--- title: "Taste Is All That's Left" url: https://daily.dev/posts/taste-is-all-that-s-left-yibj85oi2 source_url: https://notashelf.dev/posts/taste-is-all-thats-left type: article source: "Hacker News" published: 2026-08-06T19:56:35.918Z updated: 2026-08-09T03:14:19.681Z tags: ["productivity", "ai-coding"] reading_time: 11 upvotes: 0 comments: 0 language: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Taste Is All That's Left **[Hacker News](https://daily.dev/sources/hn)** · 11 min read · 0 upvotes · 0 comments ## Summary As AI tools collapse the distance between idea and working software, the traditional barrier of production — the hours of typing, debugging, and grinding through APIs — has effectively disappeared. This shifts the scarce skill from making things to judging what deserves to exist. Taste, defined not as aesthetic preference but as the fast, wordless verdict that separates plausible from right, was always the core of the craft. The uncomfortable corollary: taste was built through friction, through shipping bad work and living with its failures. Removing that friction for new developers may produce fluent generators who never developed the judgement the friction taught. Meanwhile, taste is economically invisible — it slows you down, prevents disasters that leave no trace, and earns no dashboard credit. Drawing parallels to the Arts and Crafts movement's response to industrialization, the argument concludes that when making becomes free, choosing becomes the craft. The human question shifts from 'can I build it' to 'does this deserve to exist' — and that was always the more serious question. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What happens to developer skill and judgement when AI tools can generate working code instantly? The value of production skill does not disappear — it moves. When AI collapses the cost of making things, the scarce act shifts from making to choosing. Taste — the fast, wordless verdict that distinguishes plausible from right — becomes the only skill that cannot be automated or rented back to you. The economics of effort used to enforce a quality floor; removing that floor makes judgement the sole remaining filter. _Engineers navigating what to invest in as AI reshapes the craft find the sharpest takes on daily.dev._ ### How is taste or judgement developed as a software engineer, and can it be learned without struggle? Taste is built through making bad things and being forced to live with their failures — not through consuming good work. The friction of climbing walls, paying costs repeatedly, and sitting with mistakes is the curriculum. Removing that friction for new developers produces fluent generators who skipped the apprenticeship, arriving at productivity without the judgement that the struggle used to build. _Developers thinking through how to grow their craft in an AI-assisted world keep up with the conversation on daily.dev._ ## Community take How the wider developer community reacted, aggregated from 2 discussions and 118 comments across lobsters, hackernews (as of 2026-08-09). **TL;DR:** The community is deeply divided — many commenters dismiss the post itself as AI-generated slop (ironic given its subject), while a minority find the core argument about taste and craft genuinely resonant; the debate over the article's authorship largely overshadows engagement with its ideas. **Sentiment:** 20% positive · 30% mixed · 50% skeptical **The case for** - Several commenters found the core argument — that friction was the curriculum for developing taste — genuinely resonant and worth sitting with. - The fashion/haute-couture analogy sparked an interesting thread about boutique software as a plausible future, where decades of manual experience defines the high end. - The Ira Glass 'taste gap' quote surfaced as a meaningful complement to the post's thesis about taste being built through volume and failure. - One commenter noted that taste in software translates concretely to readability, maintainability, security, and performance — not just aesthetics. **The pushback** - A significant portion of commenters believe the post was written or heavily shaped by an LLM, calling it ironic that an essay about taste reads like 'slop.' - The premise 'the output is good enough' does enormous unexamined work — critics argue AI output frequently isn't good enough, and granting that assumption quietly buries the stronger objection. - The claim that 'taste is all that's left' is seen as reductive hubris — coding was never all there is to making software (SOC 2, scalability, privacy, onboarding, etc. remain hard). - Taste is economically invisible by the post's own admission, leading commenters to question how it can be a viable guiding star when the market can't see it. - The observation that 'everyone thinks they have good taste' makes the concept conveniently unmeasurable and self-flattering. - Several commenters noted the topic has been covered better elsewhere (Kant's Critique of Judgement, Hume, prior blog posts) and the post adds little new insight. **By community** - lobsters (mixed): Discussion is thoughtful and good-faith, with the author engaging directly; the main tension is whether granting 'output is good enough' fatally undermines the argument, alongside a productive fashion/boutique-software analogy thread — though one commenter flatly flagged it as spam. - hackernews (skeptical): Dominated by accusations that the post is AI-generated (with the author denying it), producing a meta-irony that overshadows the substance; a minority engage seriously with the ideas, but the majority are dismissive