will stay secret as you use Anthropic's products, considering they've been launching specialised models like Claude Legal and Design. What happened to Figma with Claude Design should be a warning sign.
You can inject "secret sauce" through your domain knowledge or life experience.
You could vibe code the "tedium" out of your app with little to no care about it using AI while paying close attention to the critical aspects of your product. Of course, the fact that all of your AI code usage is being monitored by the company that provides you the model/harness is also still means they can just steal your product whenever they want
Stricter use would remove the primary benefit while not really giving much upside so I don't think companies will move in this direction
> Of course, the fact that all of your AI code usage is being monitored by the company that provides you the model/harness is also still means they can just steal your product whenever they want
Also anything which isn’t kept private can quickly be cloned. I think it’s going to be hard for a SaaS to stay profitable unless there’s a real-world tie-in to keep someone from pointing a bit at your app and cloning the observable behavior with just enough changes to claim they didn’t.
Internal business tools are not innovative products. The potential edge comes from things like being better aligned with the business process or eliminating tasks from the process.
Put on the hats of a risk manager or supply chain manager. Yes, that would have mattered. What you insource today, you can repeat tomorrow. If you know the price of an input will multiply in the near future, you should at least develop processes that can handle disruption. If you expect dirt cheap LLM’s to remain available, or even better: improve in quality, feel free to make that assumption explicit and keep using the external supply. I don’t know what the future holds, but the vibe your software organizations cannot go back to manual development once LoC has exploded. I hope firms are making these choices deliberately.
You seem to be referencing as core business value a combination of (1) the ability to maintain a (2) business criitical resource, but stating it as if catastrophizing from a hasty generalization. Can you clarify?
It's really not that simple. A lot of what's involved is fungible. Of course, the answer to "Was the greatest intelligence harnessed to make the greatest decision?" Is always no.
AIs can be swapped for one another, run locally, and implemented in ways that are less prone to loss of function. Loss of anyone who understands the working code is a type of risk, but that kind of issue tends to bounce between losing skill from lack of foresight due to economic savings, and overhiring / bringing back lost employees as consultants.
Meta requires tens of thousands of engineers to maintain a social media site. Google even more for an ad platform.
Never have so many achieved so little and the joke is all those clowns think they are “10x engineers”. Meanwhile WhatsApp got to global scale with less than 30 people (before Meta bought it and piled on the inefficiency).
Vibe coding is many orders of magnitude more efficient than the industry standard and that’s why it’s so disruptive.
I am currently working with a non-dev startup CEO that's fully embraced Claude Code and vibe coding.
90% of my work is to run code review workflows and steer his CLAUDE.md into the correct architecture choices and away from past mistakes.
So far it's working pretty well -- I'm able to unslopify the code and maintain the agent's performance. And the CEO is happy, he's able to develop his product pretty fast and not hit any walls.
Your landing page looks extremely AI written - if it’s not, you may want to consider rewriting it in a more human tone, given the market you’re going for.
15 years ago it was always fix price for undefined amount of work, 10 years ago it was agile where client was promissed something but paid per day.
I prefer the old way of doing things: do the offer for free, commit to a task, and accept, that it might not be a success after all. I'd just loose a week of work, but probably learn a lot.
We have been doing this for years now: it is great. We build our products faster and better and we get more money for fixing products vibecoded by others. More money in every way.
I wish these guys luck in finding their customer. Really. Because real solution to the problem would be to hire old-style developers to rewrite the whole slop from scratch without AI being involved. Fixing broken slop is Sisyphus's labor.
I mean, not really? The urge to throw all the code out and start over is what ever mid-level software engineer has always wanted to do, and it’s almost never the right choice. The old code worked well enough most of the time, it just didn’t have good or safe practices and those can be retrofit.
In fact, doing and directing such things are kinda senior, principal and management jobs, in general.
209 comments
[ 3.7 ms ] story [ 96.9 ms ] threadThere is a new kind of task for software engineers these days. A client calls, asks for a "small refactor," and sends you 100k lines of AI-generated spaghetti.
And this is great! This is something we can work with.
