Comment by Shank
1 day ago
> But as the models get better and the quality of the output will match the quality of the established SaaS but tailor the whole thing to a single user with the ability to make any change they can imagine within minutes, and perhaps deploy to Hetzner and whatnot where they could host all of those apps for a single $5 instead, the exodus will accelerate.
I do think you're vastly overestimating people's ability to write software, even with LLMs, and use it in production. The average computer user does not even use a computer as their primary computing device, they use a phone. The barrier to going from idea to phone app on iPhone or Android is relatively high.
Todo list apps, habit trackers, and the like are almost a special snowflake breed. Almost everyone has some different cross-section of needs they care about, and no app is perfect for each individual. So it's natural to say "is there something that matches what I want?" and then reach for tools to make that. The world is your oyster for todo list apps. Of course, the real issue comes from data sovereignty, trust, quality, things like that. When Apple launches a new device or a new iOS feature people want, you get to see which apps will actually implement the new features or which stagnate. They're a natural avenue for vibe coding since they're so particular.
Depends on how you define "production".
People in general would recoil in horror if they knew how many essential operations are backed by a mess of Excel sheets with formulas and VBA nobody understands anymore.
All it needs is the maker mindset of being just lazy enough to be bothered by a repetitive task and the courage (and permission) to use an Agentic LLM to figure out a fix for the issue.
> People in general would recoil in horror if they knew how many essential operations are backed by a mess of Excel sheets with formulas and VBA nobody understands anymore.
Yeah, but that mess is deterministic! With a little bit of rigour, someone with no experience of that specific mess but knowledge of excel from a previous employer will dive in, make a small change, see if the results are messed up, back it out, try again with a different change, and repeat until they get what they want.
Good luck asking an LLM to modify something made by a different LLM 5 years ago.
Deterministic but also very fragile. Excel _still_ doesn't have unit tests or linters.
Someone can accidentally type a static number in place of a formula and it may stick there for years.
Or Excel decides that a name of a gene is a date: https://www.theverge.com/2020/8/6/21355674/human-genes-renam...
Or Excel silently losing important health data: https://www.bbc.com/news/technology-54423988
None of these would've happened with a vibe-coded bespoke tool. A basic elementary level unit test would've caught them instantly.
Eh, that really depends on how well the LLM understands edge cases of the particular need. Quite often these cases are hidden deep in files nobody understands any longer and will never get in a training set.
You end up with a system that works right up to the moment it doesn't and fails spectacularly and expensively.
This is one of those reasons you always hear about sweeping medical/hospital records systems being upgraded going tens or hundreds of millions over budget. The edge cases are demons.
Well of-fucking-course you don't vibe code your salary management system =)
Just normal non-coder jobs have massive amounts of repetitive crap that could easily be automated - and already has been automated with Excel - to a degree.
Now Agentic AI lets them automate the rest - or if they're real smart they use an agentic AI model and create an application to do it that doesn't require a LLM subscription.
1 reply →
It will be interesting to see if Apple/Android provide a platform for vibe-apps.
It's somewhat like the Shortcuts system on steroids.
> It will be interesting to see if Apple/Android provide a platform for vibe-apps.
They could have done a low-code/no-code platform ages ago, but they didn't. They don't want their users creating their own apps instead of buying, because that would cannibalise their income from hopeful app devs selling 5 units at a 30% cut.
> It will be interesting to see if Apple/Android provide a platform for vibe-apps.
It would be interesting, particularly for Apple, as this would cannibalize fees charged on the App Store. I imagine they could charge for use of the vibe-coding platform, but Apple hasn't been great at figuring out LLMs.
It would be cool if 3rd partly app platform could provide this functionality, but as I noted in another comment, I cannot even install my own vibe-coded apps to my own iPhone. (Without the 100 USD a year developer tax.) So I'm not sure how the architecture would work on iOS.