Yeah. Part of why this is possible is simply that there are tons of subscription apps out there that were never really justified in requiring a recurring payment and are actually fairly trivial.
It used to be that you offer subscriptions only if there are ongoing costs, and a one-time payment if not (utilities, local, etc). SaaS kinda ruined that.
I'd welcome a boom in DIY vibe-coded utilities for personal use.
What I fear is a pollution of the open source space with tons of tailored apps that have a lot of overlap, but none of them get meaningful contributions because the maintainer will most likely respond with wontfix to almost everything (if they respond at all).
Shrug, it's hard to have an open app where everyone wants to add/change something and not have it turn into a Turing machine that attempts to do everything.
Sometimes you just want an app does X and Y, but not A, B and Z.
Was reminiscing about the early iOS App Store days when many apps were free and often hobby projects. Some hooked up google ads to make a nice easy profit if they stumbled on a particularly good early app idea. I don't really find apps like that anymore, or at least they don't really get shared the same way. Maybe this is a return to that in a sense.
I also don't think any particular idea is off limits for making a profit, if you do something and you do it well, you can charge a fee. But if the free hobby version is better then you best find a way to justify the price.
Most users expect everything to be cloud these days. In the cross-stitching community (which is mostly older non-technical folk), the amount of people that get mad every day because the most popular app is local-only, is phenomenal. What do you MEAN they smashed their device, bought a new one, and all their WIP projects aren't there anymore?
I made the same realization two weeks ago. Posted about it here, where I rebuilt bare bones todoist with a habit tracker, goal setting and more within a few vibe coding sessions: https://news.ycombinator.com/item?id=46633092
I think that many existing apps with huge userbases will gradually lose users as the models become better and better. Their biggest advantage is that people don't like change, and thus having to e.g. export data from some tools etc. seems to be a hassle not worth $5 a month.
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.
On the other hand, new products will have a much harder time to gather a big userbase. Whenever I'll see a launch of a SaaS asking for $$$, the first question I'll ask myself will be how long it will take LLM to recreate it. And for most cases, I imagine that the time it will take to get 80% of what they have is a few vibe coding sessions (as most newcomers will probably have used LLM themselves to code it up).
Some apps just do not make any sense for monetization and are now raced to zero. If it's not already open sourced then someone will vibe-code an implementation if none exist.
Vibe-coding accelerates the destruction of basic (closed-source) apps charging a subscription for features that offer little to no value whatsoever.
First of all, I’m skeptical about these being free. Time isn’t free, and the tokens to make these projects certainly weren’t free.
Second of all, all of these SaaS apps that don’t actually have a need for recurring charge probably should be paid one time. I don’t use Loom — I use CleanShot X and it was a one-time $30 payment and has a lot of great features I benefit from. I can’t reimplement it in $30 of tokens or $30 of my time.
But for an app whose use case doesn’t change and is recurring for no reason? Yeah there’s probably not much value in recurring payments outside of wanting to support the developer. I pay a lot of indie devs out of the goodness of my heart, and I’ll continue to do that.
But the value for “SaaS apps” without clear monthly costs should have always been under scrutiny.
> the value for “SaaS apps” without clear monthly costs should have always been under scrutiny.
It should have been, but the number of people qualified to offer proper scrutiny has been low, and those people have largely been occupied with bigger things. Or they were making those apps and had a conflict of interest.
The point is that now that vibe coding is at a level where it can identify and put together off-the-shelf components, and there are all these end users that don't really care about standardization (it's not like their SaaS products used open, interoperable standards in the first place), the ability to compete with those offerings has exploded.
Biggest problem for SaaS is that people don't have enough time to be informed buyers. Like in theory you should be able to make a $0.99 annual SaaS app that provides some small service really well and sell it to a million people who need it, but that kind of sale is almost impossible. Most people are either missing out on great software they should be buying, or paying for software they don't need.
I probably didn't market it enough but I specifically made an iOS game last year to be premium, $2.99, as a one time purchase to try and get around the obsession with subscription and freemium/ad-supported models but pretty much didn't get any more than a handful of sales.
At least for games I think it's much too late for the one time purchase model unless you're part of a pro studio making relatively big games.
