No Skill. No Taste
blog.kinglycrow.com
blog.kinglycrow.com
Taste is subjective. Having 1 million todo apps, great. Maybe someone I know will find one they like and tell me about it. Maybe I'll find one that doesn't suck. Maybe I'll just make my own.
One thing I won't do though, is complain about how there's now 1 million todo apps that aren't up to my standards. Everyone being able to make their own apps however they want is a beautiful thing.
Seems to be what the essay implies.
It’s super easy to talk about who has taste or not in the abstract. A lot harder to tell someone straight up they have no taste because of some idea you have.
Posting something to SHOW people without considering how people may want or need what you're showing is just bad etiquette anywhere frankly. If you're building for yourself that's great, maybe qualify it in your post because otherwise it's free game to judge poorly. Spam is inherently unwanted content, you don't get to decide what is wanted content the collective community does.
It's something many of us have learned building software for years that all the new people building are going to figure out for themselves. Just because you can build it doesn't mean anyone will care if you're trying to show it off and with the flood of new apps, it's fair game to discuss.
Edit: all of us -> many of us on the last paragraph
Right and my point is you (or i) will never be consulted, it happens emergently through community dynamics. No one sat in a group and decided this, Show HN in particular has always been selective. Different things are interesting to different sub groups and they select for different things. Show HN is not homogenous. My argument is not to not post, it's to post knowing who you hope to reach and why it would matter to them, don't just post to post, that is a large part of taste to me.
Might be unintentional then, but the language in your post comes across as a textbook case of gatekeeping.
Similarly, I should have done more in the post to steer people way from the perception I'm shitting on them for building for themselves, that's great I have plenty of personal projects running at home that are just for me, if I ever decided to share them out I'd work to make sure its ready and valuable for people to receive.
"Things that don't consider their audience get ignored or are perceived poorly."
The only thing I stated was a simple thing which is almost immovable fact at this point, that someone posting should be considering that.
My opinions are actually a lot stronger than anything I've written here and if it was about them the post would have been radically different.
A feeling of self righteous indignation? (I joke)
Anyway, I appreciate your take, but yes I think we just take fully different sides. I really am having a hard time seeing it from your perspective, but I respect that we attempted to get through to each other. Cheers.
Gate keeping isn’t inherently good, but I think Trump is essentially the right wing outcome of zero gate keeping.
Second, I've founded several companies, had customers, put out products to be judged by the market and raised capital. I'm more than qualified to put out an opinion here. Been there done that.
The people I have a problem with are the ones who have neither but nonetheless find their ways into positions of power and influence where they proceed to make everyone else’s lives varying degrees of miserable.
OTOH I have huge respect for anyone who makes their thing for their own satisfaction.
(emphasis mine)
Sounds like (good) taste to me!
Like you mentioned, ofc nobody wants ugliness.
But "good taste" in software can mean things that are not just decoration. And presentation is not irrelevant because it is our interface to any software.
It's far more than "frontend" or even "how things look like".
Words like "user story" are made from grains of truth!
No. Silence is better than noise.
If I spend twenty years subsisting solely on a high sodium cup-of-noodle diet, get severely impaired under the influence of everclear while trying to use a straight edge razor for the first time, hang up a white canvas, and spin around like a whirling dervish yard sprinkler and then display this finished piece next to Jan van Eyck’s The Last Judgement - we’ve long since left the realm of pure subjectivity.
I'm being silly but I've always thought that the "taste is subjective" argument is not very compelling. Taste, if not entirely objective, at least can be measured in demographic thermoclines.
Okay, but so what? "Taste is subjective" is meant to defend the existence of some thing. "Just because you don't like it doesn't mean it shouldn't exist (or shouldn't be the way it is)." Are you therefore saying the opposite? "Because most people don't like it, it shouldn't exist"?
Taste is not synonymous with personal preferences, otherwise we wouldn't describe some taste as "bad taste" or "poor taste." Rather, to me, one's taste refers to one's power of discernment as to what is good.
We can enjoy cup-of-noodles without conflating our enjoyment as being good taste. I like a lot of things that are fairly trash.
