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 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.
"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.
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.
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.
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”.
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.
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.
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.
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.
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.
64 comments
[ 2.5 ms ] story [ 85.0 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.
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
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.
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”.
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.
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.
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.