Any experienced engineer can look at a codebase like that and quickly see what to refactor, where a library replaces a few thousand hand-rolled lines, and what smells bad. Removing the first 30% is easy. The next 30% is harder, and that is exactly what the price should be on: doing what others can't. We use coding agents too, of course, but as a tool, not as the driving force.
That is why we started Slopfix, a software house focused entirely on refactoring AI-generated codebases. We commit to a reduction target up front, and the client pays in proportion to how much of it we hit. We get paid to delete code.
I am sharing this because cleaning up after agents with 1M token context is a real business for engineers. Curious what HN thinks.
A common way to market to these firms is to be very easy to find when their software starts to have serious issues.
[1] https://www.laputan.org/mud/
Well but something really is something totally new. Github went from x commits per year in 2025 (when AI-slop was already being pushed to Github) to the same number of commits in four weeks in 2026. 2025 compared to 2024 was already something like 15x.
It's never happened in the history of computing that so much new code was produced so quickly.
My bet is we'll see much more of this. And these aren't going to be 100% AI-pilled companies solving these issues but companies like the one in TFA: experienced devs using the help of LLMs to fix slop.
My other bet: slop shall outlive COBOL and dwarf COBOL's legacy big times.
Hope you like it.
Its the same as it ever was. Cleaning up after cloud migrations, cleaning up after crypto integrations, cleaning up after LLM tokenmaxxing. I think people are deluded if they tell you LLMs will replace humans.
"Fulfil" is the same way
My writing workflow is: (1) write what I want to have on the page. (2) /grill-me it should be sound and logical and easy to read. (3) Manually review the text, replace by hand what I don't like.
Some people like AI generated comfort-slop nowadays. They feel uncomfortable when they run into individualistic human language.
Human to human interaction is the tool we use the most :)
The typical client is a 40 years old ex-CTO, that had idea, verified it with Claude Code and got to the point, where the repo is too big. Maybe even rewrote it all from zero, once or twice, but end-up with the same outcome after adding more features.
He can either hire a developer to work on the codebase and refactor it or hire 3party company.
Sometimes the requirement is a security review. And you pay much less if you downsize the repo before handig it over.
You always have to remember to tell the barber "No mistakes", just like you have to tell Claude.
And let’s say you’ve been hired, what happens after that? You think Claude.md file is sufficient to progress from that point?
The problem is real, but the solution is a fantasy.
Example would be removing service implementation that is bash code handling manually PID files, and replacing it with pm2 tool, that has quite different workflow.
So the client must approve such decisions.
something's off here
> Then we [perform the act of] cut[ting]: [thereby,] the fourteen date formatters become (i.e. are replaced with) one,
it's not about the prose quality, but about the fact that it seems like the service of deleting ai-generated code is also going to be ai-generated, or at least the service is being advertised via ai-generated text, which is…funny
If the client hasn't invested in setting that up, the resulting situation is the clients' responsibility.
Umm, what?
Bugs can cause user data loss in production, or total system outages, or a slew of other Really Bad Things. How are you planning to vibecode your way out of that after the fact?
But the true cost of minds, not AI assisted minds, is probably higher. They may have found a pricepoint which scales.
Imagine a future, where people get jobs to .. "write code" (in hand quotes) based on specifications "written" by machines..
haha
Honestly, the code we write with AI is cleaner, better documented, better factored, more maintainable, and less bugs than back in old days before code assistant agents. I think people must be just yoloing it, because it seems a lot like a holding it wrong type problem.
Documentation driven development is your friend.
Problem is that you can't do a FOMO-fueled hype IPO that gets a trillion dollars if your argument is "this is a tool that can improve the quality of work your employees output".
It needs to be a "we are building a doomsday weapon here, give me money" argument. Even if it is false. Especially if it is false.
Previously, I would need to do the trade-off calculation. How urgently does this need to ship, and do we have time to rework this? What are the deal breakers that need to be addressed, versus what things are best practice/ideal for maintainability? How did their last code review go and do they need a small win right now?
There's no more "nit" comments tagged as nits: just things to fix. It's de-personalized in the sense that we can both at least pretend/have plausible deniability and blame the model for being dumb, as opposed to the person making mistakes. I flat out told someone that a PR was not solving the right problem earlier, and neither of us thought it was a big deal. I could give the technical guidance and suggest a path forward to "help Claude understand better".