Agreed. As someone who watches an embarrassingly large number of isekai, I'm not going to drink from a public water fountain and call it a pierian spring.
It doesn't need to be able to be described in objective terms to be objective, or rather to matter.
I find that a convenient UI becomes the most important aspect of some applications (to-do list, alarm clocks etc). Getting it to be exactly the way I like it is a benefit by itself.
I've been thinking of making a note taking app for my phone as well. The 10 or so that I've used all have had issues that made me not like them for one reason or another. Eg 16k char limit per note, no searching inside a note, broken bullet lists, long startup time etc.
Judgements of taste, on the other hand, implicate all other humans when they are made. They implicitly demand consensus in a way that is unlike any other subjective claims. This is the only possible explanation for why people will in one breath say, "it's a matter of taste, it's all subjective" and then argue about whether or not The Last Jedi is a good Star Wars movie for hours, if not days, on end. Because the truth is, we are constantly seeking consensus and we usually resort to "that's just your opinion man" when we give up and disengage. But we don't believe that, not really.
According to Kant, "a judgment of taste involves the consciousness that all interest is kept out of it, it must also involve a claim to being valid for everyone, but without having a universality based on concepts. In other words, a judgment of taste must involve a claim to subjective universality." Unfortunately, it's Kant we're talking about, so trying to understand what he meant by subjective universality is a huge headache. Still, his reasoning reflects the way people actually talk about taste better than anybody else I've read.
More importantly, I think that enough time has passed that we can critique poor old Kant on this matter. When he says the taste has no interest in something what he is really implicitly describing is that taste is the province of rich people. If one has to strive or worry or self promote or anything like that, with regard to an aesthetic decision, it is easy to mark as tasteless. In most cases, the people with access to the kinds of habits that allow them to act in matters of aesthetic without interest are rich.
The main reason people drive themselves in circles, talking about taste and subjectivity, and college-educated words for subjectivity is because we don’t want to admit that it is bound up in class and upbringing. That and not the passage of time is why it is so hard to understand Kant on this matter. He’s describing a fiction that we agreed upon so that we didn’t have to talk about the influence of money.
If I was to be charitable, I guess maybe their argument was that Kant only believed in subjective universality because he was rich, but that doesn't make any sense. Both Kant and Hume grew up middle class, and ended up in academia, and had very different conclusions about what "taste" is.
It's just a knee jerk reaction to dead white men philosophers and anyone who is interested in them as a bunch of elitists. That's not an argument, that's some kind of misplaced class resentment masquerading as an argument.
If someone likes what you make it doesn't matter where you come from.
Taste is often advanced as this subjective yet ultimately discriminating notion which refuses to be pinned down. Insistent but ineffable. This idea that you and I know what good software is due to having paid dues and they don’t, and the truth will out, is a common one!
My argument isn’t that it’s class. It’s that this framework of describing taste is PURPOSE BUILT to ignore questions like status, access, and money in favor of standing in judgment.
We are in the middle of an earthquake. The 90s was like this, but it’s bigger. Radical changes in what it means to build software are happening right now. That will without a hair of a doubt result in equally radical changes in what constitutes good and bad work.
Maybe, just maybe, the thing that seems really durable (taste) is already getting put into a blender that’s still running.
Here I don’t know what the trouble is. I’m sorry for calling your phrasing the equivalent of “hafalutin” (a word Marx has used more than twice—he’s dead and white), but what do you expect having come in to cloud the waters with 2 extra syllables to little end?
This dude, Diderot, is gonna make a new encyclopedia of the world with his friends which breaks the monopoly on printed and well-regarded learning that was held by the traditional humanities. He wanted articles about the trades, about objects and engineered things, and he was PISSED OFF that he had to fight for it.
Is this guy's idea of how to organize knowledge "right"? Probably not. Will it light your brain on fire and make you grumpy or nosy or suspicious about categories of knowledge that persist still? YEAH.
This isn't true at all. There's a whole world of artisans and fine artists that range from middle class to broke, and they wouldn't be in that financial situation if they felt like compromising their point of view for money.
Whether or not economic capital is actually transferrable to cultural capital seems to be another debate, but as the old saying goes "money can't buy taste". In fact, a newly rich lower class person marrying a contemporarily poor higher class person seems more likely.
