Live data from Hacker News

Thoughts and feelings around Claude Design

samhenri.gold

161–170 of 253 posts

Re: Thoughts and feelings around Claude Design

#161
post #117

Earlier quoted context omitted.

> I used it today to take a look at my previously built design system with Logos, branding, fonts, and everything else. The fact that you are using this language tells me you are probably more advanced than the average individual, and likely have higher expectations. My sister-in-law has a small apparel company. She’s developed quite a bit of skill over the past six years but she really struggled at the start. She ha…

Funny. My read on that language was this person has absolutely no idea what a truly robust and scalable design system and component library actually are, particularly within the scope of a successful business. Well built ones serve every facet of the organization, not just the product.

Apologies to parent. This reply was intended for a separate thread.

Re: Thoughts and feelings around Claude Design

#162
post #47

Oh no. Figma has variables and instances and it's hard to debug bad colors. And here I am with Claude Code... That so far generated a 2000-line CSS file for a 7000-line app consisting of literally three web pages [1]. Where almost every single color, component, class and style is duplicated at least two times. Where custom classes are fighting with Tailwind classes (yes, there's also Tailwind ON TOP of custom CSS) th…

LLMs tend to do better with component libraries like shadcn or daisy than writing raw CSS in my experience.

Re: Thoughts and feelings around Claude Design

#163
post #33
post #30

Earlier quoted context omitted.

It's very easy to know when code is wrong: it doesn't work the way it's expected to. So you explain to the AI what's wrong and the AI fixes it.

Your designers are going to be looking at the layout; they're not going to notice if it's slow, uses too much memory, is not maintainable, doesn't follow repo patterns, etc. Do you think it is reasonable to expect a person with an arts degree to know this?

> Do you think it is reasonable to expect a person with an arts degree to know this?

There are plenty of people with arts degrees who know this, and PLENTY of dogshit engineers with CS degrees who don’t

Re: Thoughts and feelings around Claude Design

#164
post #132

Earlier quoted context omitted.

I used Claude Design to see how it'd spit out a design I already had been working on for some weeks, given a dense enough prompt and a decent requirements document (I did not feed it visuals). I thought the output was pretty good! It didn't match the style we're after at all but it did do some logical content grouping and made some IA decisions I decided to pull into my own explorations. Overall I left with a good im…

Homogenous might be awesome. I miss predictable UIs.

Good design is distinctive. No one wants a world where everything looks the same.

Re: Thoughts and feelings around Claude Design

#165

Earlier quoted context omitted.

Homogenous might be awesome. I miss predictable UIs.

Good design is distinctive. No one wants a world where everything looks the same.

Design is too broad a word for what is being discussed here and often in the world at large.

Still, to me, good design is intuitive. I look at the thing, and I know how to use it. If it looks great and distinctive, even better. But most outlandishly distinctive design I've (consciously?) found is terrible.

Obviously, these short sentences hide a lot:

- To know how to use things, I must have prior experience. But different users have different prior experiences and acquired design patterns (i.e. interaction patterns)

- My knowledge of the domain is also different from that of other users.

- The way I interact with the system is affected by many factors (e.g. accessibility related concerns, zoom, etc.)

- Intuition is not magic. It comes after training as well. Good design is discoverable. Extraordinary design reinforces its own patterns seamlessly, so that I learn it without even knowing I'm learning (see: hidden tutorials in game design). I also include here the incredible attributes of good design that far predate computer-related design (e.g. how an icon should be recognizable just by its silhouette, or how apps "invisibly" teach us what each color or even section of the screen means).

- My incentive to learn (sometimes "tolerate") the design depends on many variables. Some of these include the design's "taste", yes. Others depend on how much my boss/client is paying me to "use this shit".

I wouldn't say I want a world where everything looks the same, but I certainly want one where everything works the same, and some geniuses once in a while add something new to my list of known (and loved) design patterns. I am not anti-design-experiments, but I will take a predictable UI that looks like windows 98 everyday over some "distinctive" shit that breaks all manner of expected behaviors (from keyboard shortcuts, to colors, to button placement, to relative sizing, to........)

