> It's a lot more that just a CRUD-app.

That still seems like a simple CRUD app.

Steady on, I'd say it's at least a fancy CRUD app.

Yes, sure, a fancy CRUD app. Still, enabling a non-programmer to do this is... interesting, and ultimately may be game changing.

He didn't spend a fortune. This wasn't "agentic", eating zillions of tokens. It was the standard stuff anyone could do with a personal subscription ($20/month or so) to a couple of AI services.

what about the data? is it locally hosted? if he drops his phone everything will be lost? or are servers and databases involved? if so, where are they being hosted? how did he manage those?

even these sorts of stories are incredibly shallow and hard to believe for me personally.

I was just talking to a friend of mine who has been making webapps for himself in a similar fashion. Very little to no programming experience. His first app scans his course notes (med school) and creates structured question banks. He's released it so everyone at his school can sign up with their institutional email. The front end is hosted with vercel and the backend with supabase.

He also has one for tracking the stats of the volleyball team he coaches. He can do things like track the direction a player hits the balls during a game and save it for review later. Hosted with Vercel and Firebase I think.

Point being: he has no experience with software development before this (although he did have some data science experience), and in the space of a couple months has produced two high quality webapps that are being widely used in his circles.

I was pretty shocked, but after seeing the apps Claude made for him (or told him how to make). I can believe this story.

If someone has any curiosity, they can ask the AI about this and it will engineer a solution, like use iCloud or some free tier service.

After all, it's basically how us software engineers arrived to where we are today. It's hubris to think nobody else has the interest nor attention span to walk a solution incrementally to its conclusion, esp when they don't know what the final solution will look like ahead of time.

> After all, it's basically how us software engineers arrived to where we are today

An increasingly smaller minority of us. The vast majority have gone through a bootcamp, or an undergrad or similar to gain specific skills that they can apply writing software for a corporation.

There's hardly any reason to believe the percentage of the general public that reach that level will be any higher than in the profession itself.

The stack is typically some combination of supabase and vercel (think: managed everything), which get you far enough on a free plan if you have 1 user

I was writing a comment about the durability of this app, but you beat me to it. Something tells me that the burden of maintaining this thing through various OS updates, security policy changes (from Apple and Google), new devices, etc. is going to be frustrating for him. It's great that he vibecoded something useful to him in this moment, but I do think these stories are "counting their chickens before they hatch" so to speak.

It's not like you can't write "update this for next round of forced obsolescence " to Claude. Yes, it's unnecessary burden but solvable.

You'd be shocked at how easy Supabase makes these things. You can describe your data needs and it'll use AI to generate the table and RLS policies. You can even go a step further and have Replit do both front and backend. I had chats with multiple PMs who have entire functioning products without understanding a lick of code. Powerful, and although scary from a security perspective, not so scary if it's a personal app.

Supabase scans customer setups and throws up loud warnings for insecure setups aka RLS is disabled on $table, and unless the PM is totally irresponsible, they can throw that email at their LLM of choice and ask it "is this a problem, will I get hacked?" and the LLM will do a fairly competent review of the issue. So it's scary from a security perspective in so far as you do or don't trust AI to find issues.

Much of this could be done with a spreadsheet.

Not exactly revolutionary in the way you’re claiming.

Half of the current startups could be done with a speadsheet and yet they earn money.

The number of businesses and business departments that run on spreadsheets and earn money is almost mind-boggling.

It works until it doesn’t. The failure mode can be that the spreadsheet wizard leaves and no one understands their macros, the data grows 10x and emailing spreadsheets back and forth becomes too error prone, or any other of the well-known ways that this falls apart.

Those of us in software always cringe and want to use a database.

“Vibe-coded apps are the new spreadsheet.” Seems about right, and the problems will be similar.

Edit: This comes across as more negative than I wanted. I think spreadsheet-driven businesses are pretty amazing, and it's a testament to the tool how far they can get. I pretty much feel that way about bespoke vibe-coded apps. I'd feel even better about it if the rhetoric wasn't mixed in with claiming software as a career is over or that no one will have jobs anymore.

Institutional knowledge is just valued at $0.

