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

71–80 of 230 posts

Re: Taste in the age of AI and LLMs

#71

Post by alfalfasprout »

crystal_revenge wrote: post #58
danielvaughn wrote: post #34

Disagree with the overall argument. Human effort is still a moat. I've been spending the past couple of months creating a codebase that is almost entirely AI-generated. I've gotten way further than I would have otherwise at this pace, but it was still a lot of effort, and I still wasted time going down rabbit holes on features that didn't work out. There's some truth in there that judgement is as important as ever, t…

> ... for AI to be used effectively. I'm continually fascinated by the huge differences in individual ability to produce successful results with AI. I always assumed that one of the benefits of AI was "anyone can do this". Then I realized a lot of people I interact with don't really understand the problem they're trying to solve all that well, and have some irrational belief that they can get AI to brute force their…

> Strangely I find traditional software engineers, especially experienced ones, are generally the worst at achieving success. They often treat working with an agent too much like software engineering and end up building bad software rather than useful solutions to the core problem.

This feels a bit like a strawman. How do you assess it to be bad software without being an engineer yourself? What constitutes successful for you?

If anything, AI tools have revealed that a lot of people have hubris about building software. With non-engineers believing they're creating successful work without realizing it's a facade of a solution that's a ticking time bomb.

Re: Taste in the age of AI and LLMs

#73

Post by QuadmasterXLII »

crystal_revenge wrote: post #58
danielvaughn wrote: post #34

Disagree with the overall argument. Human effort is still a moat. I've been spending the past couple of months creating a codebase that is almost entirely AI-generated. I've gotten way further than I would have otherwise at this pace, but it was still a lot of effort, and I still wasted time going down rabbit holes on features that didn't work out. There's some truth in there that judgement is as important as ever, t…

> ... for AI to be used effectively. I'm continually fascinated by the huge differences in individual ability to produce successful results with AI. I always assumed that one of the benefits of AI was "anyone can do this". Then I realized a lot of people I interact with don't really understand the problem they're trying to solve all that well, and have some irrational belief that they can get AI to brute force their…

If every project you have tackled has come out successful, then you are managing to never tackle a problem that is secretly literally impossible, which is a property of whatever prefilter you are applying to potential problems. Given that your prefilter has no false positives, the main bit of missing information is how many false negatives it has.

Re: Taste in the age of AI and LLMs

#74

Post by aaaronic »

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…

I've worked in too many large codebases where no one can point to any _single file or class_ and label it "correct," ("the right way") yet management is amazed when the lack of a "North Star" means the codebase is full of overlapping, piecemeal patterns that are lucky to work together at all.

Re: Taste in the age of AI and LLMs

#75

Post by dfxm12 »

Taste shows up in three places:

    What you notice

    What you reject

    How precisely you can explain what feels wrong

I think it's just as important, if not more, to be able to explain what is right and what you accept. Having a well defined acceptance criteria also fits into existing project management frameworks. These criteria are generally based on asking users. The article mentions, You do not get a spreadsheet that tells you which sentence will make a customer care, which feature is worth a month of engineering time, or which design crosses the line from polished to forgettable. And this is why you talk to your customers.

Re: Taste in the age of AI and LLMs

#76

Post by gopher_space »

crystal_revenge wrote: post #58
danielvaughn wrote: post #34

Disagree with the overall argument. Human effort is still a moat. I've been spending the past couple of months creating a codebase that is almost entirely AI-generated. I've gotten way further than I would have otherwise at this pace, but it was still a lot of effort, and I still wasted time going down rabbit holes on features that didn't work out. There's some truth in there that judgement is as important as ever, t…

> ... for AI to be used effectively. I'm continually fascinated by the huge differences in individual ability to produce successful results with AI. I always assumed that one of the benefits of AI was "anyone can do this". Then I realized a lot of people I interact with don't really understand the problem they're trying to solve all that well, and have some irrational belief that they can get AI to brute force their…

> I always assumed that one of the benefits of AI was "anyone can do this". Then I realized a lot of people I interact with don't really understand the problem they're trying to solve all that well

I've been through a handful of "anyone can do this" epiphanies since the 90s and have come to realize the full statement should be "anyone can do this if they care about the problem space".

Re: Taste in the age of AI and LLMs

#77

Post by scared_together »

furyofantares wrote: post #4

Extremely ironic piece of slop.

I agree.

For those who didn’t read the article…

There are subheadings every 3 paragraphs and enough bullets to reload a machine gun.

There are also neither any sources nor any personal anecdotes. Everything feels generic.

> Over time, this changes how you work. You stop admiring polish for its own sake. You get faster at spotting empty specificity, borrowed tone, and fake confidence.

“Empty specificity, borrowed tone and fake confidence” describe the article itself.

Re: Taste in the age of AI and LLMs

#79

Post by monknomo »

andai wrote: post #52
danielvaughn wrote: post #34

Disagree with the overall argument. Human effort is still a moat. I've been spending the past couple of months creating a codebase that is almost entirely AI-generated. I've gotten way further than I would have otherwise at this pace, but it was still a lot of effort, and I still wasted time going down rabbit holes on features that didn't work out. There's some truth in there that judgement is as important as ever, t…

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?

Re: Taste in the age of AI and LLMs

#80

Post by scared_together »

dinkleberg wrote: post #19
furyofantares wrote: post #4

Extremely ironic piece of slop.

Yeah I feel like we’re getting pranked here

It’s also possible this is the first iteration of the loop described in the “A practical loop for training taste” section. Which would be less of a “prank” and more of “using the HN audience to feed the machine”.

The loop (some points snipped for brevity):

> 1. Pick one high-leverage artifact from your week. A paragraph…

> 2. Generate 10 to 20 versions with an AI model.

> 3. For each version, write one sentence that starts with "fails because..."

> 4. Rewrite the strongest version with a hard constraint…

> 5. Ship the final version somewhere real and observe what happens.

Post reply on HN