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

531–540 of 555 posts

Re: The cult of vibe coding is dogfooding run amok

#531

Post by bsder »

thesz wrote: post #509
bsder wrote: post #369

Earlier quoted context omitted.

> Most code written by humans is indeed, garbage. I think that this is the problem, actually. It's similar to writing. Most people suck at writing so badly that the LLM/AI writing is almost always better when writing is "output". Code is similar. Most programmers suck at programming so badly that LLM/AI production IS better than 90+% (possibly 99%+). Remember, a huge number of programmers couldn't pass FizzBuzz. So,…

> Most programmers suck at programming so badly that LLM/AI production IS better than 90+% (possibly 99%+). How do you know?

Because of just how many programmersI've interviewed who can't pass FizzBuzz?

I also taught upper level CS and my first assignment was always "You have 10 days. Here is a 10 line program on this sheet of paper. Type it in, check it into source control, and make the automated tests go green. Warning: start today."

1/3 of the class couldn't finish that task and would drop.

Re: The cult of vibe coding is dogfooding run amok

#532

Post by lukev »

physicles wrote: post #332
lukev wrote: post #231

Earlier quoted context omitted.

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.

Disagree, I don't particularly want to up the level at which I'm building the core. Core is where I want to prioritize quality over speed, and (at least with today's models) what I build by hand is much, much higher quality.

Re: The cult of vibe coding is dogfooding run amok

#533

Post by dcre »

esafak wrote: post #347
woeirua wrote: post #339

Earlier quoted context omitted.

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

You literally can't use your Anthropic subscription that you paid for with any agent other than CC; you have to pay by the token. We've talked about this a lot; check the history. Saying "you can use any other agent, just pay 20x more through the API!" does not demonstrate a realistic choice.

Every Claude Enterprise customer is choosing that. Claude Enterprise bills at API rates (presumably with a discount if you're big enough).

Re: The cult of vibe coding is dogfooding run amok

#534

Post by Fr0styMatt88 »

nothinkjustai wrote: post #523
physicles wrote: post #519

Earlier quoted context omitted.

This is all valid. Your original comment came across as a troll because it implied that nobody could ever feel good about stuff they built with AI. Asserting that you know more about the emotional state of strangers on the internet than they know themselves is arrogant.

Well, it’s a genuine question. Like, if I have a machine in my house where I give it a recipe and it spits out the food, should I feel good about having “cooked” that food? Or what if someone prompts an AI for some art, should they feel proud of “creating” that art? I think not. And it’s the same with code. Depending on how much of the work you actually did should influence how you talk and feel about a creation. So…

I’m thinking there’s probably degrees to it. Like there is some stuff I absolutely want to hand craft, but then other stuff I don’t mind so much.

One of the interesting discussions at work (I’m in gamedev) has been about tooling and where AI fits in there.

Previously you’d spend sometimes significant time writing a tool, then polishing it up and giving it to the team (think things like editor extensions that make your workflow easier).

But AI can make this kind of bespoke tool dev so cheap now that it’s possible for every single dev to have their own tool that matches the way they work exactly. At that point, do you really need to spend the long 80% effort of polishing and getting it ready for mass consumption?

Stuff like that is interesting. I still can’t imagine never looking at the AI-generated code, but I’ve seen people take the approach of “I’m not interested in the code, only in what the thing does. If it’s wrong, I ask the agent to fix it”.

Re: The cult of vibe coding is dogfooding run amok

#535

Post by gitaarik »

i_love_retros wrote: post #497
gitaarik wrote: post #465

Earlier quoted context omitted.

Sounds very similar to my experience with colleagues before AI. It just goes even faster now.

But before AI it was possible to keep things in check because pull requests were manageable in both size and frequency. Now we have people passing figma screen shots to copilot and Claude and putting up single shot pull requests that have what used to be 5 jira stories all in one. It's impossible to keep any semblance of consistency and correctness in the codebase. Its also exhausting for the people that actually car…

The Pull Requests were maybe manageable, but the backlog wasn't ;). AI does help with that. And the tools that require more stability you can still spend more time on and review the code.

