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

391–400 of 555 posts

Re: The cult of vibe coding is dogfooding run amok

#391

Post by forrestthewoods »

saulpw wrote: post #207
forrestthewoods wrote: post #69

Earlier quoted context omitted.

Interesting breakdown of levels. I like it. I’m not sure I believe that Level 7 exists for most projects. It is utterly *impossible* for most non-trivial programs to have a spec that doesn’t not have deep, carnal knowledge of the implementation. It can not be done. For most interesting problems the spec HAS to include implementation details and architecture and critical data structures. At some point you’re still wri…

I agree, I'm venturing into Level 6 myself and it often feels like being one step too high on a ladder. Level 7 feels like just standing on the very top of the ladder, which is terrifying (to me anyway as an experienced software engineer).

To me it’s not terrifying because it’s just so plainly bad and not good enough. If you try L7 it just doesn’t work. Unless you’re making a dashboard in which case sure yeah it’s fine. But not for complex problems.

Re: The cult of vibe coding is dogfooding run amok

#392

Post by 8note »

zephen wrote: post #277
tombert wrote: post #228

Earlier quoted context omitted.

Yeah, I'm just a little tired of seeing these pull requests of multi-thousand-line pull requests where no one has actually looked at the code. The solution people are coming up with now is using AI for code reviews and I have to ask "why involve Git at all then?". If AI is writing the code, testing the code, reviewing the code, and merging the code, then it seems to me that we can just remove these steps and simply P…

> why involve Git at all then? I made a similar point 3 weeks ago. It wasn't very well received. https://news.ycombinator.com/item?id=47411693 You don't actually need source control to be able to roll back to any particular version that was in use. A series of tarballs will let you do that. The entire purpose of source control is to let you reason about change sets to help you make decisions about the direction that…

> If people are still using git but not really using it, are they doing so simply to take advantage of free resources such as github and test runners,

does it have to be free to be useful? the CD part is is even more important than before, and if they still use git as their input, and everyone including the LLM is already familiar with git, whats the need to get rid of it?

there's value in git as a tool everyone knows the basics of, and as a common interface of communicating code to different systems.

passing tarballs around requires defining a bunch of new interfaces for those tarballs which adds a cost to every integration that you'd otherwise get for about free if you used git

Re: The cult of vibe coding is dogfooding run amok

#393

Post by dolebirchwood »

tovej wrote: post #239
eloisant wrote: post #177

Earlier quoted context omitted.

The very definition of "vibe coding" is using AI to write software and not even look at the code it produces.

People use two definitions. There's this definition of LLM generation + "no thorough review or testing" And there's the more normative one: just LLM generation.[1][2][3] "Not even looking at it" is very difficult as part of a definition. What if you look at it once? Or just glance at it? Is it now no longer vibe coding? What if I read a diff every ten commits? Or look at the code when something breaks? At which point…

It's a bit absurd that a semantic debate is happening over a term coined in someone's shower thought tweet. Maybe the real problem is that it's just a stupid phrase that should never have been taken so seriously. But here we are...

Re: The cult of vibe coding is dogfooding run amok

#394

Post by Fr0styMatt88 »

empath75 wrote: post #349
Fr0styMatt88 wrote: post #256

It’s so strange. I think there’s a few different groups: - Shills or people with a financial incentive - Software devs that either never really liked the craft to begin with or who have become jaded over time and are kind of sick of it. - New people that are actually experiencing real, maybe over-excitement about being able to build stuff for the first time. Forgetting the first group as that one is obvious. I’ve enc…

> I’ve encountered a heap of group 2. They’re the ones sick of learning new things, for whatever reason. I say this kindly, but are you sure that _you_ aren't the one in group 2, and _they_ aren't the ones learning new things? A lot of the discourse around ai coding reminds me of when I went to work for a 90s tech company around 2010 and all the linux guys _absolutely refused_ to learn devops or cloud stuff. It sucks…

That’s pretty fair, I’m currently in the “trying to get over the feeling that it’s cheating” phase and also just haven’t formed the habit yet of reaching for AI as a tool in my toolbox; particularly in things like pre-review AI-assisted code review, which I’ve found really useful but sometimes don’t think of doing when I could.

Re: The cult of vibe coding is dogfooding run amok

#395

Post by furyofantares »

hintymad wrote: post #216
furyofantares wrote: post #159

Earlier quoted context omitted.