It's the app "stores" that encourage and push for that.
You pay less tax to them when you do subscriptions rather than one time payments, if I recall especially with Apple Store (something like 30% first year, 15% the second year of subscription).
This is why 120$ over 10 years (1$/month) is more profitable to companies than 120$ in a shot.
> First of all, I’m skeptical about these being free. Time isn’t free, and the tokens to make these projects certainly weren’t free.
Yes, but it's almost one time payment. Your own personal use case is usually narrow enough, and you don't need to support different OS/browsers. You can vibe code it and just forget the fact it's coded.
Actually it's the best use case for vibe coding (the strict meaning of this word) - when you don't plan to maintain the codebase anyway.
> I can’t reimplement it in $30 of tokens or $30 of my time.
Probably not.
I also paid for FreeFileSync (the donation version) instead of rolling my own local backups (across drives), as well as MobaXTerm because I really like their UI/UX and so on. Software that others have developed and supported for multiple years, which has been already tested by a lot of folks thoroughly across their usecases is probably a good bet, doubly so if you can buy it (or I guess choose to support the devs) instead of renting it, the difference being that in the latter case you're not in control.
At the same time, 30 USD gets you about (assuming 85 input and 15 output split, which approximately matches my stats across months):
(actual figures would change with the input/output proportion, it matters a lot, and also any caching)
Not really enough to build serious software, but definitely quite the bit of help along the way!
Or if you go with subscriptions, it can vary even more, even if will cap how much you can do per day.
For example, if you pay 50 USD for Cerebras Code, you get 24M tokens per day, so that'd be close to 730M tokens per month. They're running GLM 4.7 which isn't SOTA in my experience, but is somewhere around Sonnet 4 and therefore actually quite capable: https://z.ai/blog/glm-4.7 (my experience might not match the benchmarks, but either way it can be good enough for most stuff out there)
For a decent percentage of software development, maybe where you want a feature nobody else out there has, AI can help you get rid of enough friction and lend enough help along the way, to maybe make it worthwhile. The caveat there might be that you have to treat the expense of your own time as something you do for the enjoyment of it (building something, or the delayed gratification of benefitting from using the software).
No amount of what ifs and buts is going to change the fact that the tech is now mature enough to make software in hours that previously needed man-years.
If you need $1M/y in subscriptions to build your software, you'll be outcompete by solos who needs $60k/y and don't care about the 100% churn of a one-time fee.
This is simply market optimization when the marginal cost of producing the good falls.
Some of this "I can do it for free" stuff gives me the vibes of people who monitor gas prices every day. Only to drive 10 miles out of their way to save $0.30 a gallon filing their 15 gallon tank ($4.50 savings - $2.00 gas used - $X for time). They probably also buy an overpriced drink/snack for a net negative value proposition even if time is free.
Some of these things are the feeling of "getting a deal" or "screwing the system" and people can spend their time in whatever way brings them joy. I don't want to be a "markdown editor app developer" or whatever and would rather work on more creative endeavors. In the end, we give our time to get money and then trade our money for time but time is our only limited resource.
What's actually going on here is the Unix Philosophy applied to more and more platforms.
Previously, if you wanted to rig up a screen recording app in a few minutes you'd use Linux and specifically one of the minimal desktop environments like i3 or sway. Then you'd wire up a few command line utilities (slurp, wf-recorder, etc) and get the exact experience you want. These small unix tools allowed the greater ecosystem to just cobble together what they wanted without too much hassle. I've done exactly this!
This is the exact mindset that keeps people away. They'd prefer to NOT maintain their own video recording software THANK YOU VERY MUCH. So you get people who go to Mac OS because there's always a slick solution for a couple bucks and you never have to be TOO fiddly.
This doesn't destroy the market for people in the latter camp, but it DOES open up the market for people in the former.
Subscription apps often have to target a wide userbase. However, most users only need a small subset of the entire feature set, and would be better served by a tailored version. This means that vibecoded apps can get away with being much less complex (specific featureset, no login etc), while still being more useful.
I have also created tools with LLMs that are exactly tailored to what I need, and still much more polished than what I could do without LLMs. Will have to think about if there is anything else I can do this with.