I had an interesting conversation with a junior engineer who made this observation. She shipped a feature, we gathered data, and based on data we pivoted to a different design. She called out that she wasn’t attached to the code because AI wrote it. Not that she didn’t care about quality or effectiveness of the product, but the personal emotional attachment to the code itself was not there. Probably a healthy thing. I’ve seen senior engineers defend mediocre code because they wrote it and changing it was an ego hit.
What does this even mean? Why have the junior engineer is they aren’t irrationally invested in the code the write?
I understand that it’s probably impossible to sell non-AI-assisted solutions to AI-pilled companies (even when their headaches are AI-induced), but my gut reaction to “take an AI-inflated codebase and apply AI deflation to it” is something like “that’s akin to applying two rounds of lossy transcoding; the errors don’t cancel out, they cross-multiply”.
So workflow for a full web app is make e2e tests for all use cases. Then add a very strict duplication checker, and linter, and then just tell the ai to hit a certain duplication limit like 3%, check the linter, and add unit tests to ~95% or greater of the code.
With the right CI and other checks that are deterministic you can really do a lot with a codebase.
I can basically split it into 3 groups.
1) Pure vibe code. No software experience.
2) AI with someone who knows the software development process and some things about software, but can’t code.
3) Engineers using AI assistance, reading/reviewing code, forcing structure.
If someone can pay to replace #1 with #3 it’s very worth it. The quality between each of these tiers is enormous.
I actually got curious and asked AI to look at each module in a codebase, and tell me about who wrote it without looking at git.
It successfully profiled all 3 of these groups and correctly attached them to the right module.
Broad prompts by unskilled users results in a complete mess. Targeted prompts by a skilled person reviewing the code produces something better.
Quality of application varies widely, and generally agree with the categories mentioned by the sibling post.
Process was - produced a detailed feature spec - multiple iteration of "I want this and that", make it into coherent spec", "this this and that is not correct, change to that". Made it write architecture spec(which I didn't read because too unfamiliar) and split it into tasks. Then it was implementing tasks, after each I did a change/fix those ~10 things iteration and spec corrections.
It was good to a point, but then when I started to hit performance problems I had to step in look at the code, and very often fight with CC, confront its "this is the only way", force it to do web search for proper ways to deal with problems and even explain very simple things about proper DB usage.
At some point it asked me something like "is it ok for schema migration to just fail or we need to implement complicated handling?", I have answered "it just shouldn't leave app locked in schema failure", and guess what was CC solution? - it wrote an error handler which just drops DB and recreates fresh one on ANY schema failure. And if I didn't happen to peek at the code and ask wtf it is doing, that would've been an exiting UX.
I've spent about month's worth of $20 CC subscription tokens using Opus 4.8 on xhigh, AND about 70 hours of my time.
So "anyone can just code what they want now" is correct only to a point, MVP will work, but beyond that experience will be subpar, and it still needs lots and lots of iterations of explaining what you want. Then because normal user knows very little about how software works they won't be able to ask AI the right questions, confront it and rate of improvement vs token usage will hit rock bottom.
What your markup on their salaries? For the level of work you're promising, it sounds like they may be at market or below.
We also have other gigs and ongoing project, where we can rest a bit.
Sounds like you forgot to have the agents use red/green TDD and build a robust test suite while they were shipping all of those features.
But if your code is poorly structured, it absolutely does not make it easier to modify.
Plus, SQLite famously has 590x the test core compared to the implementation code, and they wrote that by hand! https://sqlite.org/testing.html
The problem that quote (and this entire post and the folks that produced it) is putting a finger on is that vibecoding makes it very easy to build large piles of brittle, entangled code where all those early velocity gains are paid back as evolving the codebase takes more and more time (and, crucially, tokens).
No amount of <insert methodology here> replaces good judgement about architecture/design that ultimately leads to more maintainable, extensible code. That was true before AI and it remains true today.
Now eventually AI may get to the point where it's autonomously generating code that's structurally as good or better than what any experienced human would create.
