Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- I keep seeing people trying to define judgement and taste and then they don’t actually like cite Kant’s Critique of Judgement where this is basically the entire concern.by DiscourseFan
- Nor the work of sociologists like Bourdieu's Distinction.by p0nce
- Shouldn't this 236-year-old paper be updated in accordance with, say, neuroeconomics research on how provenance influences aesthetic taste?by red75prime
- Speaks more to the myopia of developers than anything else.by FLeXMurphy
- Hume also has an essay about this. People don't read philosophy anymore. They think blog posts are just as good, or at least more "relevant", somehow.by eudamoniac
- > Suppose you have taste. Suppose you paid the full price and you can feel the sag in the sentence and the wrongness in the function. > > Congratulations! You now ship at exactly the same speed as the person who cannot.
Yes, previously the person who didn't understand shipped faster. It was a long standing problem. The people who crapped, got the bonus, and ran were much faster than the patient engineer of quality.
By the way, what were the essays that formulated Claude Style? if the author was indeed formed by them, I'd like to read them - or at least enough of them to understand.
by pnathan - This post is awful! Annoyingly written and zero insight. Most posts about this taste concept are bad (and there have been so many), but this is below average.by dcre
- Heh whoops. I thought my other comment didn’t post so I wrote this one instead.by dcre
- pangram v4 model says 100% of this article was LLM-generated.
pangram v4 reports a 0.0041% false-positive rate (~1 in 24,000 human texts) and a 0.3396% false-negative rate (~1 in 294 AI texts)
and i also think it was AI generated
- You've read many of them? Then you'd be the best to review even more of them! I'm ready for a raw and truthful review of my very own edition of the "taste" blog post, posted mere ~6 months ago, on the same topic: https://emsh.cat/en/good-taste/
- Generating the first version is almost free now. Understanding why that version is subtly wrong, debugging it in production, maintaining it six months later and deciding whether the abstraction was a mistake are all still expensive...by KurSix
- Yeah. The Fable oneshot is a myth, the software will still require constant refinement and maintenance. I've been daily driving my "vibecoded" projects and they're never really finished, there's always something to do.
- I've run this thought experiment a number of times with different sections of my (relatively) diverse friend circle. I ask them a version of this question on repeat: "what if AI automates X aspect of your work?", and the final answer (either because of frustration with the loopy nature of the question or a genuine stopping point) arrives somewhere along the lines of "my judgement," "my knack," "my embodied nature," or "my quality of decision making."
I think the core still leads back to human agency and the ability to consider aspects that wouldn't fit into an LLMs limited context window or be able to be vectorized into a DB, including ultra-long-term consequences (especially those with great thinking abilities).
I still happen to think that AI/LLMs will never be able to "fully" replace humans, because the evolutionary process that led to our cognitive abilities and the way we train LLMs are vastly different thanks to different pressures, but maybe that's just me defending the last bastions of our collective humanity as a human; I don't know what else to root for.
by abixb - Judgment was all there ever was to begin with. It's why it's what God himself does, although I'd be curious if there are deities that don't involve judgment in some form.
Anyway, I completely agree and the past several years have been an absurd journey into borderline psychosis with some people.
by sublinear - > somewhere along the lines of "my judgement," "my knack," "my embodied nature," or "my quality of decision making."
Do your friends actually believe that AI can't automate these parts of their work? I think my answer would be that I'll just have to learn to do something else.
> I still happen to think that AI/LLMs will never be able to "fully" replace humans
Do you mean replace humans completely or just replace all the tasks humans don't want to do? I would hope that humans will still have a reason to live even if all the work is done by computers, and that the computers wouldn't intentionally wipe us all out.
- Right now we're all training AI models on our taste. All of our chat logs are being uploaded, and the AI companies are training the models on them to get them right the first time.
