Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Will vibe coding end like the maker movement?

read.technically.dev

Post reply on HN
Print view View original

451–459 of 459 posts

Re: Will vibe coding end like the maker movement?

#451

Post by tultras »

I've just gotten into claude code after more than a year resisting it, due to reading that I'd get dumb, lazy and forget how to code.

But the truth is that claude code made programming much more fun to me: I skip the boring parts of writing code and hopping around files and focus on funcionality, architecture and code quality. Software engineering has never been about typing. I don't consider myself a typist (even though I'm very good at it). I'm an architect above all, and using claude code has allowed me to focus on the parts of the job I enjoy the most.

Only to be clear, I treat claude code as a junior developer that needs mentoring. I review every single diff it produces keeping an eye for patterns that go off standards, hardcoded values scattered throught the code, repeated function blocks, adequate tests and so on. I don't plan on leaving it all to claude code, because at the end of the day the one responsible for code in production is going to be me, not claude. But it's been a hell of a ride (not to mention the 30x productivity improvement, literally).

Re: Will vibe coding end like the maker movement?

#452

Post by peteforde »

fao_ wrote: post #448
peteforde wrote: post #429

Earlier quoted context omitted.

Again: not doing anything at all with health or chemistry. They aren't what I am interested in, even peripherally. What you seem to be missing is that LLMs are better at/for some things than others. Legal review, 3D geometry, therapy and apparently chemistry are off the list. It doesn't make sense to project that onto domains where it excels.

> What you seem to be missing is that LLMs are better at/for some things than others. I guarantee it is using the same system to write code and teach you about electronics that it is using to teach people about chemistry, and if you can't see how that means the resulting information is suspicious at best, then I don't even know what to say anymore.

The worst thing social media has done to our species is convince everyone that they are supposed to have something to say about everything.

It's genuinely alright to stfu sometimes when you don't have anything productive to add to the conversation.

Re: Will vibe coding end like the maker movement?

#453

Post by keybored »

stavros wrote: post #242
keybored wrote: post #235

Earlier quoted context omitted.

And I make visualizations by watching TV every day. My visual cortex just has a constant stream of making visualizations all day. All these maker types dropping that differentiator immediately in the name of pragmatism.

Yeah whatever, I'm not going to let you gatekeep my enjoyment. What's the last thing you made?

> Yeah whatever, I'm not going to let you gatekeep my enjoyment.

I see.

> What's the last thing you made?

Based on you outranking me in the gatekeeping hierarchy. :)

Re: Will vibe coding end like the maker movement?

#454

Post by stavros »

keybored wrote: post #453
stavros wrote: post #242

Earlier quoted context omitted.

Yeah whatever, I'm not going to let you gatekeep my enjoyment. What's the last thing you made?

> Yeah whatever, I'm not going to let you gatekeep my enjoyment. I see. > What's the last thing you made? Based on you outranking me in the gatekeeping hierarchy. :)

It's been four days, let it go man.

Re: Will vibe coding end like the maker movement?

#455

Post by testbyhuman_tor »

ramathornn wrote: post #363
wongarsu wrote: post #306

Earlier quoted context omitted.

> No, a non-engineer can't just spin up the next great app. Even with the newest models and a great prompting/testing system, I don't think you can just spit out high quality, maintainable, reliable code I think most engineers vastly overestimate how important high quality, maintainable, reliable code is to product success. Yes, you need an experienced engineer to steer Claude into making good high-quality code. But…

> I think most engineers vastly overestimate how important high quality, maintainable, reliable code is to product success. I agree, the only thing I can’t get past is the black box approach. For the majority of business stakeholders, they can’t/ don’t want to read the code that Opus, or any other agent produces. It will most likely work, but if it doesn’t, they have to rely on the agent to find & patch. I’m with you…

[dead]

Re: Will vibe coding end like the maker movement?

#456

Post by paulryanrogers »

peteforde wrote: post #328
paulryanrogers wrote: post #324

Earlier quoted context omitted.

Electronics can kill too. IIRC capacitors in CRTs are particularly deadly. Though I suppose someone using LLMs only as a first step, much like Wikipedia, is probably at much less risk than someone using it as their only source.

Yeah, okay but... look, I concede that someone who shouldn't be doing anything except watching passive entertainment could absolutely take insane advice from an LLM (or a sociopathic human) and seriously hurt themselves. But raw dogging capacitors in CRTs is such an overtly straw man argument in this conversation. People who are cleaning bathrooms for the first time can hopefully be trusted not to drink the bleach, r…

My concern is that about half of folks are below average intelligence. And new generations will be exposed to AI from a young age, possibly lacking the rigor and experience of those who came before. I'm afraid they will trust the AI too much, and find themselves quickly in over their heads with no way back.

Perhaps I'm just pearl clutching. I guess time will tell.

Re: Will vibe coding end like the maker movement?

#458

Post by fao_ »

peteforde wrote: post #452
fao_ wrote: post #448

Earlier quoted context omitted.

> What you seem to be missing is that LLMs are better at/for some things than others. I guarantee it is using the same system to write code and teach you about electronics that it is using to teach people about chemistry, and if you can't see how that means the resulting information is suspicious at best, then I don't even know what to say anymore.

The worst thing social media has done to our species is convince everyone that they are supposed to have something to say about everything. It's genuinely alright to stfu sometimes when you don't have anything productive to add to the conversation.

Indeed, which is exactly what you should have done, instead of writing a comment that is simply an insult.

Re: Will vibe coding end like the maker movement?

#459

Post by nachocoll »

Great post, and the "dark flow" framing really resonates — the productivity illusion described in the METR study alone should give every engineering team pause.

What strikes me reading this thread is how many of you have independently landed on the same conclusions: human accountability for generated code is non-negotiable, architecture has to drive generation (not the other way around), traceability matters, and you can't maintain what you don't understand.

These aren't just gut feelings — they're actually the core of something a few of us have been trying to formalize: the Agile Vibe Coding Manifesto (https://agilevibecoding.org). It explicitly builds on top of the original Agile Manifesto to address exactly this environment.

The four values it proposes — accountability over anonymous generation, traceable intent over opaque implementation, discoverable domain structure over scattered code, and human-readable documentation over implicit knowledge — map directly to what experienced engineers in this thread are describing: staying deeply in the loop, reading the core code, and defining architectural boundaries before letting AI generate within them.

It doesn't reject AI-assisted coding. It tries to answer: what disciplines do Agile teams need so that AI-generated code doesn't become a liability? Worth a look if this resonates.

Post reply on HN