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

Claude Design

anthropic.com

Post reply on HN
Print view View original

201–210 of 819 posts

Re: Claude Design

#201

Post by _the_inflator »

Lovable was a TailwindCSS recombinator, that’s it.

Lately it is more and more ShadCN as well.

TailwindCSS is a masterpiece but ironically doesn’t really get its fare share while “Build on top of TW” frameworks make money.

TailwindCSS is the final evolution after all other frameworks always had its benefits but also massive limitations.

BEM anyone?

TW is really elegant a new paradigm in its purest sense and brilliantly executed. No wholes could be poked in it for years and the extensibility shows, how brilliant it is.

Bootstrap will always be held dearly but it was about browser quirks etc first. Important milestone but stands no chance against TW.

Re: Claude Design

#202

Post by cjf101 »

ossa-ma wrote: post #30

The more I think about it the more this isn't good for design [EDIT], for a few reasons: - The best design is original, groundbreaking and often counterintuitive. An AI model is incapable of that, it's uninspired, it will absolutely converge to the norm and homogeneity (you see it everywhere now, just scroll on ShowHN and take a look at the UIs) and produce the safest design that appeals to its understanding of the i…

I hate to hand anything to Generative AI tools, but

While Great design breaks the mould, Very Good design is about surfacing the most expected outcomes for any action which reduces friction and lets people get work done. And this generation of Generative tools is very good at identifying the most common/most expected response to a prompt.

Re: Claude Design

#203

Post by godzillabrennus »

ljm wrote: post #18

I reckon something like this has only been possible to develop because of how homogenous the internet has become in terms of design ever since the glass effect and drop-shadows took over in Web 2.0 and Twitter Bootstrap entered the scene. You'll get a competent UI with little effort but nothing truly unique or mind-blowing. Impressive technology, but that old skool artisanal weirdness of yore only becomes more valuab…

Nothing screams old school more than 98.css https://jdan.github.io/98.css/

Re: Claude Design

#204

Post by criddell »

freedomben wrote: post #23
mikeaskew4 wrote: post #11

Thumbs down. Great design is original thought. AI is wholly incapable of that. Go ahead and roast me.

> Great design is original thought I don't agree. For novel use cases, yes there's some truth to that. But consistency is huge in a UX. If basic controls work well for a situation, they should be used. Designers should not be getting "creative" or "original" for those sorts of things.

I don't think you are really disagreeing. I'd guess mikeaskew4 would include the constraints of following platform conventions / HIGs and using native widgets for any GUI. Those constraints do not preclude original thought.

Re: Claude Design

#205

Post by slopinthebag »

mjr00 wrote: post #55
ljm wrote: post #18

I reckon something like this has only been possible to develop because of how homogenous the internet has become in terms of design ever since the glass effect and drop-shadows took over in Web 2.0 and Twitter Bootstrap entered the scene. You'll get a competent UI with little effort but nothing truly unique or mind-blowing. Impressive technology, but that old skool artisanal weirdness of yore only becomes more valuab…

There's no shame in being homogenous and obvious, though. If I'm building out an internal tool for, say, a hospital lawyer to search through malpractice lawsuits, I want my tool to be the most familiar, obvious, least-surprising UI/UX possible. Just stay out of the way and do what it's supposed to do. The trick is, of course, that the human is still responsible for knowing when homogenous is fine, or when there's rea…

The issue is that you actually don't want it to look like the modern ubiquitous UI we see everywhere, because it's some of the most jarring, least-intuitive crap we could possibly design. Even I struggle with it when trying to help my parents out, so of course they have no chance, and if they have no chance neither does the hospital lawyer. Modern UI is garbage, and thus this just outputs garbage. Believe it or not, creating good UI takes real skill and experience. You can't just slop it out and expect your tool to do what it's supposed to do.

Re: Claude Design

#206

Post by arbuge »

They state the link is claude.ai/design, which currently goes to:

Page not found Claude can help with many things, but finding this page isn’t one of them.

when logged in.

Re: Claude Design

#207

Post by weinzierl »

"create polished visual work like designs, prototypes, slides, one-pagers, and more."

I use Opus to generate Typst for that and I'm already pretty happy with that approach. It gives me a degree of control I do not have with other methods, because

1. Typst is really powerful

2. Opus is really good at surgically modifying Typst

I basically never look at the Typst code for this. Telling Opus visually what I want changed is usually good enough.

Re: Claude Design

#208

Post by slopinthebag »

levmiseri wrote: post #153
mjr00 wrote: post #55

Earlier quoted context omitted.

There's no shame in being homogenous and obvious, though. If I'm building out an internal tool for, say, a hospital lawyer to search through malpractice lawsuits, I want my tool to be the most familiar, obvious, least-surprising UI/UX possible. Just stay out of the way and do what it's supposed to do. The trick is, of course, that the human is still responsible for knowing when homogenous is fine, or when there's rea…

This is reducing the role of Design as some lego-blocks assembling process. And higher quality being seen as adding ‘pizzazz’. You are right, though. Many products don’t need more than that. But I fear that this will greatly impact design innovation and progress. We might get stuck in the current UI paradigm for a long time.

It's no different to people trying to reduce the role of Programming to the same lego-block assembling process. And I believe the same conclusion follows.

Re: Claude Design

#209

Post by slopinthebag »

voidfunc wrote: post #190
ljm wrote: post #18

I reckon something like this has only been possible to develop because of how homogenous the internet has become in terms of design ever since the glass effect and drop-shadows took over in Web 2.0 and Twitter Bootstrap entered the scene. You'll get a competent UI with little effort but nothing truly unique or mind-blowing. Impressive technology, but that old skool artisanal weirdness of yore only becomes more valuab…

Homogenous design is a good thing. The internet isn't nearly homogeneous enough actually. The mid-90s desktop apps got it right and we've been regressing ever since then because web designers are like kids with crayons.

The early web was filled with wacky and unique websites and it's a ubiquitously loved period of the internet.

Re: Claude Design

#210

Post by moelf »

weinzierl wrote: post #207

"create polished visual work like designs, prototypes, slides, one-pagers, and more." I use Opus to generate Typst for that and I'm already pretty happy with that approach. It gives me a degree of control I do not have with other methods, because 1. Typst is really powerful 2. Opus is really good at surgically modifying Typst I basically never look at the Typst code for this. Telling Opus visually what I want changed…

how does Opus see the output? via HTML (which Typst can output) or visual tokens?
Post reply on HN