Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Thoughts and feelings around Claude Design

samhenri.gold

Post reply on HN
Print view View original

151–160 of 253 posts

Re: Thoughts and feelings around Claude Design

#151

Post by ceejayoz »

hbosch wrote: post #132
mickdarling wrote: post #51

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 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.

Re: Thoughts and feelings around Claude Design

#152

Post by b212 »

miohtama wrote: post #127
alwillis wrote: post #119

Earlier quoted context omitted.

Things to keep in mind: • Claude Design uses Opus 4.7, which is more expensive than earlier models. • It's just Day 2; it's not a finished product. It's ridiculous how quickly Anthropic iterates. • If you've been using Claude for a while, Design already knows your style and preferences. You'd have to start from scratch using a different AI design tool. I don’t doubt that'll pay dividends in the long run.

They can iterate fast, because their devs and only their devs have access to the best Claude Code on the planet.

They iterate fast because they slap different names at the same thing they’ve been selling for years now.

Re: Thoughts and feelings around Claude Design

#153

Post by skydhash »

apsurd wrote: post #121
skydhash wrote: post #113

Earlier quoted context omitted.

Even with bootstrap, design was a solved problem. What you bring with a UI designer is appeal (aka make thing pretty and enjoyable). If you want utilitarian, even the old x11 toolkit like Athena, Win 98 era widgets would do the part.

This is just completely false. But I have a feeling there's no way you're going to change your mind. "make things pretty" would be a graphic designer or artist. Are you saying the entire arm of Product design is a made up value?

I wouldn’t, but you’re not much of a product designer if you can’t get your ideas across using simple tools like a sketch on a whiteboard (there was|is an app the let you take photos and link them using active areas).

So you can take bootstrap (or even raw html) and create something useful. Then you make it nice, not the other way around.

You would have to be a big outlier to feel the need to create a custom widget. Most widgets have been defined since decades.

Re: Thoughts and feelings around Claude Design

#154

Post by chr15m »

markbao wrote: post #28

I don’t really buy that Claude Design will remove all the complexity around design. Vibe-coded apps using Claude look simpler because they are simpler. They’re not a gigantic product suite with extremely specific UI components tailored to each use case. The ‘simplicity’ is an illusion coming from conflating the complexity of a bicycle (a vibe coded app) with an airplane (an app like Figma). Building the same design s…

Making the complexity simpler is the whole thing. Any software that does it wins.

Re: Thoughts and feelings around Claude Design

#155

Post by apsurd »

skydhash wrote: post #153
apsurd wrote: post #121

Earlier quoted context omitted.

This is just completely false. But I have a feeling there's no way you're going to change your mind. "make things pretty" would be a graphic designer or artist. Are you saying the entire arm of Product design is a made up value?

I wouldn’t, but you’re not much of a product designer if you can’t get your ideas across using simple tools like a sketch on a whiteboard (there was|is an app the let you take photos and link them using active areas). So you can take bootstrap (or even raw html) and create something useful. Then you make it nice, not the other way around. You would have to be a big outlier to feel the need to create a custom widget.…

I agree that design is about primitives. wireframes and IA should come across clearly at any fidelity.

But i don't think that's what tailwind and bootstrap are doing. But people very much use these tools to "solve design".

The layouts, widgets, and primitives in these tools are not primitives. I can't deny they get tons of people very far very fast. But my main disagreement is that all of this isn't design and it's not what designers do. You touched on what i agree with: UX flows, diagrams, stories, journeys, personas, etc, these all need to be designed and connected in reality using various primitives for the medium.

Then you slap a cohesive paint job on it, interaction elements, tone and terminology and yes, there is that element of design too.

Re: Thoughts and feelings around Claude Design

#156

Post by esafak »

only-one1701 wrote: post #39
operatingthetan wrote: post #29

Earlier quoted context omitted.

I think the real question is which of the four roles is going to be the one that takes over. Probably people who were already UX-Engineers.

I would ask this: which is the worse failure mode —- design not quite right, or users can’t access the app?

That's the kind of question you will have to ask if you don't hire right. I get collapsing frontend/backend and PM/UI/UX but two then collapse code and product may be a bridge too far.

Re: Thoughts and feelings around Claude Design

#157

Post by andai »

ceejayoz wrote: post #151
hbosch wrote: 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.

Damn you just made me realize.

We used to have everything having personality but being consistent as far as UX goes.

Now everything looks like tax forms and the UX is all over the place.

Re: Thoughts and feelings around Claude Design

#158

Post by andai »

juliusceasar wrote: post #64
markbao wrote: post #28

I don’t really buy that Claude Design will remove all the complexity around design. Vibe-coded apps using Claude look simpler because they are simpler. They’re not a gigantic product suite with extremely specific UI components tailored to each use case. The ‘simplicity’ is an illusion coming from conflating the complexity of a bicycle (a vibe coded app) with an airplane (an app like Figma). Building the same design s…

Most of the times people just want a bike or a car. Not everybody needs an airplane. This is going to hit Figma very hard.

Are those people using Figma?

Re: Thoughts and feelings around Claude Design

#159

Post by versteegen »

alwillis wrote: post #134
deadbabe wrote: post #125

Earlier quoted context omitted.

It will never be cheaper than what it is today. Anthropic is heavily subsidizing.

> It will never be cheaper than what it is today. Anthropic is heavily subsidizing. We don't know that for sure—they've dropped prices before: 1. Claude 3 → Claude 3.5/3.7 generation (mid-2024 to early 2025): Haiku went from $0.25/$1.25 to $0.80/$4.00 per MTok — this was actually a price increase for Haiku, but Sonnet stayed flat at $3/$15 while delivering significantly better performance, effectively a price-per-cap…

They're definitely not subsidizing API pricing, can't believe how prevalent that fallacy is on HN of all places. The question is how profitable Claude Code is. Your example 2 is real and major but your example 1 is ridiculous, almost any new model from any company is better at the same price, and how is increasing the price an example of decreasing prices??

BTW, Github Copilot is pricing Opus 4.7 at 2.5x the cost of Opus 4.6 at promotional pricing (so maybe it'll be 4-5x). But Github's request based pricing is insane, completely divorced from their actual costs (you can achieve 1+M tokens for $0.10 if you give it a large request), so I'd assume they're losing a lot of money.

Re: Thoughts and feelings around Claude Design

#160

Post by wahnfrieden »

freeone3000 wrote: post #139
kevinsync wrote: post #32

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

Design management will say that they don’t want to limit the designers’ creativity.
Post reply on HN