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

331–340 of 555 posts

Re: The cult of vibe coding is dogfooding run amok

#331

Post by SpicyLemonZest »

cassianoleal wrote: post #218
tombert wrote: post #88

Earlier quoted context omitted.

I suspect if people saw the handwritten code of many, many, many products that they used every day they would be shocked. I've worked at BigCos and startups, and a lot of the terrible code that makes it to production was shocking when I first started. This isn't a dig at anyone, I've certainly shipped my share of bad code as well. Deadlines, despite my wishes sometimes, continue to exist. Sometimes you have to ship a…

This is the product that's claiming "coding is a solved problem" though. I get a junior developer or a team of developers with varying levels of experience and a lot of pressure to deliver producing crummy code, but not the very tool that's supposed to be the state-of-the-art coder.

The bet is that it will be trivial for them to invest in cleaning up Claude Code whenever they face real competitive pressure to do so. My best guess is that it's a bad bet - I don't think LLM agents have solved any of the fundamental problems that make it hard to convert janky bad code to polished good code. But Claude Code is capable in my experience of producing clean code when appropriately guided, so it's not that there's no choice but jank. They're intentionally underinvesting in code quality right now for the sake of iteration speed.

Re: The cult of vibe coding is dogfooding run amok

#332

Post by physicles »

lukev wrote: post #231
saulpw wrote: post #8

> That wouldn’t even be a big violation of the vibe coding concept. You’re reading the innards a little but you’re only giving high-level, conceptual, abstract ideas about how problems should be solved. The machine is doing the vast majority, if not literally all, of the actual writing. Claude Code is being produced at AI Level 7 (Human specced, bots coded), whereas the author is arguing that AI Level 6 (Bots coded,…

I like this framing, but it does seem to imply that a whole dev shop, or a whole product, can or should be built at the same level. The fact is, I think the art of building well with AI (and I'm not saying it's easy) is to have a heterogenously vibe-coded app. For example, in the app I'm working on now, certain algorithmically novel parts are level 0 (I started at level 1, but this was a tremendously difficult proble…

100% agree. Velocity at level 8 or even 7 is a whole order of magnitude faster than even level 5. Like you said, identifying the core and letting everything else move fast is most of the game. The other part is finding ways to up the level at which you’re building the core, which is a harder problem.

Re: The cult of vibe coding is dogfooding run amok

#333

Post by tedmiston »

dd8601fn wrote: post #212
f-serif wrote: post #200

Earlier quoted context omitted.

Not AI but perfect example is Cloudflare. They have implemented public suffix list (to check if a domain is valid) 10 different times in 10 different ways. In one place, they have even embedded the list in frontend (pages custom domain). You report issues, they fix that one service, their own stuff isn't even aware that it exists in other places.

Meta has four different implementations of the same page to create a “page” for your business… which is required to be able to advertise on any of their services. Each one is broken, doesn’t have working error handling, and prevents you from giving them money. They all exist to insert the same record somewhere. Lost revenue, and they seem to have no idea. Amazons flagship ios app has had at least three highly visible…

they prioritize bugs based on what impacts the largest amount ($) of customers — fixing every bug of a huge complex project rarely makes sense if the impact of the bug on revenue is tiny

Re: The cult of vibe coding is dogfooding run amok

#335

Post by SpicyLemonZest »

reese_john wrote: post #314
bcrosby95 wrote: post #78

Earlier quoted context omitted.

Bad code works fine until it doesn't. In my experience, with humans, doing the right thing is worth it over doing the bad thing if your time horizon is a few months. Once you're in years, absolutely do the right thing, you're actually throwing time away if you don't. And I don't mean "big refactor", I mean at-change-time, when you think "this change feels like an icky hack." For LLMs, I don't really know. I only have…

If you are a company founder, what scenario would you rather find yourself in? a) a pristine, good codebase that follows the best coding practices, but it is built on top of bad specs, wrong data/domain model b) a bad codebase but it correctly models and nails the domain model for your business case Real life example, a fintech with: a) a great codebase but stuck with a single-entry ledger b) a bad codebase that perf…

"Perfectly implements" is doing a lot of work there. Enterprise software is very rarely perfect out of the box, and the issue with bad code is that it can make it extraordinarily hard to solve simple problems. I have personally seen tech-debt induced scenarios where "I want a new API to edit this field in an object" and "Let's do a dependency upgrade" respectively became multi-month projects.

Re: The cult of vibe coding is dogfooding run amok

#337

Post by azov »

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…

Your code is that contract (unless your tests cover every possible input, which is not practical in most cases).

Re: The cult of vibe coding is dogfooding run amok

#338

Post by pron »

chucklenorris wrote: post #223
pron wrote: post #122

Earlier quoted context omitted.

1. "Vibe coding" is a spectrum of how much human supervision (and/or scaffolding in the form of human-written tests and/or specs) is involved. 2. The problem with "bad code" has nothing to do with the short-term success of the product but with the ability to evolve it successfully over time. In other words, it's about long-term success, not short-term success. 3. Perhaps most importantly, Claude Code is a fairly simp…

1 is definitely false right now. I gave specs, tests, full datasets, reference code to translate to an llm and still produce garbage code/fall flat on it's face. I just spent one week translating a codebase from go to cpp and i had to throw the whole thing out because it put in some horrible bugs that it could not fix even burning 500$ worth of tokens and me babysitting it. As i said it had everything at it's disposa…

Oh, I agree. Anthropic themselves proved that even with a full spec and thousands of human-crafted tests, unsupervised agents couldn't produce even something as relatively simple as a workable C compiler, even when the model was trained on the spec, tests, the theory, a reference implementation, and even when given a reference implementation as an oracle.

But my point was that I don't think the development of Claude Code itself isn't supervised, hence it's not really "vibe coded".

Re: The cult of vibe coding is dogfooding run amok

#339

Post by woeirua »

esafak wrote: post #304
dcre wrote: post #284

Earlier quoted context omitted.

Incredible take. They are selling it.

No, they are not. People just want the model. Let people bring their own harness to their Anthropic subscription and see who's still using CC.

You can literally do this right now if you want. The masses have spoken, they want CC.

Re: The cult of vibe coding is dogfooding run amok

#340

Post by tedmiston »

tristramb wrote: post #195
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.

Yes, that is how Facebook, Yahoo and many other companies started out. But they rewrote their code when it became to big to be maintainable. The problem with shoddy code is not necessarily that it doesn't work but that it becomes impossible to change.

ehh, as long as the overall starting architecture is decent, it's not hard to do tiny refactors across components

claude code, the app, is also not some radically complex concept (even if the codebase today is complicated)

but hey, that's why people do version breaking rewrites

Post reply on HN