I want that to be true because it means I'll still have a job, but vibe coded apps by non-developers are still backed by git (as far as I've seen), addressing at least one issue with spreadsheets, and are hosted on Vercel, and backed by Supabase, so there's no sending files back and forth and the database (PostgreSQL) has backups and is able to scale somewhat. What are the other well-known ways that spreadsheets fall apart? If the person leaves, all the next person has to do when something breaks is to the LLM the problem and ask it to fix it. You couldn't do that with a spreadsheet.

UI/UX is important.

> 6 months of fiddling with a couple of different AIs in his spare time

Six months of fiddling and $X00 in subscription/token fees to make a DIY inventory management app that's going to need regular attention and revision, with ongoing service fees, to accommodate not-quite-right implementations and hidden technical debt.

That's a toy for wealthy hobbyists, not a revolution.

The industry needs to deliver on a lot more than that to justify the investments that have been made.

I know right and after 6 months it is an app managing a database with some ocr functionality. 6 months for that? I get the wine guy couldn’t do this beforehand, but in the “old days” of say 6 years ago this is the sort of thing you might build after a 60 minute tutorial…

> That's a toy for wealthy hobbyists, not a revolution.

Isn't this exactly how many technologies begin?

A PC used to cost as much as a very nice used car, and had few practical uses cases, as one example.

No need to be wealthy. Last December I paid $180 for an year of Z.ai's coding plan. It's enough for hobby use.

I have developed multiple such applications myself. Essentially a wrapper around SQLite in pick your favourite language, that you then use to extract and combine different data.

So the future is - Everyone has their own apps built specifically for their own use case and spending tokens just for the satisfaction to have created something themselves? That sounds like a tool for hobbyists.

I have no clue about wine connoisseur apps but I have to assume that someone some where has build apps to manage the obvious data and now integrating AI into it so that it can do photo to text and reports and summaries etc.

If there are no other apps then commercializing the app might be a better win and use case.

If there are others apps then I can't imagine the nightmare where everyone has their own Supabase/Firebase/AWS etc instances and run their private apps because it does things exactly as what they want to do along with satisfaction of spending 6 months on it. Instead of paying for an app which might be used across the industry and helped them save those 6 months.

Yeah, I think I agree with your assessment.

Everyone creating their own bespoke apps sounds great until all these people realize what they were paying software companies for, maintenance, security and inoperability.

I'm seeing this in my ops role currently. Everyone from development to marketing vibe coding things that look good and function on a surface level but are creating more maintenance headaches for me to support since once they get their pretty front end, they think they did the hard work and now it is on ops to support.

A couple weeks ago, I had accounting come to me to show me their cool app they vibe coded and asking for help "just finishing it up." They spent 6 hours making the front end to a form.

A form that I could have spun up in 10 minutes if they came to me first using tools we already had. But now because they "made it" they feel ownership of it and don't like the idea of me rebuilding it in a more standard way.

Marketing last week showed me another "app" they spent all week on. It again was just a form. They didn't like the jira form interface so they decided to make a prettier way to submit tickets. However it doesn't actually do anything, it is just a front end. But of course they showed leadership and got kudos for it because it looks so nice, and now I have to figure out how to wire it up and maintain it.

And don't get me started on an engineer who decided to make their own BI tool that is half baked and not even connected to anything (they give it a csv every day and hit run). When we literally have a live dashboard with the same data.

These things are killing efficiency. You have teams "building things" instead of dieing their job. And leadership loving it because sexy UI must mean productivity.

I think you are too cynical. His app works. It needs no maintenance, unless the underlying OS changes something fundamental. It doesn't use AWS or any other cloud service.

Look, as an IT professional, I build dry stone walls. Could a professional do it better? Probably. So what? I have the satisfaction of having built them myself, exactly how I want.

AI had enabled something new, and us only going to get better.

You are basically repeating what you said above. It works. There is satisfaction of building the app yourself. Its your baby and it works - AI enables that and it will get better.

Replace what you said with many hobbyist examples from over the years. Lets say hydroponic farming. "You can grow your own vegetables without needing soil and it works even if you live in the city. Farmers can do better but so what you grow the vegetables yourself. Hydroponic farming has created magic".

Man, I wish he open sourced in on GitHub, I’d love to customize it for my own collection.