---

title: Vibe Coding

subtitle: But the vibes are off

permalink: '/text/vibe-coding/'

tags:

- cat:development

- cat:ai

- cat:technology

- cat:web-development

- cat:accessibility

- state:draft

intro: Vibe coding might be the answer, but how much is the fish?

date: 2025-11-01

---

Being a developer in the year 2025 is easy. All you need to do is get 20 dollar, hand them over to Cursor, Claude Code, Windsurf or whatever the tool de jour might be, and off you go. Others, have [been but a fraud](https://www.businesstoday.in/technology/news/story/700-indian-engineers-posed-as-ai-the-london-startup-that-took-microsoft-for-a-ride-478514-2025-05-31).

Being an AI-skeptic developer in the year 2025 is not that easy. [You might be called nuts in popular blog posts](https://fly.io/blog/youre-all-nuts/). Blog posts that are, frankly, a bit nuts.

## Setting the field

So, how did we end up in this very peculiar moment? How can there companies that promise that you can just insta-wish the app you’ve been dreaming off into being, and how can there be pundits that believe this?

To make one thing very clear: I strongly believe that, for good or for worse, probably for both, software development _will change drastically_. Used responsibly, AI coding tools can be an incredible tool. I have used them myself. But it is despite, not because of it, that I’m weary of the debate. And antagonistic to the hype.

## Development is a social activity – yes, even if you code alone

The section where I situate technological solutions in the realm of the social

### Accessibility

Accessibility is an area that human developers already treat with an astounding level of neglect, though rarely anyone will say that much.

It doesn’t matter which model in which version. The first generated result for a website will likely be the infamous soup of `<div>`s accessibility advocates have railed again for decades now.

I bring this up as it makes a case in point: Coding assistants generate code based on prevalence in thetraining data combined with some finetuning, reinforcement learning, whatever. None of this guarantees quality. It guarantees the middle of a bell curve.

There might be better languages. Or worse. But the middle of the bell curve of web development is [inaccessible, error ridden, unsemantic crap](https://webaim.org/projects/million/). I’ve done [my share of this](/text/the-value-of-old/). We all have. Because we all are learning. Constantly. And code we have published can survive years and years once we stop maintaining sites.

There are so many demos showcasing something cool, so many websites just pushed out as fast as possible, so much code generated by Wix or whatever the older cousins of Claude & Co. have been called that just give a crap about semantics, or anything besides _looking good_.

The small number of carefully curated, tested, and robust examples will – unfortunately – be drowned out. This was a problem with human curation already. It is unsurmountable when developers who don’t know better get code generated by a machine that claims it knows best.

### Ain’t reading all that, I’m happy for you though

Creating code with the help of agents can be incredibly rewarding. Even though the user experience itself is, frankly, annoying. The bots are helpful but their tone of voice is so obedient it at times makes me want to [poison a dataset](https://www.anthropic.com/research/small-samples-poison).

Anyway, you will likely hit the ground running and have something

In this nut piece I mentioned earlier, the author claims «LLMs only produce shitty code if you let them». At the same time, he also claims that experienced vibe coders have agents running and only review the code.

Yes, true. All of todays coding assistant are _incredibly good_ at producing code. They will write a lot of it, and — if you’ve mastered the skill of writing the prompts — most it will solve your ~problems~ thing you mentioned in your prompts.

### Or sorry that happened

Sooner or later the context will collapse. The output will repeat and repeat and repeat and repeat and rep… sorry.

Sooner or later you will end up with hundreds, maybe even thousands of lines of code noone on your team feels confident to review, refactor or reason about. Is this how it is now? The new state of the art.

Sooner or later some bug will sneak up in production. It might be subtle. It _will be_ subtle. At first. But at one point if you trust the systems more and more and get more lenient in reviewing its output, the bug will be more serious. I’m sorry that happened, future me or future you.

All of the engineers I’ve seen so far have been pretty vigilant during the first generation. The second, the third. But over time laziness creeps in – misplaced trust in a system that convincingly puts out stochastic prediction clouded as truth.

Software engineering is really making an art out of a making a fool of itself.

But truly, it’s not just software engineering. Mathy math slop machines are shoved into every corner of the economy and our lives at breakneck speed, and [slow success](https://www.ft.com/content/e93e56df-dd9b-40c1-b77a-dba1ca01e473). Everything is generated so much that [no one is really keeping up](https://hbr.org/2025/09/ai-generated-workslop-is-destroying-productivity).

I’m sorry that happened for us all.

Luckily there is:

## The future

Just kidding.

### The breakdown

##