Is AI bad at frontend work? Perhaps if your page has some special aesthetic design constraints, reaching the realm of "art," and needs to follow a design mockup at the pixel level, then maybe that is true.

But unfortunately, the vast majority of people's pages are not like that. They just need a page that works. Ease of use and visual polish are both more advanced goals. And frontend pages written by AI—with only a bit of guidance from prompts, not even necessarily very good prompts (though of course precisely defined CSS styles and similar details will naturally produce much better results)—can end up far more polished and complete than what they would have written themselves.

Just look at the frontend work people made with Claude Code within only a few hours after the Claude Code source leak: https://news.ycombinator.com/item?id=47597085#47598853

Or look at what frontend pages written in the pre-AI era were like. For example, Debian's: https://www.debian.org/index.zh-cn.html

Or SQLite's: https://sqlite.org/

Here is another example: the official FreeBSD website: https://www.freebsd.org/

There are so many examples that I do not even need to pick them at random. These are at least world-famous major projects, and while their page design and practicality are not bad, they certainly cannot be called refined. As for the many much worse websites out there—sites that are genuinely painful to use—those are everywhere. Government websites are an obvious disaster zone. Or just look at the Japanese internet.

Do not have unrealistic fantasies about the skill level of most frontend developers. In fact, I believe that among frontend engineers as a whole, if we ignore efficiency and look purely at display quality, Claude is already good enough to rank at least in the top 5%—and that is probably still an underestimate.

I am in China, and in the past month I have heard two news stories: two well-known companies—iFlytek and NetEase—laid off all of their frontend staff and instead had backend engineers use Claude to generate the frontend.

I am not a frontend engineer myself, and it is beyond doubt that without the help of LLMs, the visual quality of the projects I write would be much worse. Not to mention building Windows native applications that actually fit Fluent guidelines despite having absolutely no prior WinUI 3 background.

▲

bryanhogan 3 days ago | parent [-]

> Just look at the frontend work people made with Claude Code within only a few hours after the Claude Code source leak: https://news.ycombinator.com/item?id=47597085#47598853

I mean, yes look at the vibe coded sites people made after the second Claude Code leak! They are horrible, there are so many issues with them. Look at the existing comments some people with front-end / design knowledge made there.

Just because bad website existed before AI does not mean we should be happy to pump out more bad websites with AI.

▲

linzhangrun 3 days ago | parent [-]

However, it is obvious that if it were humans, even several hours would clearly not be enough time to create not only a visually stunning website but even a basic one, such as the pure text site introducing Lua itself (https://www.lua.org/manual/5.5/) (which achieves such visual presentation by uniformly using a set of templates designed by Lua itself)—that's very difficult, isn't it? Given the author one or two days, I believe most those detail issues mentioned in the comments could be fixed. Most problems stem from the "rush to release a half-finished product within a few hours to gain traffic" approach. Of course, such impatience is a common issue in many VibeCoding projects, like OpenClaw, but this is not a problem with AI's capability to write front-end code.

▲

bryanhogan 3 days ago | parent [-]

I mean, there's a fundamental missing understanding of how to build a coherent design, then there's also the problem of just poor implementation such as the animations.

The Lua site has some problems as well, like an uncessary border, text size and spacing, even when it's this minimal. You can get much faster and better results from using or taking inspiration from something like Astro Starlight or UnoCSS

Astro Starlight: https://starlight.astro.build/

UnoCSS: https://unocss.dev/

But of course, I agree that with AI you can create websites much faster, but it doesn't replace the knowledge needed to build a "good website".

	▲	linzhangrun 3 days ago \| parent \| next [-]
		Yes, that is what I mean: most front-end work does not require exceptional creativity or especially polished visual effects. Many people comment that AI-generated pages are extremely mediocre, but that “mediocre” result is already quite good in practice. In the software-related examples I mentioned, whether it is Debian, FreeBSD, SQLite, or Lua—and even Python’s official site, which I would already consider one of the better examples in this category—the visual quality clearly does not reach the same level as the supposedly “mediocre” output generated by AI. These are already some of the best projects in the world. At least their front-end interfaces still show traces of a coherent design language. As for what the broader landscape looks like, I do not think that needs much explanation. This is not really a matter of capability. It is simply that, before AI, people were generally unwilling to spend more effort on these pages. For people in the pre-AI era, this was already good enough. Of course, websites for front-end-related tools tend to look better. Besides the two examples you mentioned, sites like Vue and Bun also look quite good. Even so, I do not think they necessarily have any significant visual advantage over what Claude generates. Let’s return to the title: “Why AI Sucks at Front End?” Does Claude produce genuinely awful page designs? If so, then are not all the examples above—and many, many more—also quite awful by the same standard? That alone is enough to challenge the premise of the question. To criticize AI-generated pages for “lacking innovative design” and being “too mediocre” is really an overly rarefied standard. It forgets what most of the world’s front-end actually looks like, does it not?
	▲	linzhangrun 3 days ago \| parent \| prev [-]
		Suddenly remembered, isn't Hacknews itself the best counterexample of frontend design? Deliberately minimal styling to ensure content focus, lol :P I believe generating https://news.ycombinator.com with Claude should be a piece of cake.