I liked building apps and helpful tools before AI came around. I've been doing so for 15 years, 10 of them professionally.
Today, I like it even better. It's never been so fun.
What would have taken days of work, if it was feasible at all, I can have implemented in half an hour now and iterate on the result to make it work the way I want.
I stopped reviewing the code at all.
People on here are often saying how that's a disaster, how the result would be unmaintainable, and so on. I think they are clueless.
My app has 200k LOC + 100k in tests, and there is no sign of the AI slowing down or being unable to maintain it.
I've been working on the project for four months now. I invested hundreds of hours, and I expect to publish my paid app in the AppStore this month.
It has been fun. I am using the app every day and I look forward to the features I will add in the future.
>My app has 200k LOC + 100k in tests, and there is no sign of the AI slowing down or being unable to maintain it.
May I ask what does this app do ? 200k is like GTA vice city level, is like sqlite level, If its a financial tracker or a to-do list or an agent coordinator I am going to kill myself
I'm not going to share exact details about my paid app, but you could think media management, with a lot of extra features, an in-app browser with custom controls, and multiple AI powered features with on device processing.
> I'm not going to share exact details about my paid app
You might not be aware of this, but you've answered the question - just indirectly.
You're selling an app, but don't want to share any details, or even name it?
Call me suspicious.
He's not. That's how things will be from now on. Because there's plenty of hacks who think prompting will make them millions if they could just find that one idea, yet aren't willing to do the work to find, vet, build, and iterate.
I said I'm hoping to complete it this month and I already shared some details.
Should I post my market and keyword research too, here on this site for software developers and entrepreneurs?
It doesn't matter when you post it; some kid with a $200 claude sub (or cheaper) is going to clone it for far cheaper than you, and sell it for far cheaper than you.
There's no friction to what you produced, so why do you think that you won't have 100s of clones, all cheaper?
We're now in a market for lemons as far as software goes.
I spent hundreds of hours on this, so there is still some friction.
If I told you the exact market and use case, I'd still have a decent head start, but indeed, someone without a job could invest more time than I do. People in a cheaper location can work for far cheaper than I can afford to.
With head start I don't meant that the idea is so novel that I need to keep it a secret. However, I believe that if there is an established app that does the same thing, and your app cannot beat it on quality, it will be hard to attract users.
A conundrum I see is that once someone releases a “solution” to a problem, it becomes much easier for someone else to come up with prompts to have AI make a clone of that solution.
Basically, the moat for many products is disappearing, and it would be relatively cheap for someone to make a clone that undercuts the cost of the first to market. The original product is charging $2? Cool, the clone will cost $1 - maybe it’s not as good due to less QA, but consumers will see the lower price and buy it.
> I spent hundreds of hours on this, so there is still some friction.
I'm afraid your hundreds of hours of prompting will reduce to "clone this product, here are 200 screenshots of every screen."
I don't understand why people aren't getting this: there is no skill in prompting! The CC leak literally showed Anthropic engineers developing Claude with broken half-english prompts like "gud, now make better".
Hundreds of hours doing what? If you're not reviewing the code, then what are you doing, just planning features? Because that would be trivial to copy in a fraction of the time by just feeding screenshots of your app to one's AI of choice.
Yes, and a lot of QA testing.
That's the thing. The moment you publish, the design you spent 100s of hours on also becomes public, at which point it becomes entirely replicable with little to no recourse. Hence the theme of this entire thread: a devaluement spiral.
Despair is a choice some people have made, and they want to drag others into it to justify their inaction. Take your best shot. Maybe it takes off, maybe it doesn't.
Either way, it's a hell of a lot better than being a replyguy.
>it's a hell of a lot better than being a replyguy.
It's best to live by your own words
Ignore the "dropbox-in-a-weekend" trolls, they're just nosy. Your project sounds interesting, good luck.
Vice City was released nearly 25 years ago! Also it's a game, so it's not really an apples-to-apples comparison. If you count the unique 'features' (or systems) of Vice City, you might find it's a comparable count to the number of features of a medium-sized mobile app.
You are joking right ? renderer, audio, math, physics, animation, AI, asset streaming,.... in addition to the gameplay itself, and you compare it to a medium-sized mobile app ???
Apps usually have tons of boilerplate, so pure LoC may be similar. But in density, no contest. I recently dug up an old objc app of mine and was shocked how few lines it took to send a REST request, parse and process it. Nowadays it is split into multiple files, usecases, repositories, protocols to accomplish the same. All in the name of testability or architectural “correctness”. Write that in a game and you’re fired because it kills performance.
There's a different bar for maintenance though. Many games exist in a single point in time, they ship and are done, whereas the goal with SaaS is to support the code forever.
Maintenance, sure, but also: games have one chance to be good, and that is at release. With a multi-year development cycle, what we get at release (of the good ones) is like a version 4 or 5 of an app. Everything is connected and changed (and thus maintained) over the years.
The physics of the car tires in vice city by themselves outweigh 99% of all apps in terms of complexity and features…
I feel you need to clarify which mobile apps are "medium-sized" for you, because if we just interpret this comment literally it's just laughable.
> I've been working on the project for four months now. I invested hundreds of hours, and I expect to publish my paid app in the AppStore this month.
I wish you the best, but you have invested a considerable about of time and I'm guessing token budget for something with no revenue and no customers. That in itself is totally fine, but I'm not sure it gives you the authority to calling people clueless for having a different opinion on the maintainability of 200k unreviewed, llm generated code with no users.
