alt Hacker NewsI 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.
Replies
> 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 find that it falls apart after the first 1000 or so lines.
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.
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.
AI has really revealed the programmers who were temporarily inconvenienced idea guys
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.
>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
>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