of both the writing quality and the thesis. **Hottest debate:** Whether the post itself was written by an LLM — and whether that matters for evaluating its argument — consumed more thread energy than any substantive disagreement about taste or AI. **Open questions** - If taste is economically invisible and leaves no dashboard credit, how does a developer or team actually justify or protect it in a market that rewards speed? - Does removing the friction of manual coding genuinely prevent new developers from building taste, or does taste simply migrate to a new kind of friction (prompting, reviewing, refactoring AI output)? - When AI code becomes measurably better than human code, what replaces 'taste' as the human contribution — and is that just moving the goalposts? - Will a 'boutique software' tier analogous to haute couture actually emerge, or does software's functional nature make it fundamentally different from fashion? **Highlights** > As I read this, I was reminded of two quotes. The first is about [the taste gap from Ira Glass](https://vimeo.com/85040589): > Nobody tells this to people who are beginners, I wish someone told me. All of us who do creative work, we get into it because we have good taste. But there is this gap. For the first couple years you make stuff, it’s just not that good. It’s trying to be good, it has potential, but it’s not. But your taste, the thing that got you into the game, is still killer. And your taste is why your work disappoints you. A lot of people never get past this phase, they quit. Most people I know who do interesting, creative work went through years of this. We know our work doesn’t have this special thing that we want it to have. We all go through this. And if you are just starting out or you are still in this phase, you gotta know its normal and the most important thing you can do is do a lot of work. Put yourself on a deadline so that every week you will finish one story. It is only by going through a volume of work that you will close that gap, and your work will be as good as your ambitions. And I took longer to figure out how to do this than anyone I’ve ever met. It’s gonna take awhile. It’s normal to take awhile. You’ve just gotta fight your way through. The second is from [The Ze Frank Show](https://archive.org/details/zefrank-theshow-083): > For a very long time, taste and artistic training have been things that only a small number of people have been able to develop. Only a few people could afford to participate in the production of many types of media. Raw materials like pigments were expensive; same with tools like printing presses; even as late as 1963 it cost Charles Peignot over $600,000 to create and cut a single font family. > > The small number of people who had access to these tools and resources created rules about what was good taste or bad taste. These designers started giving each other awards and the rules they followed became even more specific. All sorts of stuff about grids and sizes and color combinations — lots of stuff that the consumers of this media never consciously noticed. Over the last 20 years, however, the cost of tools related to the authorship of media has plummeted. For very little money, anyone can create and distribute things like newsletters, or videos, or bad-ass tunes about "ugly." > > Suddenly consumers are learning the language of these authorship tools. The fact that tons of people know names of fonts like Helvetica is weird! And when people start learning something new, they perceive the world around them differently. If you start learning how to play the guitar, suddenly the guitar stands out in all the music you listen to. For example, throughout most of the history of movies, the audience didn't really understand what a craft editing was. Now, as more and more people have access to things like iMovie, they begin to understand the manipulative power of editing. Watching reality TV almost becomes like a game as you try to second-guess how the editor is trying to manipulate you. > > As people start learning and experimenting with these languages authorship, they don't necessarily follow the rules of good taste. This scares the shit out of designers. I'm not sure what I make of all this. > — [spc476 on lobsters · 4 points, 2 comments](https://lobste.rs/s/4qfkrz/taste_is_all_s_left#c_b1a4to) > There's a lot here that I enjoy muddling on. And I think taste is very vital. Taste, ambition, seeing possibility: these resonate to me, long resonate, as what I've wanted to see. And honestly: I've been tired of an age of engineers that are beat down, that only want simple, that finding the most blunt approach is the only way. It has felt tasteless. Anti-ambitious. It often is still very sensible and practical and what you should shoot for! But there are also people wandering around now trying much harder! And I am excited for those frontiers! I think it will challenge and shake the foundations that we've accepted as true, as There Is No Alternative, in exciting bold and fun ways. I am however pretty unconvinced by the article. There's a lot that doesn't quite work for me, that isn't building the case I'd like, whose takes are off from my read. > The output is good enough—that is the problem. Good enough is a solvent. It dissolves the reason to do better. For as long as making things was expensive, the expense did quiet work on our behalf. It rationed output. Agreed about the rationing of output. I do think that the article though continues to show a magical thinking. That we have these things now and they autonomously do the thing. That the LLM's have solved it