As the abstract states: "Because persons are taught their cultural tastes in childhood, a person's taste in culture is internalized to their personality, and identify his or her origin in a given social class, which might or might not impede upward social mobility." Money can't rebuild the personality that is internalized in youth, but marriage might give your kids a shot.
1. https://en.wikipedia.org/wiki/Distinction_(book)
edit: also to add, the relationship between these is the underlying theme of The Great Gatsby.
c'mon. Are you really going to tell me "ahem dear sir, I found out that this Mr Bourdieu likes him some nuance!" His most famous book is essentially an article ballooned into a monograph via nuance.
Your source does not support your position.
But we aren't here to discuss apparently.
No, no, no! Here on Hacker News, it is apparently forbidden to criticize the dead because "they can't defend themselves." It's seen as somewhere between "cowardly" and "uncouth."
This policy seems to mainly apply, for some weird reason I suspect I would prefer not to know about, to the recently-departed Dilbert guy. But I'm sure his fans would stick up for Kant also!
> "that's just your opinion man"...But we don't believe that
Why not? Many people have opinions I strongly disagree with, but I don't question that they actually have the opinion.
I disagree, it seems to me that most people are seeking validation. In that sense, we don't want some global consensus, but a consensus within a specifically chosen group that proves our membership.
I would like to offer a counterexample: iPhone, when it first came out anyways. Tasteful design is rather so obvious that when you see it you'd say yes, this is what anyone would expect from a "phone". That doesn't seem to be so subjective.
HN is generally considered a filter in industry, or a place to launch and make a hot start. The author is making their comments from the context of Show HN, where we expect some self-filtering, for quality and appropriateness.
What we see in Show HN the last few weeks is slop, submissions where the time from first commit to posting on HN is less than an hour. I've been posting some selections to Bluesky. The fastest I've seen so far is 25m [1]
I fully agree with everything you said and everything the author said. The two are not mutually exclusive.
[1] https://bsky.app/profile/verdverm.com/post/3mf2hygnbkc2o
There are so many problems that people have that have never been important enough to get solutions, that now can.
It's less about taste and more about experience and outcomes now.
The way we built software in the past, including the processes, ceremonies
Vibe coding creates the illusion that code has become far more malleable. And it has, for greenfield, for a game, for a one-off stateless utility.
But most applications of significance work with a lot of data. Data resists the malleability you have with code. At scale, data is expensive to migrate and it's easy to make a mistake that loses data. With distribution, you may have to act at a distance, and write code you hope will work with the data where it is, and follow careful migration patterns like dual writing, fallback read, ongoing rewriting and so on, at a distance.
Distributed or privacy gated data generates constraints that AI can't easily see, can't easily react to. AI thrives on quick feedback loops. Test-first works great. Testing in production only works when it's your hobby project.
In many ways, software businesses are gardeners of data. Data creates stickiness; when customers decide to take their data elsewhere, or create a new stock of data somewhere else, that's when they churn.
I'm not sure the unleashed masses would be happy to be such gardeners.
And there's a deeper point here, about sovereignty. Even if we have the magical data systems of the future, that the AI can do as you say, even though it's hard to execute, and the AI will still do it reliably: what if you tell it to do something irreversible? To drop a column, to combine separated data into one blob. The AI might advise you not to do it, but the AI can't actually fix the problem of bad judgement without removing your sovereignty. And that would be a very dangerous place to go; I would hope, and expect, that we don't go there.
Is there nothing? Great, go ahead and fill the void.
Is there so much that it becomes overwhelming to even look? If so, ask yourself: does your thing have any significant differentiators? Are you willing to maintain it? Do you want the people who come after you to see one more option in the sea, or an existing project made better thanks to your changes?
It's about respecting the time of one another. If I'm looking for a to-do app, I'm looking for a good one, at least in the ways that matter to me. Not for thousands of applications with the same exact issues. And so are you. Nobody needs a million of options that suck. We all want a handful or ideally one that does the job.
Yes, you should do discovery, but that alone is not sufficient to develop taste. Being an also-ran is low taste even if you religiously meet the market expectations by following a pattern. Just like in fashion, you need to understand the rules to know when its okay to break the rules so that you appear fashion-forward, that is a form of taste no differently.