It will soon no longer require taste. Or at the very least be 95% of the way there on the first run.
by asdfman123 - Hard disagree on "Good enough", most things are mediocre at best. Despite the massive AI boom I can at best count on one hand "fresh" products made with AI that are meaningful in day-to-day usage. Not to mention most of them seem to be targeting AI-space itself instead of bridging some actual business use case. Just look at all the products on ShowHN, you can "tell" a vibed product in seconds.by GrayHerring
- How would you count them or even know if they were made with AI or not ? Such nonsenseby aprdm
- If you are waiting for someone else to make a good product for you with AI, you are missing out. The best AI products have userbase of one.by scotty79
- Mediocre is good enough, that's what it means.by satvikpendem
- You are using countless products that are built or have become maintained by AI without realizing it apparently.by jatora
- I think you agree with what is in the essence of the post, but has been worded poorly. I do agree that most things are mediocre at best. Hell, I'd argue that most of my comments on everyday observations are negative. Ranging from "this sucks :/" to "holy fuck". They are, however, "good enough" for some and despite how clever I must to notice how much something sucks, that does nothing to the fact that it will receive adoption. Turns out I'm not clever. Huh.
In hindsight, I have worded this rather poorly and let some phrases do a lot of heavily lifting for me in the post. Ultimately, I agree with you. Knowing, for this instance, is not half the battle.
by notashelf - This article resonated tremendously with me, speaking as someone who has been coding since the 1980s and had to develop my own taste the hard way, through lots and lots of mistakes. Whenever I see a software demo built by someone mostly using agents to do the work, I have to question whether it's any good on the inside - or whether any real intuition or judgment went into its design. On the flip side, maybe none of that matters anymore - as long as it works, who cares how it was built.by mdwelsh
- The LLM has its own intuition and judgement which at this point is quite good. I’m not just throwing that around, I use LLMs 12-14 hours a day and for a long time reviewed atleast 75% of the code.by dyauspitr
- I wonder, when you have a McDonald's McDouble, do you really care how it was made or do you just care that it's yummeroni and costs $2.99?by hellojomp
- “as long as it works” is doing a lot of work here. Did the people building it say “no, again” enough times, and at the right times, in order to make something that _actually_ works instead of _merely_ works?by devin
- For what it is worth, I appreciate you sharing your experience. Looks like you have more programming experience than I have in life, so your comment matters to me. It also gets rather close to something I wanted to evaluate in the post: "whether any real intuition or judgment went into [its] design". I think that's a big question to dwell on these days.
Ironically, though, I had written a post that had people debating whether I put any intuition or judgement into. Would've been real ironic to instead add a post-scriptum that said "Yep, none of it matters. I just slopped something in 5 minutes and it easily went to the frontpage. Look how easy it is!" but unfortunately that is not why I write, not what I intended to achieve, and not something I am equipped to do. I care about my work, which is why I care about your comment as well.
by notashelf - It resonated with me too, and even as a once fairly prolific coder that now uses agents to do all the coding, I feel like this is all relevant and does matter. The agent does whatever you ask and provides thin judgements based on what it thinks is your motivation and context, even feeding it the context it will often make bad generic choices. I think this is the part hard to optimize because it's not a verifiable reward, it's the feel of the software. I think Herdr is a great example, I've tried several dozen terminal multiplexers / session aggregators and they are all vibed and different, but this one felt so much better to use because of its choices and actually increased the number of parallel sessions I was able to keep going. My own projects I find I have to stress every detail, that is what makes the software good now is really diving into it, the experience feels like just as much of a craft as coding was and 'taste' captures the concept for me.by mshafir
- For majority of people, including business executives it's the latter. No one cares about artisan code. Software is just a means to an end for them and not an art form.
People treat their computers like any other appliance. They don't care if it's riddled with bugs, they'll gladly restart their computer or refresh the page at infinitum to get it to work.
I think it's also why marketing and designers get more of a say in the software than engineers. UI polish matters more since it increases sales.
This is the hardest thing to come into terms with in this industry.
by swat535 - We've been talking about taste for a year now as it relates to AI, so I'm going to counterpoint it: if competitors can reproduce your features, UX, and visual decisions within days, your taste is not really an advantage. How many apps implemented pull down to refresh once one person did it? How many people even remember (or care) whose taste spawned that UX pattern? [1]
AI is not inaugurating an age of taste. It is shortening the half-life of taste and commoditizing software. What happens when software features, UX, and visual fidelity aren't competitive advantages anymore? If you ask me, it looks like business did in the 90s. We'll probably see the return of department store software in the next few years.
1: for the record https://en.wikipedia.org/wiki/Pull-to-refresh
by madrox