So far, IME, that is not yet this case and nothing can yet substitute for an experienced human in the loop to steer AI toward better decision-making.
And before it's said, yes, that also means humans made ugly balls of mud in the before time. That term obviously came from somewhere.
But that only proves that AI is as good as prior humans that did a bad job, which on the one hand is impressive, and on the other hand is deeply alarming when you know there's folks out there letting these things loose without any supervision.
Of course if all one is doing is tossing off and walking away from greenfield projects, man, vibecoding is magical. I suspect a lot of the "we never look at code anymore" claims come from this world.
But there's another word for that: slop.
At least, one could hypothesize. Perhaps incorrectly. :)
AI is an imprecise "programming" language, full of ambiguity (English) trying to produce precise relationships between different concepts.
It certainly works great on small scale, building block type of things, but the more a project grows in complexity, components, interfacing with other heterogenous systems in other languages or APIs, understanding wtf is going on top to bottom.... it fails miserably.
Reminds me of how xUML was going to be the panacea to replace coding. AI is failing for the same reasons. At least with xUML you have a precise definition - with AI, you're vibing your way into one.
Both have been replaced by "vibe" coding. It works well. Everyone's happy. People are having fun with it. We get feature requests, improvements, ideas, feedback. JIRA tickets get created, and we ask AI to reference that ticket, code to it, and create a PR.
We have senior engineers review the actual functionality and none of them have read any more than a few lines of code.
Every person who builds like this has the same DX (developer experience): "Wow, I've been wanting to build this thing for years now. I just never had the time to do the things I wanted to do to help me and the teams that depend on us"
Total cost of AI subscription per month: Less than $1000. Preference is Claude Opus and Codex whatever the latest model is. Effort is a personal preference since it does not seem to matter.
> none of them have read any more than a few lines of code
So what do you / your team do?
Probably the hard part; figuring out what the heck to actually build, talking to customers, and figuring out whether it's actually working for people.
Nobody cares that your codebase is Clean and SOLID, or uses $whatever_framework of the day with 100% test coverage.
However, the poster explicitly said they don't do what you said:
RE "talking to customers"
> We get feature requests, improvements, ideas, feedback. JIRA tickets get created, and we ask AI to reference that ticket, code to it, and create a PR
RE "figuring out whether it's actually working for people"
> have senior engineers review the actual functionality and none of them have read any more than a few lines of code
RE "figuring out what the heck to actually build"
> replaced by "vibe" coding
Maybe my definition of vibe coding is wrong?
--
In any case, I don't have some ulterior anti- or pro-AI motive. I'm genuinely curious why and how a project run this way has humans in the loop at all.
We ultimately decided that paying for low code/no code platforms was pointless because that's what AI coding is. 90% of the time, we don't even have VS Code open and just gloss over the diffs in the PR.
I honestly don't know what the trajectory of those low code/no code platforms are going to look like. Are their senior strategists looking at the landscape in the last year and going "oh. no. What is the point of our product anymore because what's the point of people dragging and dropping no-code connectors to build an application when they can get 100% portability and transparency by having code generated by AI"
- user experience/expectation (i.e., if feature X worked three years ago, it still works in a consistent way today after a bug fix) - development cadence (if implementation of feature X took N days, a comparable feature Y should take N days) - sanity (can we assume that a fix going in Thursday night or Friday morning doesn’t wreck the weekend)
SOLID, DRY, ACID-compliant, linted, formatted, clean, functional, compositional, etc. May be the means (misdirected or otherwise) but they are not the motivator(or at least should not be).
What matters is whether the day two feature requests, bug reports, CVEs, and traffic load that are coming can be met on time.
Not saying it can’t be done without a developer at the helm, Anyone Can Cook™, but I guess it depends on what harness is in use or has created for the org, and whether that consideration is baked into the guidelines for the codebase (which seems to be, at least to some extent, what this service tries to course correct).
And of course, what is done to the process when incident x happens, again and again. Are we only updating code without paying attention to process that enabled it in the first place?
Maybe that’s the story of vibe coded repos: the code devs were removed but we really still need devops personnel. Also maybe new tech will be more readily adopted.