IMO most of the unpleasant truth about taste is that it is really a stalking horse for money and distinction (cf the book of the same title).
It took less than 90 minutes using claude code, I have a testflight I've shared with friends for feedback, and I'll probably put it out there for a dollar once I add a couple more settings.
The built in UIs, syncing, and integrations are really good. It took me a while to realize I didn't need another todo list app, just to tweak the built-ins.
When I see a Show HN around a very popular product concept (like a habit tracker), the first thing I search for is a FAQ or comparison table against other similar apps.
Shallow taste is stuff like popular trends that come and go, and hating the taste of beer until you’ve had it a few times (not saying everyone has to like beer, that’s not the point).
Deeper taste is more like your deeply held cognitive biases. Like a current of a river or the valleys cut into a mountain. It’s the shape of your cognition that determines how information flows through your brain.
Deeper taste is heavily connected to you and your identity. It’s part of who you are. I think most people would agree that parts of themselves change very slowly, and some not at all.
I know there are parts of me that feel the same as when I was a child. To deny the existence of taste is to deny the existence of a “you” that is different from others.
There are long lists of successful programs that market themselves as little more than "like program X, but faster/distributed/higher resolution/bigger map"
I think that's fine.
What I really think is that most of the logical folks here think we ought to be focusing our attention and organizing to maximize the efficiency of app making, and that vibe-coding really blows that up, because there is no way to know what is quality and what is trash without actually having to do the work and figure that out. That does suck, but it's why creators should have blogs, github/bitbucket accounts, etc, to offer up their credibility to facilitate bona fides.
I think the programming industry is going to become a lot more like the indie game industry, where loose networks based on mutual respect start forming and critics review the newest apps, because you really don't want to waste a bunch actually using all the stuff.
It's inefficient, but that's life.
Most people don't have blogs though.
- Restaurant Row in NYC is full of packed restaurants b/c people like variety and the demand is high enough to have multiple market participants
- Clorox is a chemical with a fancy bottle and a lot of marketing. They make $150 million+ profit a QUARTER on this [0]
- As someone once said: if it's visible and people see it as part of their identity, there are many brands e.g. clothes, cars etc. If it's not visible, there are fewer brands e.g. underwear
- The ability to personalize applications has been around for over 20 years but people still want predictable user interfaces so they can share with friends, spouses etc
0 - https://www.wsj.com/business/earnings/clorox-posts-lower-pro...
There's a whole lot of people wrestling with something that is the core purpose of an entire career that is often derided as being useless, and folks are realizing maybe it's the only thing that will matter in the future.
Are the people that make these apps tasteless? Or soulless? Or do they just have no respect for the craft? Probably. That’s not much different than how things were before. I’ve had tasteless coworkers who only programmed for a paycheck. The were perfectly pleasant people to work with, and I don’t judge them in the slightest. Besides, how do you distinguish an excited novice who genuinely wants to get into programming versus someone trying to extract value versus someone using AI to finally bring a hobby project to life? The same way you did before.
Point being, I doubt HN will suddenly stop being discerning or start celebrating low-effort garbage any more than they did before LLMs. The tasteful remain tasteful. The tasteless remain tasteless. And as such, I find myself more interested in directing my AI-related concern elsewhere.
Which makes sense. The reason I wanted to make this app is that there are two very popular paid apps in the same category that I use every day that don't quite feel the way I want them to. It'll be easy to fix the little annoyances and missing features, but there's a feeling that's missing from them as well. I don't think it's wrong to say that I'm put off by a lack of taste, at least according to my taste. I don't know if I can do better, but I'm looking forward to trying, and I love that Claude makes me fast enough that the project has finally tipped from "I'd love to tackle this, but I know it's too big for me" (which is what I've been thinking for the last 5-10 years) to "I can make a credible attempt at this."
AI is actually fine at telling you objective metrics for your field of interest, it's just that people ignore them because they already have the thing they want to do locked in their head. They want to build a skyscraper out of toothpicks and the AI does help them, but the goal remains elusive.