I would be chasing altcoin revenue - those worthless things nobody wants. Hold those but encourage their spending too, with an app, is the road to riches in a world where one's IP can be immediately negated by a disgruntled robotic employee jumping ship.
Actually, I don't know if the premise works in the real world, but can't see why "crypto-enabled" isn't adopted at every turn.
Altcoins - the snowball lying in wake. Bitcoins were crap too at one point but they have stood the test of time and obscurity. It's about going from HODL'ing to spending for dear life. Something like that anyway. Maybe 3+ years to go before any serious price movement because of dumping pressure being so high from pre-miners and the like. No idea.
My impression with how the wind is blowing is that someone is going to come along, if your app has merit, and duplicate it with Astra/Fable. Then they'd back it with significant ad spend, outcompeting yours.
Me too I use my apps every day. But the main thing coming out of this is that they are tailored to me. Turning hobbies into hustles is one of the worse things that happened in the post social media days.
I think selling software that solves your own problems is great and beats trying to develop for customers you do not understand.
Completely agree. You tell the best story for your product doing it that way.
AI has really revealed the programmers who were temporarily inconvenienced idea guys
This is BY FAR the worst part of LLMs to me. The idea guys were always incredibly annoying but very ignorable. Now they are constantly in your face but providing the exact same 0 value as always.
Not the case here. When I was young I dabbled in reverse engineering and hacking games for example.
I don't think I am less of a 'hacker' or programmer than the next person on HN.
Same here. Loved hacking on things from all angles, still do. The only thing lost to me now is the yak shaving, and good riddance. I want to think in systems, solutions, integration, and first and foremost the higher level problem, not nitty gritty implementation details.
Ever since Fable and Sol level LLMs/agents came online, I have ceased to look at the code. I recently launched a project for a client that integrated many many systems, has considerable traffic with low latency requirements and everything just.. works. I've never had to do this little firefighting when launching a project of that complexity and scale. It's been liberating and I was able to focus mostly on polish and QoL improvements of the stack and systems. What a time to be alive for a technical builder.
I mean, wasn’t that the case for most of them? Im not a developer anymore, but to me programming was always a means to an end. Sure you can have preferences (static vs dynamic typing, functional vs OOP, etc.), but in the end they should only be relevant if they make you more productive, makes the codebase more readable and so on.
Since these nuances are progressively getting less and less important, why would you care about the process?
There is such a thing as difficult concepts that code can express elegantly and words cannot. Its far beyond the simple preferences you allude to. Recursion is the simplest example i guess. Perhaps maths is even more elegant, but im among many a non mathmetician for whom code is the only way ive experienced it thus far.
Especially when you combine and mix those concepts in expressive, simple, intuitive ways. Im just not sure what else is like it that our minds can percieve.
Because a lot of people enjoy the process. Why do you think people so wood working as hobby or the whole demo scene?
Same experience here. I have published 3 apps this year that have just been ideas I've been kicking around for far too long - I never had the time outside of my day job to work on them. Most modern models write code better than I could, maintain it better, and free me up to focus on creativity and trying to add value.
I find that it falls apart after the first 1000 or so lines.
I used to think this but then improved and found that it was a matter of tooling. Using beads[1] and getting the AI to write its own tickets and wiki articles using GitHub's wiki feature on repos, it can keep track of long horizon projects pretty easily. Then you curate some of the tickets or read through them and have them update the beads or adjust them as they work them. When they want to retain some important piece of knowledge you have them add it to the GitHub repo wiki.
Modern AI programming looks an awful lot like traditional product owner or product management roles.
1: https://beads.gascity.com/
I’m not into the personal wiki thing, let alone an AI wiki. This feels like productivity porn.
Then you're really really bad at using it. At the very least it is functional with minimal effort on codebases with 10s of thounsand
Or what happens is that after 1000 lines there are hundreds of decisions it would have to consider to do anything and it doesn’t do that and instead finds the smallest path to insert its latest request.
>there is no sign of the AI slowing down or being unable to maintain it
This means you designed the system well and made sure the agent implemented it correctly. Even at Big Company the big shot architects don't review every line of code, and nobody seemed to mind that
It’s just a fact that an ai will write and read faster than me. I can’t compete so getting ai to do that has freed up both time and mental capacity to actually think about the implementation details.
I'd like to think it comes down to my expertise, but I don't believe I did a lot of designing.
Sure, I've given a lot of inputs over the time, probably I've steered it to solutions that work.
Maybe it was also helpful that I set up a skill to use a different model to review the code for correctness, technical debt, and whether the location where the code is added is appropriate or warrants a new file or abstraction. I set this up long before subagents were widely used.
The way I see it, they are two types of ("technical") peoples:
The ones that loves the technicity, the challenge of building something, putting complex things together, the puzzle part of creating something.
The ones that wants to have stuff build to use them, were coding was just a mean to an end. (DHH mentioned in his podcast with Lex Fridman, that he is more in this category)
For the later, AI is the perfect tool that could come around, removing that barrier that was stopping them to achieve their needs (which you appear to be part of, I'm saying this without no jugement)
The writer of the blog post is in the former category.
I'm also having the time of my life building products I want to exist. It's like suddenly having the budget to hire a small team and materialize ideas that before would have required many months or years of your time (or taking investment).
And yet, I'd be lying if I said I don't miss the flow.