alt Hacker NewsNo Skill. No Taste
Comments
While I think there are plenty of reasons to be unhappy with this particular shift, I find myself struggling to care about it in particular. I get the impression that things will just be… different now. When finding an app for your phone, you might have to skip a few obviously vibe-coded ones to find what you actually want. But that’s not much different from before, when you’d have to filter through ads and apps that haven’t been updated in 6 years.
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.
The hard thing about coding isn't really the code. It's the data. Both data at rest and data flowing in and out of your system.
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.
I suspect that in the future, apps will be like these blogs: most people will have them. The app authors will they they are great, most won't be great. Some will be great and hugely popular, many will be great but nobody will know or about them, because the attention economy is always hard.
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 of this mythical "taste", at least as hinted by the article, can be acquired rather easily—by looking into what's already out there before jumping to creating.
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.
For all of the "saturated market" talk, I always think of the following examples:
- 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...
I respect the feelings behind the post and I agree with a large part of it. I’m inclined to disagree on a few points made. The core problem is outsiders without taste are showing up in a space where there is a long history of dues paid by the current occupants. But how is taste developed? It’s not innate, unfortunately it’s a product of the long ugly process you are currently witnessing. Think back to the first program you were proud of and judge it with today’s eyes.
Ironic that you complain about people posting a to-do app because it's so common, and proceed to post the 100th AI rant of the day with absolutely no original thought in it.
>The overall suffusion of this [slop] into the broader scene rightly has the more sensitive of us up in arms. It's noise, it's spam, it's a perversion of the years of skill we've spent accruing.
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.
Application design is still a challenge. I had Monday off and vibe-coded up an app that I've been wanting to use for years. The thing is, I can tell it's going to be challenging to make it something sticky that I actually use.
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."
Yes, a positive from this is those with authenticity and taste will shine. Self-expression will be a form of resistance and we'll see a lot less homogenisation across things like writing, ui/ux, animation, individual websites, blogs.
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.
What I hated most about the NFT culture was being approached by people who wanted me to make NFTs out of my photographs and visual art.
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.
Hmmmm, where on the taste scale would you put making text unreadable when selected?
I am happy with all the apps I am creating only for me. Nice if someone else likes them, but I create them for me. That now takes 1 day from idea to playstore instead of weeks to months. I don't really care if someone calls it slop. My life is better for it so I shall continue.
I get exhausted very quickly reading stuff about AI by people who think there is some secret language of prompts or some better model or better framework which will make them successful at developing things.
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.
"You can't scratch your own itch because of reasons" is not a great message. Sure, let's tell people they can't become rich off their pet app, but we shouldn't shut it down.
Kind of meaningless if you let "taste" be a vaguely-defined term. Like, what do you mean by "taste"? How is it a differentiator? Does Apple have taste? Is the reason one open source app is better than the other because the devs of the first one have more "taste"?
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.
I have no taste with web design and haven’t touched web dev in a decade. I absolutely hate web development and usually delegate it.
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
If you vibe coded any software, by definition, it means you have no skills and no taste.
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.
Here's another thing: I think spending too much time with generative AI makes your taste worse, by habituating you to stuff that's pretty bad.
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.
I wish some taste had been used in the choice of font. Courier New is rather unpleasant to look at for prose.
So it’s taste now, eh?
The last redoubt of the old world.
Reading the title made me think about the USA King. You know the orange one.
Lol last night, on a forked and accessible version of Termux I vibecoded into existence, on an Emacs and Emacspeak vibejiggered to work on Termux, I vibecoded, with gptel-agent, an Emacspeak package to make it speak when tool calls are being asked for by the model, and automatically speak any explanatory text after all the tools are called and edits are made. All on my phone with a Bluetooth keyboard. It's so easy, even a blind man can do 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.
This is the most awkward comment section I've read in a long time. Programmers talking about 'taste'... ouch.
"The only problem is, no one needs their dream application"
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
Why the text is so small? Or it's just me
I've seen this played out 3 times with none devs i know personally. Somebody had an idea, starts vibing and feeling like they're making insane progress and cool stuff, but what can most generously be summarized as: a big Meh.
> 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.
This is entirely a problem of AI sycophancy. You would expect a system that has expert level knowledge in so many domains to be overly cynical and straight up tell you that "No, there is no market for a language learning app, Duolingo doesn't teach language it uses dark patterns and fake testimonial to get people addicted"
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.
This blog post is on point, but it's somewhat interesting to see developers realizing that taste matters. That's fundamentally the idea behind product management as a role within a company, to be an arbiter of taste and to understand customers and the problem space so thoroughly that you have the right feel for things. Taste is often the most important element of product-market fit. Realizing that the vibe app you built doesn't have a need to exists is all about finding a failure of product-market fit.
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.
The site seems to be falling over. Is that a skill or taste issue?
basically means you let the LLM design for you and you had very little detail control over the outcome other than to keep rolling the dice till it hits you.
If only we had some kind of voting system that could uplift the good stuff...one can only dream...
Not sure if you'd consider this a counterpoint or just proving your point, but in the sea of AI slop there's also a real chance for people to create things that they couldn't before - my 7 year old is now able to nerd out and create games using claude even though he's just barely learned to read: https://www.kidhubb.com/play/meteor-dodge-solarscout64
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.
[dead]
There's been a lot of discussion around in the future how "taste" will be the only differentiation / moat (recently watched a good video about the gen-ai music industry), as everything will be trivially easy to recreate. But your vision and how well you execution it... and the nuance involved in getting every minor detail correct is much harder (and something the LLM is exactly average at). I recently experienced this while vibing the duckdb vscode extension "I always wanted". Code is 100% LLM generated, but I think I probably have well over 1000 turns of conversation at this point to make every detail exactly as I want it.
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.
I don't know man. I'm writing a flashcard app, and I like it. It makes me happy and it works the way I want. Exactly how I want. BC I could never get into quizlet. Whatever. Maybe others will like it, maybe not, I don't care.
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.