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

I don't care how well your "AI" works

fokus.cool

Post reply on HN
Print view View original

291–300 of 808 posts

Re: I don't care how well your "AI" works

#291

Post by 0xFEE1DEAD »

gavmor wrote: post #166
0xFEE1DEAD wrote: post #155

I honestly don't get vibe coding. I've tried it multiple times, but even after spending 4 hours on a fresh project I don't feel like I know what the hell is going on anymore. At that point I'm just guessing what the next prompt is to make it work. I have no critical knowledge about the codebase that makes me feel like I could fix an edge case without reading the source code line by line (which at that point would pro…

> I have no critical knowledge about the codebase that makes me feel like I could fix an edge case without reading the source code line by line (which at that point would probably take longer than 4 hours). Peter Naur argues that programming is fundamentally an activity of theory building, not just program text production. The code itself is merely the artifact of the real work. You must not confuse the artifact (the…

I agree with this take, but I'm wondering what vibe coders are doing differently?

Are they mainly using certain frameworks that already have a rigid structure, thus allowing LLMs to not worry about code structure/software architecture?

Are they worry-free and just run with it?

Not asking rhetorically, I seriously want to know.

Re: I don't care how well your "AI" works

#292

Post by atleastoptimal »

HN loves this "le old school" coder "fighting the good fight" speak but it seems sillier and sillier the better and better LLM's get. Maybe in the GPT 4 era this made sense but Gemini 3 and Opus 4.5 are substantively different, and anyone who can extrapolate a few years out sees the writing on the wall.

A year ago, no reasonable person would use AI for anything but small-scoped autocomplete. Now it can author entire projects without oversight. Inevitably every failure case for LLM's is corrected, everything people said LLM's "could never do" they start doing within 6 months of that prognostication.

Re: I don't care how well your "AI" works

#293

Post by ciconia »

Where's the popcorn? I don't really care either way about so-called AI. I find the talk about AGI quite ridiculous, but I can imagine LLMs have their utility just like anything else. I don't vibe code because I don't find it useful. I'm fine coding by myself thank you very much.

When the AI hype is over and the bubble has burst, I'll still be here, writing quality software using my brain and my fingers, and getting paid to do it.

Re: I don't care how well your "AI" works

#294

Post by rsynnott »

aurareturn wrote: post #273
rsynnott wrote: post #130

Earlier quoted context omitted.

Don't be the person refusing the 4GL/Segway/3D TV/NFT/Metaverse. Regularly give the new tool a chance and check if improvements are useful for specific tasks. Like, I mean, at a certain point it runs out of chances. If someone can show me compelling quantitive evidence that these things are broadly useful I may reconsider, but until then I see no particular reason to do my own sampling. If and when they are useful, t…

Like, I mean, at a certain point it runs out of chances. If someone can show me compelling quantitive evidence that these things are broadly useful I may reconsider, but until then I see no particular reason to do my own sampling. If and when they are useful, there will be _evidence_ of that. My relative came to me to make a small business website for her. She knew I was a "coder". She gave me a logo and what her sma…

Okay, I mean if that’s the sort of thing you regularly have to do, cool, it’s useful for that, maybe, I suppose? To be clear I’m not saying LLMs are totally useless.

Re: I don't care how well your "AI" works

#295

Post by codeflo »

poszlem wrote: post #258
easterncalculus wrote: post #244

> I find it particularly disillusioning to realize how deep the LLM brainworm is able to eat itself even into progressive hacker circles. That's the thing, hacker circles didn't always have this 'progressive' luddite mentality. This is the culture that replaced hacker culture. I don't like AI, generally. I am skeptical of corporate influence, I doubt AI 2027 and so-called 'AGI'. I'm certain we'll be "five years away"…

> That's the thing, hacker circles didn't always have this 'progressive' luddite mentality. This is the culture that replaced hacker culture. People who haven't lived through the transition will likely come here to tell you how wrong you are, but you are 100% correct.

You were proven right three minutes after you posted this. Something happened, I'm not sure what and how. Hacking became reduced to "hacktivism", and technology stopped being the object of interest in those spaces.

Re: I don't care how well your "AI" works

#296

Post by otabdeveloper4 »

easterncalculus wrote: post #244

> I find it particularly disillusioning to realize how deep the LLM brainworm is able to eat itself even into progressive hacker circles. That's the thing, hacker circles didn't always have this 'progressive' luddite mentality. This is the culture that replaced hacker culture. I don't like AI, generally. I am skeptical of corporate influence, I doubt AI 2027 and so-called 'AGI'. I'm certain we'll be "five years away"…

> is absolutely filled with busy work that no one really wants to do

Well, LLMs don't fix that problem.