I get that this is tempting but it just means you'll slowly get dependent on things that will eventually break in ways you will have no capacity to fix. And disaster recovery is most certainly a manual task.
Loved the article, thanks for sharing. I’m curious if you’d share your setup. I haven’t made any macOS apps before, primarily because I never wanted to really learn XCode and obj-c. I like swift but still prefer simpler editors like Zed/VSC vs. What XCode offers.. so when you’re building these are you doing it in XCode or in another tool like Claude Code/codex/gemini CLI?
Seconded, I would be interested in knowing people's workflows + experiences developing MacOS and iOS apps with claude, etc.
From the repo here, it looks like its just using swift command line tools, which might just work well enough with cursor/vscode/etc. for small projects. You won't have Xcode's other features but maybe thats fine for an agentic-first development workflow.
I've been using Cursor with the Swift Extension. Works really nicely, but sometimes I switch to Xcode to do some tasks such as testing that it works to build.
It’s easy to overlook what I think is the real value of these “home-built” tools.
We can now produce products and apps that are tailored to our own preferred ways of working.
Regardless of the cost of generating them (which can be as low as $20 per month for a ChatGPT Plus subscription) or the effort involved (sometimes less than an hour of “vibe coding”), we’ve reached a point where the resulting product can be significantly more valuable than the existing product, service, or subscription it replaces.
"Death knell" is, I think, putting too fine a point on it.
At the same time, Apple better wake up as the quality of the App Store (such as it is) is about to get much, much worse as a flood of vibe-coded apps make it onto the store. These will likely crap out in spectacular ways and, as I say, bring user's experience with the App Store in general way down.
It's like when Amazon intermingled drop-ship sellers on their platform.
Which is exactly why whenever I have an idea I just tinked with ClaudeCode for an hour or so until I have exactly what I need. It takes less time than trying to compare 10 similar products, none of which have the exact specifications or features that I need.
I think there's still an underestimated burden to vibe-coding an app for a non-software engineer. I'm not recommending my parents vibe-code apps to solve problems, so I think the market is smaller.
But Roberto's use-case is definitely more sane than most.
I assume the learning curve will get shallower over time. Onboarding is better than ever and will only improve. Lots of 70 and 80 year olds on Facebook now, and future Facebooks will verbally handhold you as you log on. "Press the red button that I just highlighted... great job!" etc.
> Then just yesterday, a friend of mine was telling me how he got tired of paying for Typora and decided to vibecode his own Markdown editor
But typora is actually one time purchase and one of the rare apps that is priced well with good business model.
They have probably best RTL support and I wanted like your friend to write my own focused markdown editor with RTL support using clause and made some progress but realized that the time and cost of doing this is not worth it. I just paid typora a week ago for $15.
But I understand the point and I use Claude to hack together personal tools all the time.
Yeah, I was confused by that as well. Typora is sold as a perpetual license for 3 devices at $15. I don't understand why their friend would be tired of paying for it.
I did this recently at the company I work at. Someone suggested GitBook, I 'Vibe coded' an internal docs website in under and hour. Does what we need, looks good.
Unless the app has a large community/network and is just a SaaS with some offering, it'll be very easy to replace it.
I'm doing something very similar (creating my own apps for personal use), but I'm creating iOS apps primarily.
Here's what bugs me: I cannot permanently install my apps to my iPhone because of Apple's walled garden. I need to reinstall every 7 days and constantly re-confirm that I am a "Trusted" developer.
I know I can pay Apple 100 USD a year for a developer account, but I bought this phone outright 7 years ago, I own it. (Obviously, I clearly don't in this case.) /rant
I had never written an iOS app until a couple months ago and was initially very put off when I hit the same wall. The alternative is to host on a cheap VPS and find some way to prevent other people from using your app. When you cost it out, it's close enough to the 100 bucks a year for the Apple account. However, the kicker for me is the side loading process. Way too much headache compared to a deploy script that has my changes running nearly instantly.
Has anyone tried, on a large scale, designing the architecture of an application or writing behavioral tests (which effectively is designing the app through testing) and given the LLM the task of writing the implementation details?