The most important metric in language learning is willingness to communicate, an app (duolingo or flashcard) that lowers WTC is the opposite of a language learning app.
Who knows maybe the old, scattered, personable, decentralised internet will come back - things like MySpace, geocities, sites like this (a lost art): https://www.cameronsworld.net/
Also taste comes from your ability to steer a model instead of having it steer you. e.g. a model suggests a basic pill button, you push back and curse it for its blandness and use it to design something new and novel.
Seeing how predatory these companies are in their scraping and then continuing to publish where they can scrape is the absolute height of stupidity
Would also result in fewer sites with ads -- yay!
Sharing is great. Having everything you share taken and monetized/weaponized is terrible
I'm looking for ways to build community that is resilient against LLMs, both scraping and also contributing. Unfortunately (or fortunately depending on your point of view) that means it can no longer happen online
One of the first uses I discovered was to have it identify my own blandness. I'll give it a general scenario from my writing and ask it for ten resolutions to that scenario. If my own resolution appears, I realize at best my resolution is bland and at worst cliche.
I then wait a few days, and then use a couple of systems (embeddings, deBERTa, etc.) to rank comments by novelty against the LLM-produced replies.
1) make it difficult to select or copy text, 2) and even if you manage it, you discover that the actual text in the webpage source is encrypted,
mainly so they don't vibe-code their homework assignments. So I guess it rates high on my taste scale.
(kidding of course; but you can always bring your own stylesheet to the party)
It’s hard to say precisely what the effect is, but I will say that students performed better this semester on written exams than ever before. Lots of confounds, of course, but I do think the emphasis on having to retype things yourself forced students to really engage with the material. That said, the number of students coming to office hours was WAY down. Given that I’ve taught this course many times over the years, there’s really only one explanation for that.
At the time I was very much craving feedback and validation but I wanted honest validation, I knew some of what I was making was really good and some of what I was making was crap -- I wanted validation from people who could tell the difference, not from people for whom it was all the same.
I'm left with the same feeling I have when I read blogs by celebrity managers and developers like DHH or Spolsky or Graham or Atwood or Yegge, they talk as if you could learn something transferable from their experiences except... you can't. Their opinions about spaces or tabs or whether you should use static or dynamic languages are as good as anybody else's but not better!
The difference is that those guys actually made something and sold it, whereas the vibe coder almost made something.
People who make something significant with AI are going to do it because of all the others skills and attributes they have: good taste, domain knowledge, modeling, knowing what good code looks like, knowing what good user interfaces feel like, etc.
That's why I am not doomscrolling X to see what celebrity vibe coders say they are doing right now.
I still tend to go by the advice I read when I was just out of school: If you want to be successful, find someone who is successful, and do what they do.
https://spencer.wtf/2026/02/20/cleaning-up-merged-git-branch...
https://www.justinmklam.com/posts/2026/02/beginners-guide-sp...
https://www.caimito.net/en/blog/2026/02/17/web-components-th...
https://learn.pimoroni.com/article/overclocking-the-pico-2
are about reproducible results and are written by people who know what they are talking about and are situated in a frame which doesn't distort their value.
A report on AI coding is usually like a report on what happened when you spent an evening playing the slots -- it's not at all reproducible, half of it is that raw luck (you win some you lose some) and the other half is that "dark matter" of skill and taste which of course is captured in your prompts, particularly as you feed back to that randomness. I can scan those other articles and quickly pick up something cool, "vibe coding" reports just exhaust me.
Past that are all the posts where people who don't know what they are talking about make big pronouncements about what it all means or how it will go and even if they are the likes of Ezra Klein or Scott Alexander it noise and not signal. You could throw a high-signal article into this arena and people wouldn't recognize it for all the noise.
So yeah, I go to the /new page quite often and find there are 22 articles about AI (probably 20 are noise) and 8 articles that aren't about AI and I will upvote the 8 even if some of them are noise, at least they are noise about something that's not AI.
I think it's a sort of slot machine effect, you get used to losing and when something goes slightly well you wildly overestimate how good it is. You see this with visual artists who got way too into image generation. Because they have to spin the wheel a thousand times to get one good output, they have totally habituated themselves to a lower standard by the time they emerge from the AI mines clutching their one good output, because that output is not all that great.
