Most things that people who don't know how to code want to build are not actually dead simple, and they often won't be able to articulate what they need very well.
Ironically, an experienced coder that needs a specific and simple tool quick will have a better time.
> Most things that people who don't know how to code want to build are not actually dead simple, and they often won't be able to articulate what they need very well.
I think it's wrong to frame vibe coding as something that's done by people who don't know how to code. Those who I see effectively vibe coding things tend to be staff- and senior-level engineers, who use it to speed up implementations while focusing on architecture.
What I see as the main obstacle to vibecoding at the moment is that vibecoding is mainly effective at greenfield development projects with little to no prior contrext, and that small-scope work over reasonably sized projects ends up being iterative, time-consuming, and with mixed results.
One of the factors I've noticed is that legacy projects gravitate towards messy, unstructured, poorly maintained projects. When these projects carry huge contexts that tend to be unstructured and inconsistent, coding agents have a hard time outputting anything that is worthy of the term "improvement".
Another issue with legacy projects is that maintainers often don't have the full picture of what the codebase does and is expected to do. They at best gain enough context to do tactical changes whose scope is minimized. Coding agents don't show the same concern, and often propose sweeping changes that can and often do introduce regressions. That's frowned upon tactical-minded programmers, who don't want the risk or the work of testing and verifying their changes.
As someone who vibes codes web apps that are being used by people, they take way way longer than initially expected. The prototype can take one shot, and the full prod implementation can take weeks to months. If you aren’t able to stick it out it will die but if you are willing to learn how to prompt to integrate Auth, email, security, performance than you can create truly incredible apps with no coding experience. But it’s basically a new skill in and of itself. Claude Code already gets the prototype to final product gap down a lot because it’s so good and getting better but it still makes mistakes and needs lots and lots and lots of nudging and directing and reminders and writing docs and getting other agents to check work based on docs ect.
When you say with no coding experience, what does that mean to you? I can get near miraculous results from vibe coding, but it often gets stuck in weird “bug loops” where it goes back and forth between broken states, and I have to understand either like bracket formatting, or be able to research library failures and conflicts. I suppose with no coding experience I could maybe muddle through, but itw would require hours of patience and probably learning some coding fundamentals to do something I can identify in sometimes seconds.
This guy keeps writing negative articles trying to wish into existence his bad call on the usefulness of LLMs. He really isn’t an expert, as he claims. Instead he cherry picks anecdotes to feed his confirmation bias.
Even if “vibe coding” is dying, there is a very real boost to the productivity of people writing software from AI based tools. That’s here to stay, even if there is a human element in working with those tools. Vibe coding is not dying, unless you reductively try to define it in very limited ways.
A tool for non technical people to build things within reason.
I don't know how you're trying to define vibe coding, but I would definitely put it as more of a pejorative/negative term.
I have 20+ years of coding experience, I use coding agents well, and I'm not a vibe coder.
I would also bet that vibe coding will never become good enough to replace me because the models will never have enough context window for an entire repo of a complex app. LLMs can output code for you, but coding is only part of the job.
Tradition is circular, it's only done based on tradition. I would prefer to call it classical coding because it's still useful in modern frameworks and a wonderful base skill set that can enhance current practice. Take for example, Bogo sort, a "trad" algorithm. No one uses it and the only reason people would use it is to continue some kind of tradition. Merge sort is one of the classics. Asking an LLM to sort a list might be a modern approach, but sometimes the classics are there for a reason.
kylecazar|3 months ago
Ironically, an experienced coder that needs a specific and simple tool quick will have a better time.
locknitpicker|3 months ago
I think it's wrong to frame vibe coding as something that's done by people who don't know how to code. Those who I see effectively vibe coding things tend to be staff- and senior-level engineers, who use it to speed up implementations while focusing on architecture.
What I see as the main obstacle to vibecoding at the moment is that vibecoding is mainly effective at greenfield development projects with little to no prior contrext, and that small-scope work over reasonably sized projects ends up being iterative, time-consuming, and with mixed results.
One of the factors I've noticed is that legacy projects gravitate towards messy, unstructured, poorly maintained projects. When these projects carry huge contexts that tend to be unstructured and inconsistent, coding agents have a hard time outputting anything that is worthy of the term "improvement".
Another issue with legacy projects is that maintainers often don't have the full picture of what the codebase does and is expected to do. They at best gain enough context to do tactical changes whose scope is minimized. Coding agents don't show the same concern, and often propose sweeping changes that can and often do introduce regressions. That's frowned upon tactical-minded programmers, who don't want the risk or the work of testing and verifying their changes.
lil-lugger|3 months ago
techblueberry|3 months ago
bji9jhff|3 months ago
SilverElfin|3 months ago
Even if “vibe coding” is dying, there is a very real boost to the productivity of people writing software from AI based tools. That’s here to stay, even if there is a human element in working with those tools. Vibe coding is not dying, unless you reductively try to define it in very limited ways.
paool|3 months ago
A tool for non technical people to build things within reason.
I don't know how you're trying to define vibe coding, but I would definitely put it as more of a pejorative/negative term.
I have 20+ years of coding experience, I use coding agents well, and I'm not a vibe coder.
I would also bet that vibe coding will never become good enough to replace me because the models will never have enough context window for an entire repo of a complex app. LLMs can output code for you, but coding is only part of the job.
vips7L|3 months ago
dangus|3 months ago
For all we know the right side of the graph is actually representing something else like accelerating layoffs in the tech industry.
If I’m unemployed I’m perhaps not doing AI code completion like I do at work.
ares623|3 months ago
kittikitti|3 months ago
elcritch|3 months ago
postalrat|3 months ago
dickersnoodle|3 months ago
red-iron-pine|3 months ago