Does that work better for maintainability than letting it decide on its own what the architecture should look like?
The SaaS business model took things too far anyway. Everything is a subscription and it gets tiring quickly. I am glad that LLMs can replace crappy SaaS with crappy code now.
I replaced a whole bunch of these with one shot prompts for shits and giggles.
This is the same for me and I've not written code for years since I was a kid in school.
I vibe coded a webapp that I was paying yearly for and the version I made does everything I wish the app I paid for did as it's 100% personalised to me.
I've been thinking for awhile that this is going to be the future and I'm already starting to think of more things I will create.
Software is a manifestation of someone’s knowledge of and experience in and ideas about how a thing should work. We learn from the software we use, we benefit from everyone else’s ideas, we benefit from the hundreds and thousands of hours other people put into understanding a problem to design a solution. My workflow is better because of the incremental improvements made by developer after developer year after year. Would we have Claude Code if our foredevelopers hadn’t spent thousands of hours deep in thought, obsessing over every last detail?
Building all the software you use yourself, whether by hand or by vibe coding, cuts you off from the world.
I have no philosophical objection to vibe-coding apps for yourself, but personally, I wouldn’t be 1/10th of the engineer I am if I wasn’t constantly exposed to the work of others.
For some, this trend worries software engineers — who needs software if they can vibe code it themselves? — but I am much more optimistic. I think people will start valuing good software a lot more. Claude code can deliver the first 90%, but we all know it is the last 90% that differentiates.
I like to say "my code is 200% vibe-coded; the tricky bit is figuring out which 100% to keep".
Decisions matter, both technical and product ones. LLMs don't make as good technical or product decisions as I would, and the way I work with them tries to maximize my strengths and the LLM's strengths. I don't know if I succeed, but it's better than "make me an app like X" as a prompt.
Your entire post is self selection bias and survivorship bias.
SWE field is one of the most cognitive dissonant social groups; cries foul at the slightest whiff their free speech and agency is being put upon; seeks to reduce blockers to their productivity, fewer PMs! Less management!
Now complains about users using their machines without having to block on an SWE.
Insert that quote about how someone will not see the obvious if their paycheck relies on them ignoring the obvious.
Here come LLMs and all they can accomplish with a few arithmetical rules instead of the arbitrary semantics of an SWE; watch as SWEs block social evolution away from disrupting software engineers.
As an example; "protected memory", among many other individual software problems, is an access control problem mired in old semantics relative to OS monoliths.
Didn’t see you all halting as you decimated travel agent jobs, retail jobs, etc etc. Technology advancement must now stand still after centuries of evolution? The self selection bias is as obvious as Trump's.
"Transportation, like software, is accumulated knowledge. The horse embodied centuries of breeding, training, and hard-won understanding about terrain, endurance, and failure. People learned from the horses they rode. Travel improved through incremental refinement, generation after generation. The automobile didn’t appear in a vacuum.
Building all your transportation yourself—whether by breeding horses or assembling a Model T—cuts you off from that accumulated experience. You lose the benefits of thousands of hours spent by others thinking carefully about the same problems.
I have no objection to Model Ts for personal use, but I wouldn’t be one-tenth the traveler I am without constant exposure to well-bred horses.
Some worry cars make horses obsolete—who needs breeders if anyone can buy an engine? I’m more optimistic. As cars proliferate, people will value good horses more. A Model T gets you the first 90%; it’s the last 90%—judgment, robustness, and adaptability—that differentiates."
> Building all the software you use yourself, whether by hand or by vibe coding, cuts you off from the world.
No one is doing that. In foreseeable future I don't see people making their own OSs, browsers and drivers. Workplaces never ditched Offices and Windows for the open source counterparts and they are certainly not going to do that for vibe coded solutions.
> I think people will start valuing good software a lot more.
How will people determine what is good software and what is not? Even experienced engineers can't tell just by looking at the final product.
Some of the most solid rock-solid applications I see were built years ago and still look primitive (native Windows 7 controls, etc). Many of the worst, bug-infested anti-user software looks slick and modern.
> Claude code can deliver the first 90%, but we all know it is the last 90% that differentiates.
