[dead]
I Tried Building a Real App with AI. It Took a Year
81–90 of 90 posts
Re: I Tried Building a Real App with AI. It Took a Year
#82I've been working on an app over a year. I think it needs to be considered that agent cli's only really released about a year ago. Before that, I was copy and pasting code between web chat windows into a terminal.
Additionally, the ai models only got good in November/December last year. How easily we forget.
The result of this? I had to do several full rewrites and there are still many bugs left over from these. AI simply wasn't powerful enough to do the task and littered the codebase with issues that I'm still even now dealing with.
Re: I Tried Building a Real App with AI. It Took a Year
#83Maybe it's my PTSD from developing iOS apps speaking, but this reads to me more like an indictment of developing on Apple platforms than developing with AI. Even if it's partly about AI from a year ago.
I haven't really done any iOS-native programming in about a decade, but I have spent a godless number of days working through bugs, inconsistent behaviors, poor documentation, and weirdly broken builds in Xcode and iOS and various SDKs, and then going through a different version of the same hell for every new release.
Like, after suffering through the first few upgrade cycles, I started keeping a journal of repeated issues that came up, hoping I could reference it and save me some headache the next time... and then the journal just kept growing!! Every goddamn new release had a bunch of new headaches to deal with.
I recently touched upon some iOS/MacOS-related development (Safari extensions), hoping things had improved over the years, and immediately ran into frustrating dev experiences. Unfortunately I'll be doing more of this. TFA was light on the details, but it still left me with a bit of a 1000 yard stare.
Re: I Tried Building a Real App with AI. It Took a Year
#84> Spending your time cleaning up AI slop that you didn't want to write in the first place doesn't sound like much fun. Pretty much every job I've had since 2003 involved cleaning up human-written slop. For the moment, I'm finding that AI speeds up certain things: It can bang out unit tests in a few minutes, or do 80% of the work for me; but once it gets to the "test, make small change, test" loop, that's all done by…
Human written slop is SIGNIFICANTLY more enjoyable than LLM slop, it tells a story no matter how bad the dev is. LLM slop is a tidal wave of meaningless drivel.
As a someone who's fixing my own slop from the all the past years and with the help of the good coding agent, no less, no, human slop is not enjoyable, it's embarrassing.
Re: I Tried Building a Real App with AI. It Took a Year
#85Earlier quoted context omitted.
Ugh, that happened to me too. But instead of researching other apps and waiting for them to decide to go premium too, I built my own workout app. Been using it for a couple months now and it's working great, but the hassle of publishing it to the app store means that it will only ever be a solution for me and I can't share it with anyone.
Have you considered making it into a PWA? I've always thought of cloning the old Zero fasting app into one, when I have a bit more time to point my Claude at building something else.
I actually started with it as a PWA, but ended up rewriting it in react-native. I wanted a couple features (heart rate monitor, lock screen integration) that afaik don't work with PWAs.
Re: I Tried Building a Real App with AI. It Took a Year
#86What I find a problem is when I build everything with AI then if I have a flaw in a fundamental concept it can become very hard to refactor, to the point that the project can die.
So far I never built anything that didn't need human in the loop, otherwise things just don't function well or my ideas are not translated as well.
Re: I Tried Building a Real App with AI. It Took a Year
#87> This was just before Claude Code was released so this wasn't full agentic hands-off engineering. Instead, I broke down the development into lots of small tasks and went through them manually with the AI, testing each change as I went along Is there really much use in deconstructing a vibe coding process that was used before the term "vibe coding" existed? It's like critiquing a caveman's fire-starting routine. > Me…
I am not exactly sure, but my gut feeling is that Cursor existed before Claude Code was released, and the term vibe coding existed already at that time. EDIT: Okay, Andrej tweeted about Vibe Coding on February 3rd 2025, and Claude Code was released in the same month. But Cursor was already there (I can see usage starting January 2025 in my account and know that it took me a few weeks before I tried it).
My point was that it was critiquing a development process from 2023 in 2026, regardless of the term used.
Re: I Tried Building a Real App with AI. It Took a Year
#88Earlier quoted context omitted.
same here. Did a timeslot management app for beauty salons etc. Tons of features, never once looked at source or even database (C#+pgsql) The hard part were actually the sales but I'm getting quite some, going physically(!) to places. Hosting costs $50, revenue is ~1k/month, nothing special but its basically on autopilot. I did have the app for 6 months for free on a first client where they would give me feedback bug…
> I don't even have a pricing page, i try to see how much i get can from each client, from $5/mo to $100/mo That seems ethical. Vibes based fees.
It is, and it is common practice. Dressed up as additional features like everyone else.
Every feature cost me the same (tending to $0), but i price them as i see fit.
Re: I Tried Building a Real App with AI. It Took a Year
#89Earlier quoted context omitted.
"always" is a bit strong here.
No it isn't. I don't trust A.I. to generate maintainable and correct code and the people that use are too lazy or incompetent to write it themselves so I don't trust them either. Ergo: I'd always go for "NO A.I. WAS USED IN CREATING THIS PROGRAM"
I'm sure you will, but "people" in general will not give a crap about it and continue to choose the most convenient/cheap/ergonomic thing and only a minority will look at such a certification (which does not exist)
Re: I Tried Building a Real App with AI. It Took a Year
#90Earlier quoted context omitted.
No it isn't. I don't trust A.I. to generate maintainable and correct code and the people that use are too lazy or incompetent to write it themselves so I don't trust them either. Ergo: I'd always go for "NO A.I. WAS USED IN CREATING THIS PROGRAM"
I'm sure you will, but "people" in general will not give a crap about it and continue to choose the most convenient/cheap/ergonomic thing and only a minority will look at such a certification (which does not exist)
They will when software starts failing left and right. And companies too when they realize their developers are unable to fix the software because they have no idea how it works.
Companies chasing pipe-dreams of getting rid of all those developers will go bust in a couple of years. At the very least their brand image will be tarnished.