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

AI coding is gambling

notes.visaint.space

Post reply on HN
Print view View original

331–340 of 471 posts

Re: AI coding is gambling

#331

Post by MeetingsBrowser »

est31 wrote: post #150
MeetingsBrowser wrote: post #121

Earlier quoted context omitted.

You (in theory) have more control over the quality of the team you are managing, than the quality of the models you are using. And the quality of code models puts out is, in general, well below the average output of a professional developer. It is however much faster, which makes the gambling loop feel better. Buying and holding a stock for a few months doesn't feel the same as playing a slot machine.

You have a lot of control over LLM quality. There is different models available. Even with different effort settings of those models you have different outcomes. E.g. look at the "SWE-Bench Pro (public)" heading in this page: https://openai.com/index/introducing-gpt-5-4/ , showing reasoning efforts from none to high. Of course, they don't learn like humans so you can't do the trick of hiring someone less senior but w…

Imagine you opened a job posting and had all applicants complete SWE-bench.

Ignoring the useless/unqualified candidates and models, human applicants have a much wider range of talent for you to choose from than the top models + tooling.

The frontier models + tooling are, in the grand scheme of things, basically equivalent at any given moment.

Humans can be just as bad as the worst models, but models are no where near as good as the best humans.

Re: AI coding is gambling

#332

Post by input_sh »

IanCal wrote: post #219
input_sh wrote: post #207

Earlier quoted context omitted.

Until it produces predictable output, it's gambling. But it can't produce predictable output because it's a non-deterministic tool. What you're describing is increasing your odds while gambling, not that it's not gambling. Card counting also increases your odds while gambling, but it doesn't make it not gambling.

This is a pretty wild comparison in my opinion, it counts almost everything as gambling which means it has almost no use as a definition. The most obvious issue is it’d class working with humans as gambling. Fine if you want to make that as your definition but it seems unhelpful to the discussion.

You seem to have a fundamental issue understanding what the term deterministic even means.

If you give the same trivial task to the same human five times in a row, let's say wash the dishes, your dishes are either gonna be equally clean or equally not clean enough every time. Hell, it might even get better over time by giving them feedback at the end of the task that it can learn from.

If you run the same script five times in a row while changing some input variables, you're gonna get the same, predictable output that you can understand, look at the code, and fix.

If you ask the same question to the same LLM model five times in a row, are you getting the same result every time? Is it kind of random? Can the quality be vastly different if you reject all of its changes, start a new conversation, and tell it to do the same thing again using the exact same prompt? Congrats, that's gambling. It's no different than spinning a slot machine in a sense that you pass it an input and hope for the best as the output. It is different than a slot machine in a sense that you can influence those odds by asking "better", but that does not make it not gambling.

Re: AI coding is gambling

#333

Post by tovej »

pdntspa wrote: post #292
tovej wrote: post #285

Earlier quoted context omitted.

Would you share the music app? Do you have a public repo or demo somewhere? You didn't really describe it very much, so it's hard to say what it actually does. I'm interested in evaluating the quality of vibecoded projects people actually use.

At a later date, perhaps. I haven't messed with this project since I got employed and it was written over summer 2025, when the tooling for agentic development was a lot worse. (Very ADD here) There's also the open question of how best to package a python app that makes use of PyTorch and SciPy for distribution to nontechnical users. I want to solve that before I start putting this in other people's hands. Careful wi…

Vibecoding is the term for building software with LLM tools. Did you do something different?

I'm just getting tired of hearing claims of incredible software being built with LLM-based tools, but when I ask to see them, I get nothing.

Your claim of 12-18 months for a windowed music metadata app seem weird. That seems like about a week with Dear ImGui and some file format reading libraries to me. Am I missing something?

Re: AI coding is gambling

#335

Post by baq »

dvfjsdhgfv wrote: post #295
thangalin wrote: post #286

Earlier quoted context omitted.

> LLMs are not actually doing a great job of translating ideas into tangibly useful software Here is the source code for a greenfield, zero-dependency, 100% pure PHP raw Git repository viewer made for self-hosted or shared environments that is 99.9% vibe-coded and has had ~10k hits and ~7k viewers of late, with 0 errors reported in the logs over the last 24 hours: https://repo.autonoma.ca/repo/treetrek

Frankly, I created dozen of such projects in the last weeks. Recently I just deleted them all. I feel like there's no point. I cancelled my Claude subscription, too. I got back learning from books and use LLMs for "review my code in depth and show me its weak points" occasionally.

LLMs in teacher mode instead of solver mode can be great. ("review this change" is kinda sorta teacher mode.)

Re: AI coding is gambling

#337

Post by 6thbit »

Come on now. I pull the slot machine every time I ask my coworker Digbert to work on a ticket.

Will Digbert be able to handle it or will he pretend to handle it? Or will he handle it in a way that it will break again in six weeks and will evolve into his full time job for a year?

If this is gambling, middle management has been gambling for too long.

Re: AI coding is gambling

#338

Post by flaterkk »

smlacy wrote: post #50
jsLavaGoat wrote: post #28

Everything is "fast, cheap, good--pick two." This is no different.

I like the analogy but which 2 is AI coding? Fast & Cheap (but not Good?) - I wouldn't really say that AI coding is "cheap" Cheap & Good (but not Fast) - Again, not really "cheap" Fast & Good (but not Cheap) - This seems like maybe where we're at? Is this a bad place?

It's hitting all three, right _now_.

Eventually, it will be just Fast and Good. It won't be cheap, as companies start moving towards profitability.

Remember when Uber was super cheap? I do. They're fast and good though.

Re: AI coding is gambling

#339

Post by muwtyhg »

6thbit wrote: post #337

Come on now. I pull the slot machine every time I ask my coworker Digbert to work on a ticket. Will Digbert be able to handle it or will he pretend to handle it? Or will he handle it in a way that it will break again in six weeks and will evolve into his full time job for a year? If this is gambling, middle management has been gambling for too long.

You know there is a difference between a tool being unable to predictably accomplish its task, and asking employees to do work and them failing to do so. The accountability alone is leagues apart.

Re: AI coding is gambling

#340

Post by maplethorpe »

itsgrimetime wrote: post #92

All of this new capability has made me realize that the reason i love programming _isn't_ the same as the OP. I used to think (and tell others) that I loved understanding something deeply, wading through the details to figure out a tough problem. but actually, being able to will anything I can think of into existence is what I love about programming. I do feel for the people who were able to make careers out of falli…

If there was a website called InfiniteAppStore, which contained every app imaginable, and where you could type in your search and it would return the code for that app, would you find that as satisfying to use as Claude Code?

On the surface this does not sound as satisfying, because it more resembles shopping than coding. But once Claude Code is finally tuned to do its job perfectly, you will essentially be using that infinite app store. You're actually using it right now, every time you use Claude Code — just an imperfect version of it.

If you enjoy using AI because it allows you to "will anything into existence", it's because the process is currently imperfect. Using Claude Code is closer to shopping than coding, but because the process is obfuscated, it feels like you're the one making the products in the shopping catalogue every time you place an order.

Post reply on HN