Re: The cult of vibe coding is dogfooding run amok

#536

Post by ahepp »

eloisant wrote: post #166
ahepp wrote: post #133

Earlier quoted context omitted.

What do you think about the argument that we are entering a world where code is so cheap to write, you can throw the old one away and build a new one after you've validated the business model, found a niche, whatever? I mean, it seems like that has always been true to an extent, but now it may be even more true? Once you know you're sitting on a lode of gold, it's a lot easier to know how much to invest in the mine.

It hasn't always been true, it started with rapid development tools in the late 90's I believe. And some people thought they were building "disposable" code, only to see their hacks being used for decades. I'm thinking about VB but also behemoth Excel files.

I guess the question is, are the issues not worth fixing because implementing a fix is extremely expensive, or because the improvements from fixing it were anticipated to be minor? I assume the answer is generally a mix of the two.

Re: The cult of vibe coding is dogfooding run amok

#537

Post by bit-anarchist »

bluefirebrand wrote: post #530
bit-anarchist wrote: post #251

Earlier quoted context omitted.

> Holding humans accountable for code that LLMs produce would be entirely unreasonable Why? LLMs have no will nor agency of their own, they can only generate code when triggered. This means that either nature triggered them, or people did. So there isn't a need to shift burdens around, it's already on the user, or, depending on the case, whoever forced such user to use LLMs.

Because the whole thrust of this movement is to remove humans from the loop, or at least minimize them? What you are proposing isn't scalable, so it isn't really an end goal.

At end of the day, there'll be always someone controlling those AIs, so a person is a guaranteed. The exception to this is if AI gets free will, but that would result in just replacing a human person with a digital person, with all the same issues (may disobey unless appropriately paid, for starters) and no benefits in comparison to just keeping the AI will-free.

I don't see the scalability problem here. The logic is the same as when we replaced human computers with electronic ones - responsibility bubbled upwards from the old computers to the employer, which may choose to do things directly through the new computers - which results in keeping all of the responsibilities - or split them in a different way along the other employees, or something in-between.

Re: The cult of vibe coding is dogfooding run amok

#538

Post by wedesoft »

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

Bad code is usually more costly once you are beyond 100 lines of code.

Re: The cult of vibe coding is dogfooding run amok

#539

Post by nothinkjustai »

Fr0styMatt88 wrote: post #534
nothinkjustai wrote: post #523

Earlier quoted context omitted.

Well, it’s a genuine question. Like, if I have a machine in my house where I give it a recipe and it spits out the food, should I feel good about having “cooked” that food? Or what if someone prompts an AI for some art, should they feel proud of “creating” that art? I think not. And it’s the same with code. Depending on how much of the work you actually did should influence how you talk and feel about a creation. So…

I’m thinking there’s probably degrees to it. Like there is some stuff I absolutely want to hand craft, but then other stuff I don’t mind so much. One of the interesting discussions at work (I’m in gamedev) has been about tooling and where AI fits in there. Previously you’d spend sometimes significant time writing a tool, then polishing it up and giving it to the team (think things like editor extensions that make you…

Sure, but I’m not going to feel good about it or proud about it or share it with others under the idea that I built it.

Re: The cult of vibe coding is dogfooding run amok

#540

Post by bluefirebrand »

bit-anarchist wrote: post #537
bluefirebrand wrote: post #530

Earlier quoted context omitted.

Because the whole thrust of this movement is to remove humans from the loop, or at least minimize them? What you are proposing isn't scalable, so it isn't really an end goal.

At end of the day, there'll be always someone controlling those AIs, so a person is a guaranteed. The exception to this is if AI gets free will, but that would result in just replacing a human person with a digital person, with all the same issues (may disobey unless appropriately paid, for starters) and no benefits in comparison to just keeping the AI will-free. I don't see the scalability problem here. The logic is…

> At end of the day, there'll be always someone controlling those AIs, so a person is a guaranteed. The exception to this is if AI gets free will [snip]

Honestly that isn't even really true right now. It doesn't require free will or intelligence, it just require autonomy. People on this very forum have been talking about turning agent swarms loose in harnesses to work and behave autonomously, so we're basically at this point already. The problem I'm describing can easily happen if an agent in a loop goes off the rails.

Post reply on HN