My experience with trying to complete that last 10% of a CC generated project is that it's all very alien looking; very uncanny-valley vibes, and I have serious velocity issues because of the lack of coherence.
The prevalence of this "personal vibecoded app" spirit makes me start to wonder if an "App" is the right level of abstraction for packaging capabilities. Perhaps we need something more "granular".
I see the sceptical comments, but no one says this "vibe-coded" projects/apps/tools will be ready for your customers. It basically scratches the itch for the given users/company/whatever. Also, it doesn't have to be fast, stable or handle 1_000_000 concurrent users. You don't have to worry about that.
Not everything has to be a SaaS, but I don't think all SaaS apps can be vibe-coded to a weekend project.
If it is solving my issues and problems, why do preaching about the merits of a proper product or paying. I'll pay for what I see value in, and vibe-code where I don't see the benefit of paying.
Maybe I miserably fail and get back to paying to product. It's all good, I take that responsibility while I start my vibe-coding session.
147 comments
[ 3.0 ms ] story [ 106 ms ] threadIt used to be that you offer subscriptions only if there are ongoing costs, and a one-time payment if not (utilities, local, etc). SaaS kinda ruined that.
I'd welcome a boom in DIY vibe-coded utilities for personal use.
Sometimes you just want an app does X and Y, but not A, B and Z.
I also don't think any particular idea is off limits for making a profit, if you do something and you do it well, you can charge a fee. But if the free hobby version is better then you best find a way to justify the price.
I think that many existing apps with huge userbases will gradually lose users as the models become better and better. Their biggest advantage is that people don't like change, and thus having to e.g. export data from some tools etc. seems to be a hassle not worth $5 a month. 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.
On the other hand, new products will have a much harder time to gather a big userbase. Whenever I'll see a launch of a SaaS asking for $$$, the first question I'll ask myself will be how long it will take LLM to recreate it. And for most cases, I imagine that the time it will take to get 80% of what they have is a few vibe coding sessions (as most newcomers will probably have used LLM themselves to code it up).
Vibe-coding accelerates the destruction of basic (closed-source) apps charging a subscription for features that offer little to no value whatsoever.
Second of all, all of these SaaS apps that don’t actually have a need for recurring charge probably should be paid one time. I don’t use Loom — I use CleanShot X and it was a one-time $30 payment and has a lot of great features I benefit from. I can’t reimplement it in $30 of tokens or $30 of my time.
But for an app whose use case doesn’t change and is recurring for no reason? Yeah there’s probably not much value in recurring payments outside of wanting to support the developer. I pay a lot of indie devs out of the goodness of my heart, and I’ll continue to do that.
But the value for “SaaS apps” without clear monthly costs should have always been under scrutiny.
It should have been, but the number of people qualified to offer proper scrutiny has been low, and those people have largely been occupied with bigger things. Or they were making those apps and had a conflict of interest.
The point is that now that vibe coding is at a level where it can identify and put together off-the-shelf components, and there are all these end users that don't really care about standardization (it's not like their SaaS products used open, interoperable standards in the first place), the ability to compete with those offerings has exploded.
if you want future updates, you pay for another year of updates (discounted, of course, for loyalty).
or is it more compelling to just have one clean, flat, lifetime rate?
At least for games I think it's much too late for the one time purchase model unless you're part of a pro studio making relatively big games.
You pay less tax to them when you do subscriptions rather than one time payments, if I recall especially with Apple Store (something like 30% first year, 15% the second year of subscription).
This is why 120$ over 10 years (1$/month) is more profitable to companies than 120$ in a shot.
Yes, but it's almost one time payment. Your own personal use case is usually narrow enough, and you don't need to support different OS/browsers. You can vibe code it and just forget the fact it's coded.
Actually it's the best use case for vibe coding (the strict meaning of this word) - when you don't plan to maintain the codebase anyway.
Probably not.
I also paid for FreeFileSync (the donation version) instead of rolling my own local backups (across drives), as well as MobaXTerm because I really like their UI/UX and so on. Software that others have developed and supported for multiple years, which has been already tested by a lot of folks thoroughly across their usecases is probably a good bet, doubly so if you can buy it (or I guess choose to support the devs) instead of renting it, the difference being that in the latter case you're not in control.
