Live data from Hacker News

Vibe coding is mad depressing

law.gmnz.xyz

31–40 of 168 posts

Re: Vibe coding is mad depressing

#31

This article is not about vibe coding per se, it's about not having strong boundaries between you as the developer, and your client. You should not be allowing the client to dictate how you work, much less them having the permissions to merge in code. This was true before AI too, where clients might say, do X this way, and you should simply say no, because they are paying for your expertise*. It's like hiring a plumb…

Video/audio production here and the exact same rules apply. You can’t let clients dictate your tools any more than you feel you should tell your plumber what they can use to fix your sink.

“We use Premiere.” Cool. I use Resolve. If we aren’t collaborating on the edit then this is an irrelevant conversation. You want a final product, that’s what you hired me for my dude. If you want me to slot into your existing editing pipeline that’s a totally different discussion.

“Last guy shot on a Red.” Cool. Hire them. Oh right you hired me this time. Interesting! Should we unpack that?

Freelancers: Stand your ground! Stand by your work! Tell clients to trust you!

Re: Vibe coding is mad depressing

#32
This is all over linkedin now. Basically, idea bros manage to get their ideas seemingly working with vibe coding but the moment it breaks they expect they can just "pay to fix the small broken part" and get back to work quickly. Not realising the cost that the developer has to get up to date on the project, then probably fix a mountain of poorly done, insecure work to "quickly finish" the project. A lot of them are also scammers and try to get you to start work on it without even having an contract.

Not really worth working on any of these project.

Re: Vibe coding is mad depressing

#33

For me vibecoding has a similar feeling to a big bag of Doritos. It's really fun at first to slap down 10k lines of code in an afternoon knowing this is just an indulgence. I think AI is actually really useful for getting a quick view of some library or feature. Also, you can learn a lot if you approach it the right way. However, every time I do any amount of vibecoding eventually it just transitions into pure lethar…

I have yet to find the niche where it is "good at the beginning". So far I've mostly tried asking to build C tools that use advanced linux API.

Me: hey make this, detailed-spec.txt

AI: okidoki (barfs 9k lines in 15 minutes) all done and tested!

Me looks at the code, that has feature-sounding names, but all features are stubs, all tests are stubs, and it does not compile.

Me: it does not compile.

AI: Yes, but the code is correct. Now that the project is done, which of these features you want me to add (some crazy list)

Me: Please get it to compile.

AI: You are absolutely right! This is an excellent idea! (proceeds to stub and delete most of what it barfed). I feel really satisfied with the progress! It was a real challenge! The code you gave me was very poorly written!

... and so on.

Re: Vibe coding is mad depressing

#36
post #33

For me vibecoding has a similar feeling to a big bag of Doritos. It's really fun at first to slap down 10k lines of code in an afternoon knowing this is just an indulgence. I think AI is actually really useful for getting a quick view of some library or feature. Also, you can learn a lot if you approach it the right way. However, every time I do any amount of vibecoding eventually it just transitions into pure lethar…

I have yet to find the niche where it is "good at the beginning". So far I've mostly tried asking to build C tools that use advanced linux API. Me: hey make this, detailed-spec.txt AI: okidoki (barfs 9k lines in 15 minutes) all done and tested! Me looks at the code, that has feature-sounding names, but all features are stubs, all tests are stubs, and it does not compile. Me: it does not compile. AI: Yes, but the code…

It's terrible at the niches I actually have expertise in, which are in mathematics. I'd guess an expert is going to find the flaws in anything it's doing in their field. That being said, if you're just trying to e.g. see what some GUI library can do then it's pretty useful to get something going. I personally would prefer not using it in anything that's not very much a throwaway test project though, but that is my luxury as a jobless bum.

Re: Vibe coding is mad depressing

#37
post #8

All the consulting practice arguments aside, this is fundamentally a gatekeeping argument about clients staying in their lane. I'm sure doctors feel the same way about patients with weirdly specific questions about HFpEF diagnoses. Doctors have always hated "Doctor Google", and now they have to contend with "Doctor GPT". It's up to you how much sympathy to have for them.

I think you hit the nail on the head with the analogy to Doctor GPT, but I think you missed it with gatekeeping. I don't think it's about gatekeeping at all.

A freelance developer (or a doctor) is familiar with working within a particular framework and process flow. For any new feature, you start by generating user stories, work out a high level architecure, think about about how to integrate that into your existing codebase, and then write the code. It's mostly a unidirectional flow.

When the client starts giving you code, it turns into a bidirectional flow. You can't just copy/paste the code and call it done. You have to go in the reverse direction: read the code to parse out what the high level architecture is, which user stories it implements and which it does not. After that you have to go back in the forward direction to actually adapt and integrate the code. The client thinks they've made the developer's job easier, but they've actually doubled the cognitive load. This is stressful and frustrating for the developer.

Re: Vibe coding is mad depressing

#38
post #33

For me vibecoding has a similar feeling to a big bag of Doritos. It's really fun at first to slap down 10k lines of code in an afternoon knowing this is just an indulgence. I think AI is actually really useful for getting a quick view of some library or feature. Also, you can learn a lot if you approach it the right way. However, every time I do any amount of vibecoding eventually it just transitions into pure lethar…

I have yet to find the niche where it is "good at the beginning". So far I've mostly tried asking to build C tools that use advanced linux API. Me: hey make this, detailed-spec.txt AI: okidoki (barfs 9k lines in 15 minutes) all done and tested! Me looks at the code, that has feature-sounding names, but all features are stubs, all tests are stubs, and it does not compile. Me: it does not compile. AI: Yes, but the code…

Include in the prompt a verifiable testable exit criteria (compiling) and use agentic AI like cursor or codex with this, you’d be surprised what happens :)

Re: Vibe coding is mad depressing

#39
post #4

We’re in the geocities phase of LLM, mostly trash, very basic, but eventually, people will either get bored and go back to whatever it is they were doing or actually use the tools for useful and productive work. As for the feelings that using LLM has when it one shots your project start (and does a pretty good job), have a German word: Automatisierungskummer (automation sorrow) • Kummer is emotional heaviness, a mild…

Some remember the Geocities era as one of the best phases of the internet. Its hard to know what things will look like in 20 years but people may miss the time when AI cost nothing, or very little, and was less fettered. I think probably not- it would be like being nostalgic for really low-res, low frame youtube videos, but nostalgia is pretty unpredictable and some people love those old FMV games.

"but people may miss the time when AI cost nothing" - That's been on my mind a lot... it's like I feel like I have to use it more or I'll regret it! I am not looking forward to the AI talking about NordVPN injected into the session.
Post reply on HN