Interesting times.
Tools are always made out to seem like the human could be replaced. We've seen that every time some new technology comes out that some people claim will replace humans once and for all! But this does not seem to be true.
What AI coding allows us to do is get rid of just 1 or 2 parts of the job: coding and debugging. The rest of our knowledge based job is still there. AI just speeds things up because I can now ask it to code something while I go help plan or design something with a colleague. Most of us at this workplace also have a very good eye for UI design and system design patterns, so when we prompt/query the AI, we can understand what is happening. That isn't a replacement, that's more like getting a team of engineers who can do different things all in service of a larger goal.
Our conclusion was that we should not be concerned what search or queuing algorithm or data structure is being used. And to be perfectly honest, and I know that this will rub some in the wrong way, a lot of development since the 90s have been around object and graph management. For the 1000th time, I just do not (and most engineers I work with) care how an object is serialized and deserialized. Just display it on a table for me, why are we spending weeks coding a list, adapter, transformer, JSON/XML/whatever, networking calls, networking nuances, etc. etc. when I just want to get our customers seeing that list and move on?
I don't know if I did a good job covering the nuance, AMA!
- Yes, yes that's right.
- Well then I just have to ask why can't the customers take them directly to the vibe coding software people?
- Well, I'll tell you why... because... engineers are not good at dealing with customers...
- So you physically take the specs from the customer?
- Well... No. My secretary does that... or they're faxed.
- So then you must physically bring them to the software people?
- Well... No. ah sometimes.
- What would you say you do here?
- Look I already told you, I deal with the @#$% customers so the prompt engineers don't have to. I have people skills! I am good at dealing with people, can't you understand that? WHAT THE HELL IS WRONG WITH YOU PEOPLE?!
I think I missed where you posted what business you work at
Not to be too snide, but if that's your reductionist view of the work of software development, I'm not surprised you're comfortable vibecoding without a human in the loop.
That said, I do see a lot of those posts you're talking about, and I think a lot of AI development is way overhyped. But I also think internal tools like this can be a good use case.
Personally "none of them have read any more than a few lines of code" makes me wary, but if it works for them, then so be it!
This conversation feels like the "disturbance in the kitchen" scene from Curb Your Enthusiasm: https://www.youtube.com/watch?v=vjaHrp6JtyY
This is so funny to me, because I know it's asked in earnest but seems so obvious to me:
They get actual work done.
Programming isn't work. That's just a means to an end. A tool to get the actual job done.
At least in most orgs. Obviously there are exceptions - but the vast economy is not a bunch of software companies. It's companies doing things to build a physical product, and software is a relatively new annoying side quest/cost center.
I meant - create useful work product. For most companies software is a means to an end. The programmer writing code isn’t useful, it’s the end result. A lot of small to midsize companies employ a couple software guys out of necessity, and the results are usually middling at best. It’s a problem IT in general has really failed to solve very well.
I say this as someone who has picked up and put down “programming” as I needed it. It’s never been something I’ve gotten any satisfaction out of by doing, but I get huge satisfaction out of the resulting product or workflow automation or whatnot.
For my uses, if I could replace my programming and IT time with a robot I would - since me being in that role just slows down delivery to the end user. One of my first hires as a small startup was a programmer - specifically because I knew I rather sucked at it and what a pro could get done in a day took me a week. This is why AI for the low value/less complicated automation tasks is extremely compelling to me.
I’d immediately have 20 other things to work on to soak up the time savings!
That tells us a lot more about the leadership and management philosophies at modern companies than anything fundamental about what kind of work actually matters.
Perversely I find myself increasingly blaming the growth of product management divorced from engineering as the source of some of this.
Everyone wants to be the next Jobs, but somehow they missed that it was the marriage of high quality design and high quality engineering that got Apple where they are today.
Rather, the lesson they learned is that PMF and UX and yadda yadda yadda are all that matter and coding is just a means to an end.
It'll be interesting to see how many companies discover that you can't achieve those ends if you build on a broken foundation.
Face it - it's because developers are annoying princesses. Just read your comment again.
My entitled friend was whining AI will start monitoring his work and he won't be able to slack as much as he does now. Basically he'll have to work like everyone else. FFS.