At the same time, 30 USD gets you about (assuming 85 input and 15 output split, which approximately matches my stats across months):
From: https://pricepertoken.com/(actual figures would change with the input/output proportion, it matters a lot, and also any caching)
Not really enough to build serious software, but definitely quite the bit of help along the way!
Or if you go with subscriptions, it can vary even more, even if will cap how much you can do per day.
For example, if you pay 50 USD for Cerebras Code, you get 24M tokens per day, so that'd be close to 730M tokens per month. They're running GLM 4.7 which isn't SOTA in my experience, but is somewhere around Sonnet 4 and therefore actually quite capable: https://z.ai/blog/glm-4.7 (my experience might not match the benchmarks, but either way it can be good enough for most stuff out there)
For a decent percentage of software development, maybe where you want a feature nobody else out there has, AI can help you get rid of enough friction and lend enough help along the way, to maybe make it worthwhile. The caveat there might be that you have to treat the expense of your own time as something you do for the enjoyment of it (building something, or the delayed gratification of benefitting from using the software).
And it is getting better at a pretty rapid pace.
If you need $1M/y in subscriptions to build your software, you'll be outcompete by solos who needs $60k/y and don't care about the 100% churn of a one-time fee.
This is simply market optimization when the marginal cost of producing the good falls.
Some of these things are the feeling of "getting a deal" or "screwing the system" and people can spend their time in whatever way brings them joy. I don't want to be a "markdown editor app developer" or whatever and would rather work on more creative endeavors. In the end, we give our time to get money and then trade our money for time but time is our only limited resource.
Previously, if you wanted to rig up a screen recording app in a few minutes you'd use Linux and specifically one of the minimal desktop environments like i3 or sway. Then you'd wire up a few command line utilities (slurp, wf-recorder, etc) and get the exact experience you want. These small unix tools allowed the greater ecosystem to just cobble together what they wanted without too much hassle. I've done exactly this!
This is the exact mindset that keeps people away. They'd prefer to NOT maintain their own video recording software THANK YOU VERY MUCH. So you get people who go to Mac OS because there's always a slick solution for a couple bucks and you never have to be TOO fiddly.
This doesn't destroy the market for people in the latter camp, but it DOES open up the market for people in the former.
And this is comparing to being subscribed many years in a row. With SaaS you can unsub and sub only when you need it again.
With your side project - a weekend of your life is invested and you will never get it back.
This is the worst use of your time if you measure it in $. If you make it for fun - sure. In all other terms it is a complete loss.
Subscription apps often have to target a wide userbase. However, most users only need a small subset of the entire feature set, and would be better served by a tailored version. This means that vibecoded apps can get away with being much less complex (specific featureset, no login etc), while still being more useful.
I have also created tools with LLMs that are exactly tailored to what I need, and still much more polished than what I could do without LLMs. Will have to think about if there is anything else I can do this with.
cheers
From the repo here, it looks like its just using swift command line tools, which might just work well enough with cursor/vscode/etc. for small projects. You won't have Xcode's other features but maybe thats fine for an agentic-first development workflow.
We can now produce products and apps that are tailored to our own preferred ways of working.
Regardless of the cost of generating them (which can be as low as $20 per month for a ChatGPT Plus subscription) or the effort involved (sometimes less than an hour of “vibe coding”), we’ve reached a point where the resulting product can be significantly more valuable than the existing product, service, or subscription it replaces.
That's way too much money. The opencode default models are free
That’s the whole point - there’s no need for it to be a product when you can do it yourself, and it’s the death knell of products like this.
At the same time, Apple better wake up as the quality of the App Store (such as it is) is about to get much, much worse as a flood of vibe-coded apps make it onto the store. These will likely crap out in spectacular ways and, as I say, bring user's experience with the App Store in general way down.
It's like when Amazon intermingled drop-ship sellers on their platform.
(Oh well, not my problem.)
List of projects mentioned before: https://news.ycombinator.com/item?id=46716805
But Roberto's use-case is definitely more sane than most.
But typora is actually one time purchase and one of the rare apps that is priced well with good business model.
