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

The cult of vibe coding is dogfooding run amok

bramcohen.com

Post reply on HN
Print view View original

141–150 of 555 posts

Re: The cult of vibe coding is dogfooding run amok

#141

Post by datsci_est_2015 »

andrenotgiant wrote: post #28
semicolon_storm wrote: post #14

It’s truly strange that people keep citing the quality of Claude code’s leaked source as if it’s proof vibe coding doesn’t work. If anything, it’s the exact opposite. It shows that you can build a crazy popular & successful product while violating all the traditional rules about “good” code.

> you can build a crazy popular & successful product while violating all the traditional rules about “good” code which has always been true

It’s also possible to sell chairs that are uncomfortable and food that tastes terrible. Yet somehow we still have carpenters and chefs; Herman Miller and The French Laundry.

Some business models will require “good” code, and some won’t. That’s how it is right now as well. But pretending that all business models will no longer require “good” code is like pretending that Michelin should’ve retired its list after the microwave was invented.

Re: The cult of vibe coding is dogfooding run amok

#142

Post by hibikir »

My favorite uses of Claude code is to do code quality improvements that would be seen as a total waste of time if I was doing them by hand, but are perfectly fine when they are done mostly for free. Looking for repetitive patterns in unit tests/functional tests. Making sure that all json serialization is done in similar patterns unless there's a particularly good reason. Looking for functions that are way too complicated, or large chunks of duplication.

The PRs that it comes with are rarely even remotely controversial, shrink the codebase, and are likely saving tokens in the end when working on a real feature, because there's less to read, and it's more boring. Some patterns are so common you can just write them down, and throw them at different repos/sections of a monorepo. It's the equivalent of linting, but at a larger scale. Make the language hesitant enough, and it won't just be a steamroller either, and mostly fix egregrious things.

But again, this is the opposite of the "vibe coding" idea, where a feature appears from thin air. Vibe Linting, I guess.

Re: The cult of vibe coding is dogfooding run amok

#143

Post by kristopolous »

semicolon_storm wrote: post #14

It’s truly strange that people keep citing the quality of Claude code’s leaked source as if it’s proof vibe coding doesn’t work. If anything, it’s the exact opposite. It shows that you can build a crazy popular & successful product while violating all the traditional rules about “good” code.

devaluing craftsmanship is fundamentally insulting.

Re: The cult of vibe coding is dogfooding run amok

#144

Post by nkohari »

babelfish wrote: post #70
spoiler wrote: post #39

Earlier quoted context omitted.

Yes, and to add, in case it's not obvious: in my experience the maintenance, mental (and emotional costs, call me sensitive) cost of bad code compounds exponentially the more hacks you throw at it

Sure, for humans. Not sure they'll be the primary readers of code going forward

Because LLMs are designed as emulators of actual human reasoning, it wouldn't surprise me if we discover that the things that make software easy for humans to reason about also make it easier for LLMs to reason about.

Re: The cult of vibe coding is dogfooding run amok

#146

Post by datameta »

roughly wrote: post #82
semicolon_storm wrote: post #14

It’s truly strange that people keep citing the quality of Claude code’s leaked source as if it’s proof vibe coding doesn’t work. If anything, it’s the exact opposite. It shows that you can build a crazy popular & successful product while violating all the traditional rules about “good” code.

You can send a submarine down to crushing depths while violating all the traditional rules about "good" engineering, too.

Right, and often the tested depth isnt maximum. So you slowly acclimate to worse and worse code practices if the effort needed to undo it is the same as doing.

Re: The cult of vibe coding is dogfooding run amok

#147

Post by MBCook »

thwarted wrote: post #93
semicolon_storm wrote: post #14

It’s truly strange that people keep citing the quality of Claude code’s leaked source as if it’s proof vibe coding doesn’t work. If anything, it’s the exact opposite. It shows that you can build a crazy popular & successful product while violating all the traditional rules about “good” code.

> It shows that you can build a crazy popular & successful product while violating all the traditional rules about “good” code. We already knew that. This is a matter of people who didn't know that or didn't want to acknowledge that thinking they now have proof that it doesn't matter for creating a crazy popular & successful product, as if it's a gotcha on those who advocate for good practices. When your goal is to c…

VHS was not worse is better. It’s better is better.

Re: The cult of vibe coding is dogfooding run amok

#148

Post by moritzwarhier »

tock wrote: post #113
moritzwarhier wrote: post #94

Earlier quoted context omitted.

I don't know if the comment was referring to this, but recently, people have been posting stuff about them requiring their new hire Jared Sumner, author of the Bun runtime, to first and foremost fix memory leaks that caused very high memory consumption for claude's CLI. The original source was them posting about the matter on X I think. And at first glance, none of it was about complex runtime optimizations not prese…

Ah I believe codex has similar issues. Terrible code quality but goes to show it doesn't really matter in the end.

Yes that was pretty much my own takeaway, too.

After some experience, it feels to me (currently primarily a JS/TS developer) like most SPAs are ridden by memory leaks and insane memory usage. And, while it doesn't run in the browser, the same think seems to apply to Claude CLI.

Lexical closures used in long-living abstractions, especially when leveraging reactivity and similar ideas, seems to be a recipe for memory-devouring apps, regardless of browser rendering being involved or not.

The problems metastasize because most apps never run into scenarios where it matters, a page reload or exit always is close enough on the horizon to deprioritize memory usage issues.

But as soon as there are large allocations, such as the strings involved in LLM agent orchestration, or in non-trivial other scenarios, the "just ship it" approac requires careful revision.

Refactoring shit that used to "just work" with memory leaks is not always easy, no matter whose shit it is.

Re: The cult of vibe coding is dogfooding run amok

#149

Post by sunnybeetroot »

freediddy wrote: post #62

No, I completely disagree with this entire article. Bad code or good code is no longer relevant anymore. What matters is whether or not AI fulfills the contract as to how the application is supposed to work. If the code sucks, you just rerun the prompt again and the next iteration will be better. But better doesn't matter because humans aren't reading the code anymore. I haven't written a line of code since January a…

This entirely depends on the product. If it’s your own personal blog, then for sure no need to read the code, but a change in a banking architecture would be irresponsible to not have an understanding of the actual code change.
Post reply on HN