(They fix the "need to train your classification model on your own data" problem, but none of you care about that, you want the quick sci-fi assistant dopamine hit.)

Re: I don't care how well your "AI" works

#297

Post by teaearlgraycold »

0xFEE1DEAD wrote: post #155

I honestly don't get vibe coding. I've tried it multiple times, but even after spending 4 hours on a fresh project I don't feel like I know what the hell is going on anymore. At that point I'm just guessing what the next prompt is to make it work. I have no critical knowledge about the codebase that makes me feel like I could fix an edge case without reading the source code line by line (which at that point would pro…

I recently made a few changes to a small personal web app using an LLM. Everything was 100% within my capabilities to pull off. Easily a few levels below the limits of my knowledge. And I’d already written the start of the code by hand. So when I went to AI I could give it small tasks. Create a React context component, store this in there, and use it in this file. Most of that code is boilerplate.

Poll this API endpoint in this file and populate the context with the result. Only a few lines of code.

Update all API calls to that endpoint with a view into the context.

I can give the AI those steps as a list and go adjust styles on the page to my liking while it works. This isn’t the kind of parallelism I’ve found to be common with LLMs. Often you are stuck on figuring out a solution. In that case AI isn’t much help. But some code is mostly boilerplate. Some is really simple. Just always read through everything it gives you and fix up the issues.

After that sequence of edits I don’t feel any less knowledgeable of the code. I completely comprehend every line and still have the whole app mapped in my head.

Probably the biggest benefit I’ve found is getting over the activation energy of starting something. Sometimes I’d rather polish up AI code than start from a blank file.

Re: I don't care how well your "AI" works

#298

Post by dude250711 »

poszlem wrote: post #258
easterncalculus wrote: post #244

> I find it particularly disillusioning to realize how deep the LLM brainworm is able to eat itself even into progressive hacker circles. That's the thing, hacker circles didn't always have this 'progressive' luddite mentality. This is the culture that replaced hacker culture. I don't like AI, generally. I am skeptical of corporate influence, I doubt AI 2027 and so-called 'AGI'. I'm certain we'll be "five years away"…

> That's the thing, hacker circles didn't always have this 'progressive' luddite mentality. This is the culture that replaced hacker culture. People who haven't lived through the transition will likely come here to tell you how wrong you are, but you are 100% correct.

The folks who love command-line and terminals had not been luddites all this time?

Re: I don't care how well your "AI" works

#299

Post by lxgr »

zwnow wrote: post #249
Aurornis wrote: post #234

Earlier quoted context omitted.

> I am actually less productive when using LLMs because now I have to read another entities code and be able to judge wether this fits my current business problem or not. You don’t have to let the LLM write code for you. They’re very useful as a smart search engine for your code base, a smart refactoring tool, a suggestion generator, and many other ways. I rarely have LLMs write code for me from scratch that I have t…

> But you have to actually learn how to use them. This probably is the issue for me, I am simply not willing to do so. To me the whole AI thing is extremely dystopian so even on a professional level I feel repulsed by it. We had an AWS and a Cloudflare outage recently, which has shown that maybe it isn't a great idea to rely on a few companies for a single _thing_. Integrating LLMs and using all these tools is just a…

> We had an AWS and a Cloudflare outage recently, which has shown that maybe it isn't a great idea to rely on a few companies for a single _thing_.

I share that concern about massive, unforced centralization. If there were any evidence for the hypothesis that LLM inference would always remain viable in datacenters only, I'd be extremely concerned about their use too.

But from all I've seen, it seems overwhelmingly likely that we'll have very powerful ones in our phones in at most a few years, and definitely in midrange laptops and above.

Re: I don't care how well your "AI" works

#300

Post by yathaid »

>> No matter how well “AI” works, it has some deeply fundamental problems, that won’t go away with technical progress.

Without an explanation of what they author is calling out as flaws, it is hard to take this article seriously.

I know engineers I respect a ton who have gotten a bunch of productivity upgrades using "AI". My own learning curve has been to see Claude say "okay, these integration tests aren't working. Let me write unit tests instead" and go on when it wasn't able to fix a jest issue.

Post reply on HN