all. The article itself goes on at length about how nebulous and abstract taste is: > Taste is that. It is the compressed, wordless verdict you reach faster than you can justify. It is the “no, again” you say to yourself with total conviction and no available argument But this contrasts so distinctly to me against "the output is good enough". Is it? That depends. That depends on your taste. The proximate first results come quick. But the technics underneath? Those themselves, in my view, rely enormously on engineering taste to support and advance. I think we see a very similar sort of magical delivery thinking, very clearly on display here: > When the factories came, they could suddenly make everything—cheaply, uniformly, by the thousand. As if there was some magical "good enough" transition where suddenly the aliens came and gave us this box that just does the thing. As if we discovered the right formulas and math and now: we had production. Again I think there's just an enormous amount of work and taste that is still actively required inside the factory box, that building the industrial processes is incredibly intense & difficult, even though we have reliable industry-line production and now robots doing the labor. There's still so many gems, so much lovely material for thought. I love the provocations here, and I think there's a lot of great calibration. > The friction was not an obstacle to developing taste. The friction was the curriculum. Makes me think of yesterdays @apenwarr banger, > Every slow prototype started out as a fast prototype, I think that’s how it goes https://bsky.app/profile/apenwarr.ca/post/3msemlo4rds2h > — [jauntywundrkind on hackernews · 1 comments](https://news.ycombinator.com/item?id=49201410) > If we define taste as the intuitive act of saying "no, again," then I fully disagree with this whole article. Every AI-frustrated (but LLM-written, sigh) blog post about the loss of taste and craft and hard work in development sounds like we've given up the interaction with the machine. Like human work is sitting back in your chair and shitting on stuff. That's obviously not true! That's not how any of this works! It's hard and weird to develop with the LLMs because they just do stuff. Lots of it is good, some of it is OK, some of it's horrible. Unpacking what it's done is hard and weird because software isn't just lovely UX, it's also data structures that scale and performance and privacy and enterprise controls and SOC 2 and onboarding and accessibility. If you want to build real software, all that stuff has to get done. Today you're working on the feature, tomorrow you're making it scale. It's long-term and iterative and complex and hard to pack into a prompt or a markdown spec. The work is the work, done at and with the computer, and it's way more than just "taste." > — [trjordan on hackernews](https://news.ycombinator.com/item?id=49201472) > I find this post disheartening. To my eye, it seems to be the author's first blog entry with obvious LLM contributions. Given the recent "moving to a farm" ... 7 days later ... "leaving the farm" posts, it's hard not to read this as someone clearly struggling with the burnout which is all too common in our industry, and resultingly giving in to the false promise of a machine that can just handle the thinking for you. > — [DrBrock on hackernews · 1 comments](https://news.ycombinator.com/item?id=49202742) > After reading this reply, I read the addendum, and then read a few of your other posts. I will say that many others very much do _not_ sound like slop; when I compare them using the various AI detectors [1], posts from early 2025 say 10% or 0% and newer ones, including this one, say 100% AI or "AI paraphrased." That shift seems to have taken place, to my eye and to those of the detectors, between "The Federation Fallacy" (June 26, 2025) and "The Tradeoff Trap" (August 10, 2025). I'm really torn: on the one hand, you seem very genuine, and I'd really like to believe that there were no LLMs involved. On the other hand, there are just so _many_ of these tells present, from jarringly different sentences composed of three or four words in the form " [article] " to the little thinking-outside-of-thinking phrases like "I want to be careful here", "Here is the uncomfortable mechanism", and "[H]ere is the defense, such as it is" that emerge from the mechanism of LLMs' relentless forward march of token completion, that it's hard for me to believe. If it's really true that the machines write like you, I'm sorry. That's awful. With that said, I do think that writing well these days means taking the time to make clear, through both careful editing and clear sentence construction, that what we put out doesn't sound like the machine -- and I wonder what happened about a year ago that made you stop doing that. 1: To me, the comparison is much more interesting than the raw number. I understand that simply reporting "GPTZero says AI" is mostly meaningless. > — [mtset on lobsters · 2 points](https://lobste.rs/s/4qfkrz/taste_is_all_s_left#c_5zs9vk) **Source threads** - [lobsters](https://lobste.rs/s/4qfkrz/taste_is_all_s_left) · 16 points · 12 comments - [hackernews](https://news.ycombinator.com/item?id=49199346) · 128 points · 106 comments ## Similar posts on daily.dev - [The making was never the hard part](https://daily.dev/posts/the-making-was-never-the-hard-part-3ojgc2gd3) · Medium · 0 upvotes · 0 comments --- Tags: [#productivity](https://daily.dev/tags/productivity), [#ai-coding](https://daily.dev/tags/ai-coding) [View this post on daily.dev](https://daily.dev/posts/taste-is-all-that-s-left-yibj85oi2)