Live data from Hacker News

Scoring Show HN submissions for AI design patterns

adriankrebs.ch

201–210 of 258 posts

Re: Scoring Show HN submissions for AI design patterns

#201
post #8

I expect most side-projects are being built with AI-assistance now. Side projects are typically time constrained - if AI saves you time, why wouldn't you use it? They're also the ideal place to try out new AI tools that your professional work might not let you experiment with. (The headline of this piece doesn't really do it justice - it misuses "vibe coded" and fails to communicate that the substance of the post is…

My biggest issue with LLM‑assisted webpages (Claude Code is especially egregious) is the lack of respect for basic web content accessibility guidelines. The number of dark‑mode sites I’ve seen where the text (and subtext) are various shades of dark brown or beige is just awful. For reference, you want a contrast ratio between the text and background of at least ~4:1 to be on the safe side. This isn't even that hard t…

If you have some good sources let me know, I'll turn it into a guide that Claude can read

Re: Scoring Show HN submissions for AI design patterns

#202
> Every pattern is a deterministic CSS or DOM check. I intentionally do not take screenshots and let the LLM judge them.

I use LLM models in my side projects like this guy uses them. So many times I spent days and weeks on a side project just to make sure it was perfect only to to have 0 interest from anyone else after sharing.

Re: Scoring Show HN submissions for AI design patterns

#203
post #9

Nice list of design patterns, but imo a big unmentioned one is a grid of rounded rects https://correctarity.com/roundedrects (maybe what this post calls "Icon-topped feature card grid." ...that might be the official design pattern term)

I think that's more of a NextJs thing than an LLM thing.

Re: Scoring Show HN submissions for AI design patterns

#204
post #8

I expect most side-projects are being built with AI-assistance now. Side projects are typically time constrained - if AI saves you time, why wouldn't you use it? They're also the ideal place to try out new AI tools that your professional work might not let you experiment with. (The headline of this piece doesn't really do it justice - it misuses "vibe coded" and fails to communicate that the substance of the post is…

> Side projects are typically time constrained - if AI saves you time, why wouldn't you use it?

There could be many reasons to not use ai in a case like this, eg: retaining more control, breaking some new ground, because it’s fun, because it’s personal, etc.

Re: Scoring Show HN submissions for AI design patterns

#205

Earlier quoted context omitted.

My biggest issue with LLM‑assisted webpages (Claude Code is especially egregious) is the lack of respect for basic web content accessibility guidelines. The number of dark‑mode sites I’ve seen where the text (and subtext) are various shades of dark brown or beige is just awful. For reference, you want a contrast ratio between the text and background of at least ~4:1 to be on the safe side. This isn't even that hard t…

If you have some good sources let me know, I'll turn it into a guide that Claude can read

I use the W3 preliminary guidelines - you could try adapting them into a bespoke skill as a good start.

https://www.w3.org/WAI/test-evaluate/preliminary

Another possibility (although I’ve never actually tried this myself) is an MCP server that someone built specifically to connect to Lighthouse, which includes accessibility testing as part of its benchmarks.

https://github.com/priyankark/lighthouse-mcp

Re: Scoring Show HN submissions for AI design patterns

#206
post #65

Earlier quoted context omitted.

I've genuinely had solid results from telling Claude "... and make sure it has good accessibility".

Something I've noticed when people complain about stuff like accessibility or other things that LLMs do "wrong", it really is a case of "you're holding it wrong." The LLM does indeed know how to do it right and it sometimes does so autonomously but when it doesn't, you can simply ask it to do so. In other words, I've found people like the above to think of LLMs as fairly static, as if we couldn't change their behavio…

[dead]

Re: Scoring Show HN submissions for AI design patterns

#207

Earlier quoted context omitted.

My biggest issue with LLM‑assisted webpages (Claude Code is especially egregious) is the lack of respect for basic web content accessibility guidelines. The number of dark‑mode sites I’ve seen where the text (and subtext) are various shades of dark brown or beige is just awful. For reference, you want a contrast ratio between the text and background of at least ~4:1 to be on the safe side. This isn't even that hard t…

I think this is a second order thing when you are building a side project.

[dead]

Re: Scoring Show HN submissions for AI design patterns

#208
post #8

I expect most side-projects are being built with AI-assistance now. Side projects are typically time constrained - if AI saves you time, why wouldn't you use it? They're also the ideal place to try out new AI tools that your professional work might not let you experiment with. (The headline of this piece doesn't really do it justice - it misuses "vibe coded" and fails to communicate that the substance of the post is…

> Side projects are typically time constrained - if AI saves you time, why wouldn't you use it? It depends what your goals are. All of my side projects were started because I wanted to learn something. Using a "skip to the end" button wouldn't really make sense for me.

The person’s goals might not be spending a lot of time on CSS. Because a person who just does everything from scratch may find themselves learning about what FlexBox is or why your z-index isn’t working.

Going off of the two screenshots in the OP, neither of those were about frontend.

So if the choice is spending time designing a more human frontend or spending more time on the core product, I don’t fault people for choosing the latter.

Now if the core product also stinks, that’s a different issue.

Re: Scoring Show HN submissions for AI design patterns

#210
Is this not the ultimate “judging a book by its cover”?

Let’s take the opposite case, where someone handcrafted a website but the actual project/product was just a vibecoded mess? Is that not infinitely worse? Imo, what matters is what they actually made with the thing.

I get that these LLMs are pumping out ugly websites. But unless the product is a design system or website builder, it’s not my main concern.

Post reply on HN