They have probably best RTL support and I wanted like your friend to write my own focused markdown editor with RTL support using clause and made some progress but realized that the time and cost of doing this is not worth it. I just paid typora a week ago for $15.
But I understand the point and I use Claude to hack together personal tools all the time.
Here's what bugs me: I cannot permanently install my apps to my iPhone because of Apple's walled garden. I need to reinstall every 7 days and constantly re-confirm that I am a "Trusted" developer.
I know I can pay Apple 100 USD a year for a developer account, but I bought this phone outright 7 years ago, I own it. (Obviously, I clearly don't in this case.) /rant
Does that work better for maintainability than letting it decide on its own what the architecture should look like?
If so, what is your setup/workflow?
I replaced a whole bunch of these with one shot prompts for shits and giggles.
I vibe coded a webapp that I was paying yearly for and the version I made does everything I wish the app I paid for did as it's 100% personalised to me.
I've been thinking for awhile that this is going to be the future and I'm already starting to think of more things I will create.
Building all the software you use yourself, whether by hand or by vibe coding, cuts you off from the world.
I have no philosophical objection to vibe-coding apps for yourself, but personally, I wouldn’t be 1/10th of the engineer I am if I wasn’t constantly exposed to the work of others.
For some, this trend worries software engineers — who needs software if they can vibe code it themselves? — but I am much more optimistic. I think people will start valuing good software a lot more. Claude code can deliver the first 90%, but we all know it is the last 90% that differentiates.
Decisions matter, both technical and product ones. LLMs don't make as good technical or product decisions as I would, and the way I work with them tries to maximize my strengths and the LLM's strengths. I don't know if I succeed, but it's better than "make me an app like X" as a prompt.
SWE field is one of the most cognitive dissonant social groups; cries foul at the slightest whiff their free speech and agency is being put upon; seeks to reduce blockers to their productivity, fewer PMs! Less management!
Now complains about users using their machines without having to block on an SWE.
Insert that quote about how someone will not see the obvious if their paycheck relies on them ignoring the obvious.
Here come LLMs and all they can accomplish with a few arithmetical rules instead of the arbitrary semantics of an SWE; watch as SWEs block social evolution away from disrupting software engineers.
As an example; "protected memory", among many other individual software problems, is an access control problem mired in old semantics relative to OS monoliths.
Didn’t see you all halting as you decimated travel agent jobs, retail jobs, etc etc. Technology advancement must now stand still after centuries of evolution? The self selection bias is as obvious as Trump's.
Building all your transportation yourself—whether by breeding horses or assembling a Model T—cuts you off from that accumulated experience. You lose the benefits of thousands of hours spent by others thinking carefully about the same problems.
I have no objection to Model Ts for personal use, but I wouldn’t be one-tenth the traveler I am without constant exposure to well-bred horses.
Some worry cars make horses obsolete—who needs breeders if anyone can buy an engine? I’m more optimistic. As cars proliferate, people will value good horses more. A Model T gets you the first 90%; it’s the last 90%—judgment, robustness, and adaptability—that differentiates."
No one is doing that. In foreseeable future I don't see people making their own OSs, browsers and drivers. Workplaces never ditched Offices and Windows for the open source counterparts and they are certainly not going to do that for vibe coded solutions.
You can rest assured.
How will people determine what is good software and what is not? Even experienced engineers can't tell just by looking at the final product.
Some of the most solid rock-solid applications I see were built years ago and still look primitive (native Windows 7 controls, etc). Many of the worst, bug-infested anti-user software looks slick and modern.
> Claude code can deliver the first 90%, but we all know it is the last 90% that differentiates.
My experience with trying to complete that last 10% of a CC generated project is that it's all very alien looking; very uncanny-valley vibes, and I have serious velocity issues because of the lack of coherence.
So most software is 180% of 100%? :p
Not everything has to be a SaaS, but I don't think all SaaS apps can be vibe-coded to a weekend project.
If it is solving my issues and problems, why do preaching about the merits of a proper product or paying. I'll pay for what I see value in, and vibe-code where I don't see the benefit of paying.
Maybe I miserably fail and get back to paying to product. It's all good, I take that responsibility while I start my vibe-coding session.