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

Taste Is All That's Left

notashelf.dev

Post reply on HN
Print view View original

401–410 of 573 posts

Re: Taste Is All That's Left

#401

Post by tfrancisl »

DrBrock wrote: post #77

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.

From my interactions with him in some nix forums online, he is not in the industry. This is hobby work (not to devalue it, as his software is generally high quality).

Re: Taste Is All That's Left

#402

Post by ToucanLoucan »

ghtbircshotbe wrote: post #378
hellojomp wrote: post #8

On the topic of taste, I think of this quote in Susan Sontag's "Notes On 'Camp'" often: “For taste governs every free — as opposed to rote — human response. Nothing is more decisive. There is taste in people, visual taste, taste in emotion — and there is taste in acts, taste in morality. Intelligence, as well, is really a kind of taste: taste in ideas. (One of the facts to be reckoned with is that taste tends to deve…

I'm a little confused. She follows describing people with good/bad taste immediately with the statement that there is no system for taste. If it is all relative, then how is she determining that someone has good or bad taste? Is there anything between moral relativism and mathematical proof? Just your own ineffable belief that you are right?

> If it is all relative, then how is she determining that someone has good or bad taste? Is there anything between moral relativism and mathematical proof?

Social proof. Everyone has taste and everyone's taste in a given space is influenced and informed by the taste of others. It's mostly a consensus model. Newer members of a given community arise into said community and learn from it what "good" means, which can sound authoritarian but is really just... voluntary. If you like, for example, mens formal wear you will follow publications and noted figures in the mens formal wear space, you will learn what "good" means to them, and will emulate it out of a desire to fit in with them. As you get more knowledgeable in that space, you will develop your taste, enhanced by them, and ideally eventually contribute your own ideas to that mix. Some will be accepted, some will be rejected, again by group consensus.

It's a lot like language. If you want to speak a language you have to learn it first. If you go to France and simply blurt out French words at people, even with perfect annunciation, you will be incomprehensible to them. You learn structure, sentences, how to communicate ideas, how to inflect tone. How to tell the difference between telling someone to fuck off when they cut you off in traffic versus telling them to fuck off when they make a horrific pun. And, as people speak that language and use it daily, it will reliably change. The meanings of so many words in every language today are wildly different than they were even a hundred years ago.

Re: Taste Is All That's Left

#403

Post by CM30 »

boron1006 wrote: post #128

I don’t like the term taste, but the problem that I have is that LLMs don’t seem to work “good enough”. They seem to be able to solve the immediate problem, but stacking this on the scale of 3-4 devs over 6 months or so doesn’t seem to produce anything. One thing that I’m particularly frustrated with is the writing quality of LLMs. Like this is the thing that they should be able to do, but I would say almost everythi…

I think there are really two types of use cases for LLMs here, and people that get value out of them.

First are those that care very little about the quality of the work, or the process behind it, and just want a 'finished' product no matter what. These are many of the folks vibe-coding everything without even looking at the output, and a depressingly number of those getting hacked or what not.

But hey, if you've got an idea for a complex app or website but no interest in actually building it, an LLM will get you... something vaguely like what you wanted.

Second are small projects and small sections of existing ones, most of which easily fit inside the LLM's context window. If you're making a fairly basic WordPress plugin or React component or one page website, an LLM will probably be able to handle it just fine. Heck, it might not even look all that different from what a human might have created code wise.

One of the big issues we have those is that plenty of people and companies are using these tools despite having requirements that aren't met by them in the slightest. If you're working on a Google/Microsoft/Meta scale product where performance and security and code quality are of the utmost importance, then an LLM isn't going to be a great fit. Unfortunately, that's exactly where this technology is being used, and the results are becoming more and more obvious.

Re: Taste Is All That's Left

#404

Post by NoDodgeQuestion »

notashelf wrote: post #384
darkwater wrote: post #376

Earlier quoted context omitted.

Ok but who's pissed off bere? A human or a let-loose agent? Or a human that wrote the post with an LLM although they swear they didn't?

It's neither satirical, nor by an agent on the loose/in a loop. I read the comment section with good intentions, assuming good faith---and in their defense there is plenty---but the amount of misattribution is counterproductive. Nothing about the post-mortem section is "pissed off". I wrote it in complete serenity, like I am writing this comment to explain. There are three groups of commenters: 1. Skeptic, but engagi…

[dead]

Re: Taste Is All That's Left

#405

Post by gregwebs »

Taste ends up providing tangible value.

If you have taste in writing code, you spend less time on bugs and can implment features more quickly. This is still true with LLMs if you learn how to direct them instead of having them direct you.

Someone else without taste can re-implement what you have done with AI. But it will take them more effort, more time, and more money.

But that's always been the value in writing code. Any MBA can end up producing software to accomplish something by hiring other people. But their company might not get off the ground because of the expense of not having technical competency (or engineers with taste) at their core.

