The project I’m currently working on is getting close to 60k lines of code, with fairly complex business logic. From what I’ve heard, at this scale only a few tools (like Claude’s desktop app) are genuinely helpful, so I haven’t experimented much with other AI coding services.
At the same time, I keep seeing posts about people building 20k lines of code and launching a SaaS in a single 40-hour weekend. That’s made me question whether I’m being overly cautious, or just operating under outdated assumptions.
I already rely on AI quite a bit, and one clear benefit is that I now understand parts of the codebase that I previously wrote without fully grasping. Still, at my current pace, it feels like I’ll need several more months of development, followed by several more months of testing, before this can become a real production service. And that testing doesn’t feel optional.
Meanwhile, products that are described as being “vibe coded” don’t seem to be getting particularly negative evaluations.
So I’m wondering how people here think about this now. Is “you don’t really understand the code, so it’ll hurt you later” still a meaningful criticism? Or are we reaching a point where the default approach to building software itself needs to change?
I’d especially appreciate perspectives from people working on larger or more complex systems.
That is one of the strongest valid criticisms. Even if we ignore the possibility that the code that is vibed will be buggy and insecure, the real long-term problem is not having someone who understands the system. Almost every well maintained app has one or more people who grok the whole thing, who can hear a problem described and know right where the fix will be. They'll have a mental model of the whole system and can advise on architecture changes and other refactors. They can help teach the codebase to new folks. And most importantly, when an outage happens, they are the ones who quickly get you back up and running.
The lack of those people is why legacy systems are brittle and hard to maintain, so vibe coding a complex app puts you directly into that painful legacy maintenance mode.
One thought people are starting to throw out there is, "But the AI can just re-write the whole app every time we have a bug, so we never need to know things to that level." But those people have never worked with a customer base who gets ticked off when the same bugs re-appear on every release, or when a dozen small UI changes shows up on every release.
Vibe coding might give you some working code. But working code is an astoundingly low bar to set for actually building a product that pleases a customer base.
With the right MCPs or additional context you can have the tools go read PRs or the last 10 tickets that impacted the system and even go out and read cloud configuration or log files to tell you about problems.
The concept of a "bus factor" is a relic of the past.
So far, I’ve been reading through almost 100% of the code AI writes because of the traps and edge cases it can introduce. But now, it feels less like “AI code is full of pitfalls” and more like we need to focus on how to use AI properly.
I know what every module does (well Lambda in my case but I’m trying to be more generic), I know the abstractions, I know the business case, etc.
As a team lead/architect, even with other people writing code, I don’t know every line of code does. Claude code/Codex is just a junior/mid level developer to me
They care about the business. If you want to be like them, start by caring far less about the actual code or how it gets made. They will bring in people later who do, who will clean up the vibed mess
*I'm generally not a fan of this, but you asked
Gold plating code with the best quality standards takes LLMs seconds whereas it would take you days doing it by hand.
and they may or may not "listen", they are non-deterministic and have no formal means or requirements to adhere to anything you write. You know this because they violate your rules all the time in your own experience
Outside of work, I have just launched an iOS app I've wanted to build but has been outside my current skillset. I was able to "vibecode" this app in about 4-5 months.
The application has a tiny bit of moat because it involves a ML model (also vibecoded) trained on my own data set.
When I say vibecoded, I never reviewed or read code in detail. I really only ever saw snippets claude code shows here and there. I asked a lot of questions, much more than asking it to make changes. I only gave it high-level architectural guidance like "use MVVC", etc. I did a lot of manual testing and reading logs.
I won't name the app out of fear of shilling my vibeslop, or whatever, check my profile for the domain in an email address if you want to know more.
What's cool about this is that, every time new engineer joins this wave, there are more interesting ideas coming and shaping the "vibers" industry.
In my day to day job, now I am worried, it will be very difficult to get a new job, because I vibe so much that I almost forgot to write code from scratch.
Examples:
* Hey Claude, increase mem usage from 500Mb to 1500Mb in production - fire and forget
* Plan mode: What kind of custom metrics can we add to Xyz query processor? Edit mode: add only 3,4 and 9. Later we will discuss 8
* Any other small changes I have...
I primarily became a manager of bunch of AI agents running in parallel. If you interview me and ask me to write some concurrent code, there is a high probability that I will fail it without my AI babies
Now it's easier to traverse a live plan and to quickly make micro pivots as you go.
I also think that architecture needs to change. Design patterns that will help to provide as much context to the LLM as possible to increase understanding.
The first thing I did was keep everything as decoupled as possible with so it would be simple for Codex and Claude Code (I use both) to reason over. I work the same way when setting up my own repos.
I treat Codex/Claude as junior developers and I keep my hands on the wheel
LOC doesn’t matter if you have clean modularity
For a larger, more complex system, the real barrier is understanding what needs done well enough that you can build something that can do it. (In my opinion, that has always been the real barrier.)
The moat is most people aren't using LLMS, most people aren't building products, most people who might built it will never hear of your product, people will have other ideas competing for their attention, people are incompetent, and all the work that happens after the coding.
How many people do you think are out there vibe coding things?
Aren't companies built on execution? Or do we now build companies on tech stacks alone?
Before LLMS, how could a solo dev get a moat? Any company could hire a team to replicate your product. They might not care how much it costs them. "Hours spent coding" isn't the moat.
"If it worked for my use case and didn't work for yours, you're obviously just doing something wrong. That's the only explanation."
I just assume all the posts that claim they've got a 20k line project in a single weekend is just marketing spam.
I should also consider isolating the custom logic in the existing codebase as much as possible, converting it into general logic, and then testing the “vibe” approach directly.
What surprised me:
1. The "you don't understand the code" criticism is real but misses context. I don't understand the implementation details, but I understand the system architecture, user flows, and business logic. That's enough to make good decisions about what to build next.
2. The iteration speed unlocks something new. I can try three different approaches to a feature in the time it would have taken to spec out one. This changes how you think about product development - you learn through building rather than planning.
3. The bottleneck moved from "writing code" to "understanding what you actually want." The conversations I have with the AI force me to be precise about requirements in a way I never had to be when just thinking about features.
Where it breaks down: anything that requires deep technical judgment about performance, security, or scale. I can build the feature, but I can't tell you if it will hold up under load or if there's a subtle security issue. I need technical people for that.
The "20k LOC weekend" stories are selection bias, but the productivity gains are real for certain types of work. The key is knowing which type you're in.
Source: non-technical founder who built a production SaaS frontend this way
My sense of using LLMs for coding is me feeling like a maintenance programmer even though the code is brand new and I'm debugging a LLM misunderstanding. Weird to be working on a 10k codebase that didn't exist a few hours ago and I'm now debugging it over the next 4 hours. Having it done around 16-20 work hours later is really strange.
This is the issue. A firehose of code production is not useful for a long time. But it's very useful in short bursts. Total volume of code was never the bottle neck or the goal.
Working with LLMs has all the same pitfalls of working with people. Programming effectively for the long term requires all the same rules whether you're using LLM's or not: build incrementally, test and refactor as you go (not at the "end"), keep scopes small, ship frequently, etc.