It looks good compared to all the failed generations though!
Also, spending all your time cranking the slot machine handle and occasionally winning convinces your brain that you have a magic ability at cranking the slot machine handle, when actually you were at best slightly lucky. So you get people who convince themselves they are geniuses at using AI when they are actually average or slightly above average.
Is this actually true? I know of no artists nor programmers who used to have strict requirements, careful eyes and "good taste" who after playing around with AI suddenly dropped those things, that'd be very against basically their personality.
Do you have any concrete and practical examples of any currently public artists you've seen be affected by this?
https://www.decodingeverything.com/darren-aronofsky-ai-slop-...
(Also, this website when Show HNs with slop READMEs get to the front page and nobody seems to notice that it's written in grating Claudese.)
Or you know, it's just not that important whether the README is written by Claude or not.
Generally speaking people don't use a service/library for the author's ability to write excellent proses.
I'll read a badly-formatted readme written by a human with far more interest than a formulaic LLM summary of a project. But it seems like nobody even notices a readme is slop because it has nice Markdown, and my best guess as to why is that people have become habituated to this stuff.
I think this is incredibly wrong. I'd even go as far to say that a well presented README/website is the second most important factor, only behind network effect.
On the contrary, a lower barrier for skill could bring people from other disciplines with excellent taste to make beautiful, even if technical imperfect, pieces of craft.
> lots of amazing engineers have an awful taste in everything that is not their immediate field of knowledge or interest
which one is it?
And because it's all controlled by me, I can tell it how to have the package speak, what it should ignore, and I'm not stuck with whatever some sighted person at some big company thinks a blind person wants. Everything should at most be open source, and at least be hackable.
All that to say, AI has helped me out a ton. Now I can be as productive as Emacs, and a Linux terminal, and maybe one day a Linux GUI with real Firefox and such, allows. And it would have *never* happened without AI.
So let's please do continue bringing on the AI. Make it smart and local, so I can have continuous AI descriptions right on my phone, with the ability to screen share or even agent-control my phone to get around inaccessible apps. Oh and fix AI app accessibility so the app sends output to screen readers when I type to it cause I hate talking to my phone and not every blind person wants to speak all the time. Ugh I hate that stereotype.
I am not sure if you are able to use it, but I saw Droidrun.ai (https://www.droidrun.ai/) the other day, and agents should be able to drive the phone.
Seems like a philosophical article, but rather than exploring it deeply, it kind of just abandons it at the "hey man, everyone can create apps, so you better have that taste, aaight?" paradigm which is dangerously close to just common sense.
So like you definitely probably can get pointers from people in your specific niche and if you've been in that niche long enough you've probably developed some level of taste and feeling for what people in that group like and need.
That's just the programmer/logician in you screaming "unknown feeling!" :)
Programming (for me at least) is as much of a creative endeavor as it's one of logic. You can train yourself to at least recognize "good" from "bad", even though it's much harder to teach yourself how to go from "blank" to "good", or even being able to actually define why something is better than another thing. Sometimes it's literally just "vibes" and that's OK.
If you're unable to train this feeling in yourself, maybe the best course of action is to find someone you can tell is able to better use that particular skill, and ask for their feedback.
Same can happen with code. People may talk about readability, maintainability,… And it can be hard to improve in those aspects. So you read a lot of code that is lauded as good, figure how people goes from ideas to a written version of it, contrast it to your approach, a d reflect upon that.
If you like it the way it is, then guess what, you do have taste, tell them to fuck off and just keep it the way it is.
The difficult part is being honest with yourself about why you like it the way it is. If you do honestly like it for what it is, then others probably will too, no one is really that unique. If you like it because you put a lot of effort into it, then you're just letting your emotions lie to you.
It’s like a well written prose vs a drunk’s rambling. They could describe the same scene, but one is much pleasurable to listen to. Or strolling through a well-tended garden vs walking in a landfill.
So it’s subjective, but you know instinctively what you prefer to work with.
And that is my central gripe with this piece--it doesn't care about the details and handwaves everything bad as having "bad taste." That is fundamentally lazy imo.
