Live data from Hacker News

The cult of vibe coding is dogfooding run amok

bramcohen.com

481–490 of 555 posts

Re: The cult of vibe coding is dogfooding run amok

#481

Earlier quoted context omitted.

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.

No one cares about code quality. No one has ever cared about code quality. It’s only been tolerated in businesses because no one could objectively say that ignoring code quality can result in high velocity. With coding agents, velocity is now extremely high if you get humans out of the way.

And yet, velocity is a terrible metric to go by. It is only interesting in so far that you can spit something out before somebody else.

When agents became a thing I was hoping that we will finally be able to go through all the outstanding bugs, tighten the bolts so to speak. Instead, we produce _more_ stuff.

We have now 100 half-baked versions of everything because everybody can give their own spin on anything.

Re: The cult of vibe coding is dogfooding run amok

#482

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.

I think you're all fucking crazy. Or maybe I am? I can literally see my teams codebase becoming an unmaintainable nightmare in front of my eyes each day. I use copilot and Claude code and I frequently have to throw away their massively verbose and ridiculously complex code and engage my withering brain to come up with the correct solution that is 80% less code. I probably get to the solution in the same time when all…

> What are we doing here?

Trying to get rich quick. That's all this really is.

When your goal is to just make as much money as possible in the shortest amount of time, code quality doesn't matter because not only will your product not be relevant long enough for maintainability to become a problem, your users likely aren't using it because it's good anyway, they're using it because of the marketing and hype around it.

Claude Code is the Bored Ape Yacht Club of the current era. Burn money on marketing, build hype, inflate the valuation, then run with the bag. After they go public and the reality that current prices aren't even remotely profitable sets in, the entire scheme will collapse, and in a few years we'll all be looking back at this whole thing and laughing about how crazy people went over it, while going crazy for whatever the newest techbro hype scheme is.

Re: The cult of vibe coding is dogfooding run amok

#483

Earlier quoted context omitted.

It kind of reminds me of grammar police type personalities. They are so hung up on the fact it reads “ugly” they can’t see the message; this code powers a rapidly growing $400B company. They admit refactoring is easy, but fail to realize they probably know that too and it’s just not a priority yet.

The underlying model powers the valuation. Not the front end

[dead]

Re: The cult of vibe coding is dogfooding run amok

#484

Earlier quoted context omitted.

Well, your example is timely. Today I asked ChatGPT to make me a weekly calorie plan and it was perfect. But then I still use MyFitnessPal to log my calories because their food database is outstanding, and the UX of scanning food barcodes is unbeatable. They have the most niche items in my country, Spain. How are LLMs going any of that? An app is often much more than a CRUD interface. Maybe I could build a custom app…

The data sources often exist to build these things yourself. For your example there is Open Food Facts and USDA FoodData Central. https://world.openfoodfacts.org/ https://fdc.nal.usda.gov/ Both would make a great foundation for this sort of app. OFF is crowdsourced and does include barcode information. I have no idea how robust the dataset is for your geography though. If I were to build something like this for perso…

I am not going to even try until it becomes a literal weekend project with zero maintenance and perfect reliability. Maintenance is crucial - I would not want to become the maintainer of two dozen apps that are genuinely useful to me. At 10€ a month the economics are not there. Even researching if the codebar database has perfect coverage in Spain like MFP sounds like more time than I would like to invest. I have a thousand other projects I’d like to build.

Re: The cult of vibe coding is dogfooding run amok

#487
post #478

Earlier quoted context omitted.

If you do not know the code at all, and are going off of "vibes", it's vibecoding. If you can get a deep sense of what is going on in the code based off of looking at a diff every ten commits, then that's not vibe coding (I, myself, are unable to get a sense from that little of a look). If you actually look at the code and understand it and you'd stand by it, then it's not vibecode. If you had an LLM shit it out in 2…

You're repeating the broader definition, great. But your post leaves me with the same question about degrees. You say there's two cases: no review and full review, "deep sense of the code", and that one is vibe coding and one is not. What about the degrees in between? At what point does vibe coding become something else? For example, I would not say "looking at the diffs" to ever be enough review to get a deep sense…

You're right that it's a spectrum. Just like anything else, you can be 'mostly' vibe coding or 'somewhat' vibe coding. But the threshold where it stops being vibe coding isn't entirely subjective.

If you are trusting the AI's logic and primarily verifying the output (the app runs, the button works), you are vibe coding. If you are reading the diffs, verifying the architecture, you are transitioning back toward engineering. Any sincere developer knows where they are sitting on that spectrum.

Re: The cult of vibe coding is dogfooding run amok

#488
post #417

Earlier quoted context omitted.

Maybe I misunderstood the purpose of your post...? It seemed to me like you were arguing "Hey, what about me? Why shouldn't I vibecode since it enables me to do things that I couldn't before?" and that's what I wrote my comment addressing. I completely agree that people are going to be forced into using things that basically do not really work for anything non-trivial without massive handholding, and they will be for…

I (like many on HN I'm sure) have been continually pestered by management to use AI like it's some cure for polio. They just want to tell their VP that "my team is accelerating its use of AI!" so that the VP can pass that up the food chain. Same with when we started to migrate (unnecessarily imho) to the cloud. Just another checkbox and an attaboy from senior management. There's really not much of a place for AI in m…

> And the ease at creating a simple app that would be beyond 99% of the people in my company gives way too much confidence. And with misplaced confidence comes poor decision-making.

I 100% agree. I heard via a CTO I've worked with before that a stakeholder in the company had come to him with a mock frontend that looked beautiful, it even had bits of interactivity where it could be used as if it was real. He asked them who made it, because it was very nice; they said "I made it!" (Claude made it). Now the plan for the next product is to shove it into a server format so that it can be used with a vibecoded frontend where the stakeholder is now responsible.

Honestly, I think the above situation is as good as it can get with these stakeholder hallucinations; ultimately the web frontend is likely to buckle under the pressure of having almost zero technical backing behind its creation, it'll perform badly with even the most basic of things and a real one will likely be created instead. The key is that the person having the LLM psychosis is the one that is responsible, so when things fail it's their fault.

Re: The cult of vibe coding is dogfooding run amok

#489

Earlier quoted context omitted.

[flagged]

^ This is a troll; new account, troll username.

Not a troll. I’ve been doing a lot of self reflection on this topic lately. Some people seem to enjoy software for the act & craft, where the outcome / artifact is secondary or irrelevant. I don’t. Some people enjoy the artifacts it produces, for their utility or economic value. Not really me either. Often people frame it as this dichotomy, but I’ve realized my enjoyment and self-fulfillment comes from creating an artifact that is genuinely good and that I can be proud of creating. Too much AI robs me of this. I’ve created cool stuff with AI that leaves me feeling nothing because I didn’t really create it.
Post reply on HN