Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Taste in the age of AI and LLMs

rajnandan.com

Post reply on HN
Print view View original

111–120 of 230 posts

Re: Taste in the age of AI and LLMs

#111

Post by liuliu »

acuozzo wrote: post #109

> AI and LLMs have changed one thing very quickly: competent output is now cheap. If you're working on something not truly novel, sure. If you're using LLMs to assist in e.g. Mathematics work on as-yet-unproven problems, then this is hardly the case. Hell, if we just stick to the software domain: Gemini3-DeepThink, GPT-5.4pro, and Opus 4.6 perform pretty "meh" writing CUDA C++ code for Hopper & Blackwell. And I'm not…

I am not sure you set it up right. Did you have a runnable WolframLanguage file so it can compare results? Did you give it H100 / H200 access to compile and then iterate?

My experience is that once you have these two, it does amazing kernel work (Codex-5.4).

Re: Taste in the age of AI and LLMs

#112

Post by 9rx »

boshalfoshal wrote: post #103
pegasus wrote: post #86

Earlier quoted context omitted.

> but that gap gets smaller every year (and will ostensibly be closed) As long as you build software for humans (and all software we build is for humans, ultimately), you'll need humans at the helm to steer the ship towards a human-friendly solution.

The thing is, do humans _need_ most software? The less surfaces that need to interact with humans, the less you need humans in the loop to design those surfaces. In a hypothetical world where maybe some AI agents or assistants do the vast majority of random tasks for you, does it matter how pleasing the doordash website looks to you? If anything, it should look "good" to an ai agent so that its easier to navigate. An…

> And maybe "looking good" just amounts to exposing some public API to do various things.

Maybe, but you still need humans to make that call. The software is still built for humans no matter how much indirection you add.

There is a conceivable day where that is no longer true, but when you have reached that point it is no longer AI.

Re: Taste in the age of AI and LLMs

#113

Post by Shorel »

sodapopcan wrote: post #17
CharlieDigital wrote: post #11

> One of the most useful things about AI is also one of the most humbling: it reveals how clear your own judgment actually is. If your critique stays vague, your taste is still underdeveloped. If your critique becomes precise, your judgment is stronger than the model output. You can then use the model well instead of being led by it. Something I find that teams get wrong with agentic coding: they start by reverse eng…

> Instead, the right train of thought is: "what would perfect code look like?" and then meticulously describe to the LLM what "perfect" is to shape every line that gets generated. I think this goes against what a lot of developers want AI to be (not me, to be clear).

It doesn't matter, one way or the other. The overall market share will decide. In some cases, I think good code will be a decisive factor. Think Steam launcher Vs Epic. Epic doesn't have good code. Their performance suffers in consequence. In other cases the users are so trapped it makes no difference. MS Outlook and Teams is the prime example of this.

Re: Taste in the age of AI and LLMs

#114

Post by acuozzo »

liuliu wrote: post #111
acuozzo wrote: post #109

> AI and LLMs have changed one thing very quickly: competent output is now cheap. If you're working on something not truly novel, sure. If you're using LLMs to assist in e.g. Mathematics work on as-yet-unproven problems, then this is hardly the case. Hell, if we just stick to the software domain: Gemini3-DeepThink, GPT-5.4pro, and Opus 4.6 perform pretty "meh" writing CUDA C++ code for Hopper & Blackwell. And I'm not…

I am not sure you set it up right. Did you have a runnable WolframLanguage file so it can compare results? Did you give it H100 / H200 access to compile and then iterate? My experience is that once you have these two, it does amazing kernel work (Codex-5.4).

> Did you have a runnable WolframLanguage file so it can compare results?

Yes.

> Did you give it H100 / H200 access to compile and then iterate?

Yes via Lambda.ai. Also, FWIW, I run claude with --dangerously-skip-permissions and codex with the equivalent flag.

> it does amazing kernel work (Codex-5.4)

Specifically with WGMMA + TMA?

---

Once TMA gets involved both Claude and Codex spin endlessly until they dump TMA for a slower fallback.

I've observed this with Claude-Code having Opus 4.6 reasoning set to medium, high, and max; "adaptive thinking" enabled and disabled; and I've made sure to max-out thinking tokens.

I've also observed this with Codex GPT-5.4 in addition to GPT-5.3-Codex with reasoning efforts from medium to xhigh.

---

I've also observed this on the web, as mentioned in my OP, with GPT-5.4pro (Extended Pro), Gemini3-DeepThink, and Opus 4.6.

Re: Taste in the age of AI and LLMs

#115

Post by all2 »

danielvaughn wrote: post #104
rvz wrote: post #63

Earlier quoted context omitted.