So the act of presenting and the judgement by others are what qualify the whole “taste” thing. The judgment is not yours to make, and presentation (either voluntarily or not) is all that needed for others to form an opinion.
So your private code that no one else has seen? No one cares. The repo linked to your Show HN post? You will be judged based on that.
Imagine the scene from Ratatouille, where Remy explains "taste" and the brother finds it impossible to understand what it is ("Food is food").
The dad goes from being annoyed that Remy is a picky eater instead decides to put him to work as a taster. Gives him the job of approving forage that comes into the family & protect others from being poisoned.
The reason we say "taste" is because that's the closest parallel.
When it is even more vague, I call it a "code smell".
The technical characteristics appear to be entirely irrelevant. (I'm not sure if taste even enters into the picture.. it appears to be a third category!)
At which point we define taste as two unrelated things: skill in aesthetics, and skill in ux.
I've seen apps that looked amazing (Taste #1, aesthetics) but made me go, "Okay, did they actually try using this thing?" (Taste #2, usability). I think these tastes are completely orthogonal, from personal experience. I think the vast majority of designers suffer from Total Usability Taste Blindness.
(And, though it feels a bit mean to point out, the vast majority of FOSS suffers from a total absence of both. The winning projects only win because they have no competition, they're the only free option available.)
I've grabbed the archive link for anyone with it struggling to load. It's a single replica running with fairly modest settings on my office server so I'm proud it's managed to live so far even with some load time, but will scale up before my next blog post.
The last redoubt of the old world.
> Most of all, there is now an illusion of a lower barrier to entry.
Arguably, there has never been a higher barrier to entry.
The benefits accrue to the skilled. We all got X% more powerful, and those who were already skilled to begin with get a proportionally better outcome.
I vibe coded my dream application, and I use it. I wouldn't really say I _need_ a pixel art editor for Android, but I sure do like it!
Do I really need more than that? Am I not allowed to create my dream app, for me? Nobody needs my pixel art either, honestly I kinda suck at drawing, but I enjoy doing it!
Op needs to get off their high horse and stop shiting on people for making things. Go make something and stop whining
Making for yourself is great, if you make for others you need to actually consider what they need.
I realized recently that slop is not worthless. It actually has negative value! Just think of the Android app store. There are gems there, to be sure, but the gems are washed away by the sea of slop.
On a (consulting) project I’m leading/doing the implementation, it was specifically called out that a web UI was out of scope. But after talking to them and seeing the lay of the land, they really needed a website to manage the AWS implementation and it would help me to.
I put together and ugly internal website that will only probably be used by three or four people. I vibe coded the entire website including authentication with Amazon Cognito. The only thing I personally validated was that unauthorized users couldn’t get to it and that the database user had the appropriate permissions.
That website wouldn’t have been created at all before AI. Is it pretty? Hell no, it looks like something when I wrote an internal website in 2002 in classic ASP. Did I look at a line of code? Nope
It's not the prettiest but he's able to iterate on it and basically build whatever he can imagine just using claude on his ipad with voice transcription.
Of course he will, just not well. The point of the GP is that he doesn't need to learn anything because the AI can understand his verbal instructions.
Posting it publicly is also helping him learn about people - we talked about how no matter what some percent of people won't like it and may even say it's stupid, but that will always happen and it's still worth creating things anyway.
Which isn't diminishing the authors of that prior work either, those same individuals with these new tools would have been able to do more too.
I am extremely excited that your kid is able to do this, and even you sharing it now here isn't like "my child's game is the best game ever look at me" it's thoughtful commentary on the post I've written.
Even if you had shared a separate post on HN proper like "LLMs are enabling my child to build earlier and become involved in tech" or something that would have had thought behind it on why its interesting to other people, in considering other people you're acting in good faith.
My overall point isn't that LLMs generating apps are bad it's that we should consider why what I'm showing to someone else would matter to them in the first place, which you did here :)
Humans learn mastery by doing, not by watching.
I suppose it comes down to whether the most important skill for your kid is to give instructions, or whether it is to actually read and write.