Which is a perfect parallel to coders who don't realize that coding is a distraction. When your job depends on you not understanding something, etc
Is it a web app with vibe ops?
What's running all of the workflows now? Are you vibe provisioning new cloud instances? Or does everything run on local machines now?
And no surprise bills.
(1) after my earlier experience with AWS lambda - almost no traffic (few requests per day), on free trier and YET I had to pay for the add-on they automatically added (and it took me almost 2 hours to find all the rhizomes that were proudly anticipating another few £ for pretty much zero traffic).
I picture AI coding being the same. Ya someone with no coding knowledge can probably vibe code a small project and have it work. But more complex projects I picture AI like the calculator speeding up the work but in the end one must still understand programing and be able to ensure that the code is correct for the goal.
Paying by the token is insanely expensive. Only the 5̵ ̵R̵i̵c̵h̵e̵s̵t̵ ̵K̵i̵n̵g̵s̵ ̵o̵f̵ ̵E̵u̵r̵o̵p̵e̵ Biggest Tech Co's can afford that.
But the subscriptions are cheap honestly. Yeah they say it's not for enterprise usage but ok whatever. Not paying $10k when $200 gets you the same value (seriously)
For now, it's clear that they will likely begin restricting the subs or severely cut back their token allowance.
I could also see Claude looking at source code/repos to try and figure out if it's closed source. If true, demand token payment.
A senior engineer should be able to efficiently read thousands of lines of code per day. Maybe this is what you meant by "a few"?
https://smartbear.com/lean/code-review/best-practices-for-pe...
> A SmartBear study of a Cisco Systems programming team revealed that developers should review no more than 200 to 400 lines of code (LOC) at a time. The brain can only effectively process so much information at a time; beyond 400 LOC, the ability to find defects diminishes.
...
> SmartBear research shows a significant drop in defect density at rates faster than 500 LOC per hour. Code reviews in reasonable quantity, at a slower pace for a limited amount of time results in the most effective code review.
While "vibe-coded" apps do help lots of people who didnt have the time/money/skills to create their projects, you should be aware that currently the compute is being subsidized so that users become reliant/used to the service.
You could vibe code the "tedium" out of your app with little to no care about it using AI while paying close attention to the critical aspects of your product. Of course, the fact that all of your AI code usage is being monitored by the company that provides you the model/harness is also still means they can just steal your product whenever they want
Stricter use would remove the primary benefit while not really giving much upside so I don't think companies will move in this direction
Also anything which isn’t kept private can quickly be cloned. I think it’s going to be hard for a SaaS to stay profitable unless there’s a real-world tie-in to keep someone from pointing a bit at your app and cloning the observable behavior with just enough changes to claim they didn’t.
It's really not that simple. A lot of what's involved is fungible. Of course, the answer to "Was the greatest intelligence harnessed to make the greatest decision?" Is always no.
AIs can be swapped for one another, run locally, and implemented in ways that are less prone to loss of function. Loss of anyone who understands the working code is a type of risk, but that kind of issue tends to bounce between losing skill from lack of foresight due to economic savings, and overhiring / bringing back lost employees as consultants.
Meta requires tens of thousands of engineers to maintain a social media site. Google even more for an ad platform.
Never have so many achieved so little and the joke is all those clowns think they are “10x engineers”. Meanwhile WhatsApp got to global scale with less than 30 people (before Meta bought it and piled on the inefficiency).
Vibe coding is many orders of magnitude more efficient than the industry standard and that’s why it’s so disruptive.
90% of my work is to run code review workflows and steer his CLAUDE.md into the correct architecture choices and away from past mistakes.
So far it's working pretty well -- I'm able to unslopify the code and maintain the agent's performance. And the CEO is happy, he's able to develop his product pretty fast and not hit any walls.
> No cookies. No tracking. No JavaScript. Real people.
Commitment ain't what it used to be.
I prefer the old way of doing things: do the offer for free, commit to a task, and accept, that it might not be a success after all. I'd just loose a week of work, but probably learn a lot.
In fact, doing and directing such things are kinda senior, principal and management jobs, in general.