Re: Thoughts and feelings around Claude Design

#166

The article makes a good point about how Figma's non-open data model is limiting their utility as the source of truth. But I think it's part of a larger mistake Figma is making: they seem to have shifted to an extraction mindset too early, assuming they'd captured the market, right when the ground beneath them is starting to shift. It's most visible in their pricing model evolution, which is now explicitly anti-colla…

> The big tools that won on collaboration (eg. Google Docs) have understood that low-friction sharing is critical to becoming the default choice.

Google docs is a heavily subsidized product and not representative.

Also tool pricing seems hard, but I can’t really get behind saying that a company should bait and switch with their pricing models harder.

Re: Thoughts and feelings around Claude Design

#167

Earlier quoted context omitted.

lol yes. At least in agency world, a common approach in the last X years has been that designers create entire pixel-perfect, component-based sources-of-truth in Figma (which evolve! they aren't delivered static and complete) -- these are also what the client sees and approves, or at the very least they see branded deck slides that incorporate the Figma designs. Anyways, front end then re-implements from Figma into C…

Why don’t we just teach the designers code / the coders design? This feels very Programmer-Analyst split

Just teach backend engineers to do frontend pixel perfect CSS!

Different fields.

Re: Thoughts and feelings around Claude Design

#168
post #35

So let me get this straight (Pretend I'm 50, a developer since childhood, but I can't CSS to save my life) are there shops where developers, even front end developers, have to talk to designers who are't just sketching an idea for a logo or landing page, but designers who run this Figma thing and maintain the entire products "design" in some "style database"? And the idea is that these designers - who aren't develope…

I'm not sure about "without changing code" but I have definitely seen the believe that Figma represents something authoritative about the product instead of, say, the product being authoritative for itself. Perhaps because I have a similar bio to yours, I am allergic to this view.

Replace the word figma with the word “specification” and it seems pretty reasonable to me. Same thing. It’s not a belief, it’s a process.

Re: Thoughts and feelings around Claude Design

#169
post #117

I used it today to take a look at my previously built design system with Logos, branding, fonts, and everything else. After a lot of annoying tweaking back and forth, finally, I got something that was satisfactory. Then I looked at the usage and it said I had used 95% of my Claude design usage for the week! This isn't a real tool. This is a plaything, if that's what they're providing as examples.

> I used it today to take a look at my previously built design system with Logos, branding, fonts, and everything else. The fact that you are using this language tells me you are probably more advanced than the average individual, and likely have higher expectations. My sister-in-law has a small apparel company. She’s developed quite a bit of skill over the past six years but she really struggled at the start. She ha…

> The fact that you are using this language tells me you are probably more advanced than the average individual, and likely have higher expectations.

I am terrible at frontend, but I’m a decent engineer, and I needed to do frontend with AI a few weeks ago. The first thing I did is figure out how other people manage this; apparently there’s a whole design system made of atoms, molecules and organisms that works well.

I asked Claude about this, set up a workflow together, and now I have a design system markdown, maintaining the design standards using the atoms etc vocabulary, and it works really well.

If I can pick this up in a few days, most people that are serious about design are able to as well.

Re: Thoughts and feelings around Claude Design

#170
post #42

Earlier quoted context omitted.

HTML and CSS, sure, but modern frontend design is way more than that; it's a jungle out there.

React, Nextjs, Vue, Nuxt, and Angular are pretty much what AI is the very best at coding in my experience. Probably because they are all meant to build essentially the same thing with different curtains.

Ever seen a vibe-coded react app? It's astounding how well SOTA LLMs can produce good looking code in detail, but zoom out to the architectural or broader picture and it becomes an unholy mess.

It's like a masterpiece painted by an artist with their nose 5 inches from the canvas at all times.

Post reply on HN