For reference, my kid only just turned 6, and is at the level of reading books without pictures. I'm kinda proud that he reads better, faster and with more retention than kids aged 9, and it didn't come with the ease[1] that "nerding out" on Claude came to your kid.
The question you gotta ask yourself is this: is a skill that takes a 7 year old a day to master really going to make him more valuable than a skill that took a 6 year old 2.5 years to master?
The 6yo who can read can easily do what your kid did, but your kid can't easily do what the 6yo can.
From another PoV: how valuable of a skill do you think "prompting" is when a 7yo who hasn't mastered reading can master it?
--------------------
[1] I started a daily routine when he was 3.5 with the DISTAR alphabet. We did the routine every day, whether it was christmas, or his birthday, even on vacation. Same time, every day.
Anyway, there seems to be this vibe recently that software developers are "gate keepers" keeping the unwashed masses out or something. But nobody was keeping anyone out -- basically all the tools and knowledge are free! That's how these AI's got built in the first place. But I think what we're really seeing with a lot of these "I'm just an idea guy" people is when they get a magic genie to make their idea.. it's not actually very good. Because good ideas often come from struggling and creating, not just from passively consuming, and if you're struggling and creating you're going to pick up skills needed to create even if they're not coming from formal education. And so I kind of distrust a lot of the "vibe" bros because I'm skeptical of people that think they can get to the destination without going on the journey
Personally, it feels like taste only buys you time and taste is easy to copy.
I don't know where this leaves us, but it's going to be interesting/scary to live through what seems to be coming.
Why is it easy to copy?
I too have written a tiny essay on this topic (https://emsh.cat/good-taste/) but I don't see how "taste" is easy to copy, at least I haven't been convinced by any of the arguments people chucked at me so far.
> Why is it easy to copy? I think music trends would be one historical example of this? With software it's a bit more concrete (I'll just make my app function EXACTLY like yours does) and there is less protection from the law, unless you manage to weasel your way into a patent.
But then you've only copied one of their choices made by their good taste, not actually copied their taste. If a new situation arises, you won't be able to make the same choice as they would. Basically, it doesn't generalize.
I think (and hope) this won't be as big a problem in the arts because "authenticity" matters to most people, but I for the software industry it feels very disruptive (assuming the models continue to improve and are accessible).
They won't be able to, but they won't need to either - they can just continue cribbing off the original person, or if they are unable to continue cribbing off the same person, they'll find someone else to crib off.
The point is, for all these people outsourcing their thinking, they will always have someone to crib off.
Inherently subjective, but you can still approximate ‘more or less tasteful’ by how many people respond well to it.
Since many of our likes are driven by our shared culture and physiology, many other people will appreciate such creation (even if they don't understand why exactly they like it). Others will appreciate depth of nuance and uniqueness of your creation.
Opposite to taste is approximated "good" average which is likeable but just never hits all the right notes, and at the same time already suffering from sameness fatigue.
No offense, but only someone without taste would say this ;)
Taste is not easy to copy. If that were true then there would be no bad major Hollywood movies in established genres; yet despite hundreds of millions of dollars spent on the formulaic superhero genre, we still get stinkers like Madame Web or Kraven the Hunter.
If you actually try looking at places where people show off their taste--scrolling through the latest songs on Soundcloud being a great source--you realize that people just pump out terrible stuff without realizing it's terrible. This was true pre-AI, and AI it hasn't made it any less true.
It's similar to the transition from live instruments to the DAW in the music world. The DAW eliminated all physical training requirements for making music, and opened up massive new worlds for the types of music that could be made. The end result was a handful of great things amidst a sea of garbage.
In software it feels different though. If you build an awesome app and want to charge for it, what stops me from just pointing "Claude Epic 2.5" at it and making a pixel perfect replica?
It's the same argument people used to use against open sourcing your code for a SaaS: "If I can just clone the repository and run the service myself, why is there a hosted product?"
There is so much more going on though, from how you run something, to how you can react to changes and how you perpetually try to avoid the spaghetti ball from building, so improvements don't take longer and longer to implement and break other things.
Even if the original code is the same, two operators of that service can lead to two very different experiences, not to mention how the service will look like in a year.
Hope your right! I imagine the truth will fall somewhere in between our difference in opinion