> Kernighan's Law, which says debugging is twice as hard as writing the code in the first place. Now people are increasingly believing that AI can debug way faster than human (most likely because other smart people have done similar debugging already). And in the worst case, just ask AI to rewrite the code. I thought you were gonna go the opposite direction with this. Debugging is now 100x as hard as writing the code…

> I thought you were gonna go the opposite direction with this. Debugging is now 100x as hard as writing the code in the first place. 100x harder if a human were to debug AI-generated code. I was merely citing other people's beliefs: AI can largely, if not completely, take care of debugging. And "better", rewrite the code altogether. I don't see how that could be a better approach, but that might just be me.

I still run into plenty of situations where the LLM-agent wrote the code really inexpensively, but is totally unable to debug it, and you can sink tons of time trying to get it to do so before giving up with nothing to show for it, and trying to figure it out yourself.

Re: The cult of vibe coding is dogfooding run amok

#396

Post by nothinkjustai »

physicles wrote: post #350
Fr0styMatt88 wrote: post #256

It’s so strange. I think there’s a few different groups: - Shills or people with a financial incentive - Software devs that either never really liked the craft to begin with or who have become jaded over time and are kind of sick of it. - New people that are actually experiencing real, maybe over-excitement about being able to build stuff for the first time. Forgetting the first group as that one is obvious. I’ve enc…

You’re missing the group of high performers who love coding, who just want to bring more stuff in the world than their limited human brains have the energy or time to build. I love coding. I taught myself from a book (no internet yet) when I was 10, and haven’t stopped for 30 years. Turned down becoming a manager several times. I loved it so much that I went through an existential crisis in February as I had to let g…

[flagged]

Re: The cult of vibe coding is dogfooding run amok

#397

Post by somekindaguy »

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.

The traditional rules of good code are heuristics that are practical for human developers. A different set of heuristics will emerge for agentic development.

Re: The cult of vibe coding is dogfooding run amok

#398

Post by jannyfer »

furyofantares wrote: post #395
hintymad wrote: post #216

Earlier quoted context omitted.

> I thought you were gonna go the opposite direction with this. Debugging is now 100x as hard as writing the code in the first place. 100x harder if a human were to debug AI-generated code. I was merely citing other people's beliefs: AI can largely, if not completely, take care of debugging. And "better", rewrite the code altogether. I don't see how that could be a better approach, but that might just be me.

I still run into plenty of situations where the LLM-agent wrote the code really inexpensively, but is totally unable to debug it, and you can sink tons of time trying to get it to do so before giving up with nothing to show for it, and trying to figure it out yourself.

What kind of code do you work on, and what model & harness do you use? Genuinely curious so I can calibrate my understanding.

I work on enterprise web apps for a few dozen people with Codex CLI and GPT-5.4, and haven't really run in to those issues.

Re: The cult of vibe coding is dogfooding run amok

#399

Post by ben-schaaf »

tombert wrote: post #297
xienze wrote: post #288

Earlier quoted context omitted.

> I think that the prompt is the thing that should be PR'd at this point, because ultimately the spec is what's important. The fundamental problem there is the code generation step is non-deterministic. You might make a two sentence change to the prompt to fix a bug and the generation introduces two more. Generate again and everything is fine. Way too much uncertainty to have confidence in that approach.

If you make the prompts specific enough and provide tests that it has to run before it passes, then it should be fairly close to deterministic. Also, people aren't actually reading through most of the code that is generated or merged, so if there's a fear of deploying buggy code generated by AI, then I assure you that's already happening. A lot.

How is "fairly close to deterministic" anywhere near good enough? LLMS aren't anywhere near cheap enough to do this either.

That said it's so trivial to do, why haven't you done that already?

Re: The cult of vibe coding is dogfooding run amok

#400

Post by dragandj »

aerhardt wrote: post #286
jschveibinz wrote: post #215

Earlier quoted context omitted.

Here's my take: I think that citizen developers will be a thing--but not in the way you might be thinking. More people will be enabled (and empowered) to "build" quick-and-dirty solutions to personal problems by just talking to their phone: "I need way to track my food by telling you what I ate and then you telling me how much I have left for today. And suggest what my next meal should be." In the current paradigm--w…

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…

> An app is often much more than a CRUD interface. "I could have written Facebook over a weekend" syndrome :)
Post reply on HN