Re: Taste Is All That's Left

#406

Post by jmbwell »

ulrikrasmussen wrote: post #214
hellojomp wrote: post #8

On the topic of taste, I think of this quote in Susan Sontag's "Notes On 'Camp'" often: “For taste governs every free — as opposed to rote — human response. Nothing is more decisive. There is taste in people, visual taste, taste in emotion — and there is taste in acts, taste in morality. Intelligence, as well, is really a kind of taste: taste in ideas. (One of the facts to be reckoned with is that taste tends to deve…

An important feature of taste is also that it is highly variable between people, and because there is no system or proof of good taste, we cannot really say that one person's taste is objectively better than another's. This is what causes one person to build a large software system in a classical OOP language while another builds almost the same system in a typed functional language, each following their own internal…

I wrestle with this also. A colleague pointed out that LLMs reduce language choice to an implementation detail… don’t have to know assembly to write python, and now you don’t have to know python to write a functional app. So why stick with python when rust might be better? Leave that to the LLM and let your engineering effort go toward designing the app instead of operating a programming language.

In which case yeah, projects are likely to converge on whatever pattern LLMs broadly fall into. But maybe that part doesn’t really matter. Not every project needs the engineer to care about that. If I’m not writing hardware level code, I don’t care what instructions my python compiles to, either.

Meanwhile nothing prevents someone from caring about these details if wanted or needed. Someone who knows and cares might absolutely do a better job than an LLM. Those people won’t necessarily go away.

But there -will- be a whole new category of software contributors who have ideas they don’t know how to express in a software language. Those ideas might well be very tasteful. So it could be argued that software development as a field will gain access to a whole new range of tastes.

I don’t know the answers but it all seems plausible

Re: Taste Is All That's Left

#407

Post by basilikum »

dizhn wrote: post #356
Good4boothee wrote: post #347

Earlier quoted context omitted.

Please, I couldn't care what Pangram (or any other "detector") says. If it feels like AI, does it even matter if LLM was co-author? It lands in the same "bad writing, I won't continue to read that" category. That said I am recently getting paranoid about YT videos, I hear Claude traces in every 5th script. If people are going to spend substantial time recording and editing, is it worth "saving" time on most important…

"it's not just ...., it's ..." is in EVERY youtube video I watch. There's got to be a reason AI uses it so much. Maybe it was already prevalent in bad scripts and we never noticed it before. Sort of like the "Webster dictionary defines ... as " cliche.

An antithesis is a completely valid stylistic device. It's just very easy to overuse or to use as a cliché when you're not using language as a tool for a specific purpose, but just want to sound smart or think "fancy stylistic devices = good writing".

Re: Taste Is All That's Left

#408

Post by stiiv »

LLM-based code generation requires disciplined operation to lead to the best outcomes. Shops who only ever had taste as a proxy for discipline were missing this before, and they're missing it now. The fact that it's missing is why so many organizations are tolerating ever-growing mountains of slop. (Not new, by the way; just dramatically accelerated.)

Discipline can be linked to system design standards and your review process, and it can be translated to measurable outcomes at scale and over time, regardless of how agents are involved: unplanned work, time to recovery, employee retention, etc. When outcomes like these become your priority, you see that you can't rely on taste alone.

Re: Taste Is All That's Left

#409

Post by basilikum »

innocentoldguy wrote: post #324
nazgu1 wrote: post #310

I have mixed feelings... I stumbled upon, read a post-mortem that looks even more AI-generated than the article. "That says something about my writing. It says nothing about who wrote it." - Two contradicting sentences, author's writing skills are part of the author as-a-whole "The short sentences, the reversals, the one-word lines" and then "I will write the next one plainer.". - even more? And... I wonder if this i…

I'm a writer with what may be an unpopular opinion. I have a college degree in creative writing; I do technical writing and programming for a living, and I used to publish technical articles on Linux, Python, Elixir, and other topics—complete with em dashes—long before AI was a thing. When confronting AI as a writer and deciding how I feel about it, I've landed on the conclusion that I've never accused mathematicians…

Calculating is not math. Calculators make mathematicians better mathematicians by allowing them to spend their time on actual mathematics.

Writing is thinking. LLM writing makes authors worsr authors and even dumber people overall.

Also a calculator gives the same answer as a human (except for human errors where the calculator isa strict improvement). LLMs absolutely do not give the same output as humans.

Re: Taste Is All That's Left

#410

Post by MichaelZuo »

jmbwell wrote: post #398
ghtbircshotbe wrote: post #378

Earlier quoted context omitted.

I'm a little confused. She follows describing people with good/bad taste immediately with the statement that there is no system for taste. If it is all relative, then how is she determining that someone has good or bad taste? Is there anything between moral relativism and mathematical proof? Just your own ineffable belief that you are right?

Someone with questions about this excerpt of Sontag on taste would do well to read the rest of the work, which does a fuller job of drawing distinctions between sensibilities like taste, and systematic ideas like good/bad, morality, relativism, mathematics, proofs, and wrong/right.

This seems to be circular.

Wouldn’t anyone need some reading “taste” in the first place to decide to read more.

And if they already have it, why would they need to read it?

If it’s all relative there can be no globally valid, or fixed, reference points by definition.

Post reply on HN