> Without the above, you run into the same issue devs would run into before AI - the codebase becomes an incoherent mess, and even AI can't untangle it because the confusion gets embedded into its own context. We have a term for this and it is called "Comprehension Debt" [0] [1]. [0] https://arxiv.org/abs/2512.08942 [1] https://medium.com/@addyosmani/comprehension-debt-the-hidden...

I'm not sure I agree the term applies. Comprehension debt, as I understand it, is just the dependency trap mentioned in that arxiv paper you linked. It means that the AI might have written something coherent or not, but you as a human evaluator have little means to judge it. Because you've relied on it too much and the scope of the code has exceeded the feasibility of reading it manually. When I talk about an incoher…

> This is why I say that having a super clear vision up front is important, because it reduces this kind of directional churn.

I'm on my 6th or 7th draft of a project. I've been picking away at this thing since the end of January; I keep restarting because the core abstractions get clearer and clearer as I go. AI has been great in this discovery process because it speeds iteration much more quickly. I know its starting to drift into a mess when I no longer have a clear grasp of the work its doing. To me, this indicates that some mental model I had and communicated was not sufficiently precise.

Re: Taste in the age of AI and LLMs

#116

Post by mkw5053 »

30minAdayHN wrote: post #108

I think there is a parallel to what happened to watch market with Quartz crisis. The same way Quartz has led to decline of Swiss movements, LLMs are going to have a huge effect on developer market. I hypothesize that in future there will be a micro segment which care about quality, taste, exclusivity etc the same way the luxury watch makers found a niche. My perspective is that this "taste" or "quality" will not be a…

Didn't PG write a post about this like a month ago?

Re: Taste in the age of AI and LLMs

#117

Post by hellisothers »

arnorhs wrote: post #65
taude wrote: post #45

Earlier quoted context omitted.

I feel like you're pretty strongly agreeing that taste is important: " I'm finding that you have to have an extremely clear product vision..."" Clear production vision that you're building the right thing in the right way -- this involves a lot of taste to get right. Good PMs have this. Good enginers have this. Visionary leaders have this.... The execution of using AI to generate the code and other artifacts, is a ma…

The way I understood it, the original article is saying the _only_ remaining differentiator is taste and the comment you replied to is saying "wrong, there are also other things, such as effort". I don't necessarily interpret the comment you replied to as saying that "taste is not important", which seems like what you are replying to, just that it's not the only remaining thing. I agree that taste gets you far. And I…

Aren’t you just making their point stronger? Effort is what is being replaced here, with some taste and a pile of AI (formerly effort) you can go to the moon.

Re: Taste in the age of AI and LLMs

#118

Post by all2 »

monknomo wrote: post #79
andai wrote: post #52

Earlier quoted context omitted.

I think you're missing the point. Effort is a moat now because centaurs (human+AI) still beat AIs, but that gap gets smaller every year (and will ostensibly be closed). The goal is to replicate human labor, and they're closing that gap. Once they do (maybe decades, but probably will happen), then only that "special something" will remain. Taste, vision... We shall all become Rick Rubins. Until 2045, when they ship Ru…

do you need taste if you can massively parallel a/b test your way to something that is tasteful? say like you take your datacenter of geniuses and have a a rubin-loop supervising testing different directions. shouldn't that be close enough?

"taste" here is an intractable solution. Just take a look at how architecture has varied throughout the history of mankind, building materials, assembly, shape, flow, all of it boils down to taste. Some of it can be reduced to 'efficiency' -- like the 3 point system for designing kitchens, but even that is a matter of taste.

Find three professional chefs and they will give you three distinct visions for how a kitchen should be organized.

The same goes for any professional field, including software engineering.

Re: Taste in the age of AI and LLMs

#119

Post by switchbak »

boshalfoshal wrote: post #105
eru wrote: post #72

Earlier quoted context omitted.

Is the joke that the guy is drinking bad coffee?

The joke is that "taste" usually implies you have some strong personal sense of self and style, but if you walked into tech offices in the bay area everyone looks like that and acts/talks the same. So its ironic that these same people are talking about "taste" when they ostensibly have very little.

That seems a bit judgy though, no? As if you can tell about a person's internal sense of taste by their business-casual clothing choices?

I mean, some of those people undoubtedly like Rush ... make of that what you will.

Re: Taste in the age of AI and LLMs

#120

Post by adammarples »

lamasery wrote: post #98
eru wrote: post #72

Earlier quoted context omitted.

Is the joke that the guy is drinking bad coffee?

The joke is that the person "saying" this is wearing their "I'm a rational, independent thinker!" tech uniform (expensive Nordic outdoors wear, so practical, so smart, so active, Vimes' boot theory, et c, not like those clowns in business wear, I'm interested in practicality not signaling, that's why I'm spending so much money signaling so hard about how rational I am). They are visibly displaying a complete lack of…

Agree but arcteryx is from vancouver
Post reply on HN