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

381–390 of 819 posts

Re: Claude Design

#381

Post by bauerd »

taylorlapeyre wrote: post #349
bauerd wrote: post #336

Earlier quoted context omitted.

They are building infrastructure components that they will soon wire together with an orchestration layer. Managed agents, scheduled tasks, workflow webhook automation.

The infrastructure piece is what they do best. I'd be happy if Anthropic became the AWS of AI. But this product is just a mediocre shot at Figma, when no such shot is strictly necessary for them. These kinds of consumer products are not what they do best.

It would be interesting if they’re dogfooding it by building these research projects on those building blocks

Re: Claude Design

#382

Post by idle_zealot »

eric_cc wrote: post #319
pilgrim0 wrote: post #285

On Notes on the Synthesis of Form, Alexander defines design as the rationalization of the forces that define a problem. You’ll won’t find a better definition. But people tend to think design is the synthesis and its results. This misunderstanding of the role of design and the designer is responsible for all the unfit designs we encounter on a daily basis. Anyone equipped with a synthesis tool and feeling empowered to…

> I feel sorry for anyone that will think using tools equals doing design, because of the truly marvelous human experiences that they’ll miss, and that could never be replaced by the shallow pride of empty achievement. What if you don’t give a shit about design and it’s a means to an end for a project that involves something different that you do care about?

> What if you don’t give a shit about design and it’s a means to an end for a project that involves something different that you do care about?

Thank you for so succinctly demonstrating the problem with using AI for everything. You used to have to either care enough to do the design yourself or find someone who cared and specialized in that to do it for you. Now you quickly and cheaply fill in the parts you don't personally care about with sawdust, and as this becomes normalized you deprive yourself and others from discovering that they care about the design part. You'll ship your thing now, and it'll be fine. The damage is delayed and externalized.

I won't advocate against use of new technology to make yourself more productive, but it's important to at least understand what you're losing.

Re: Claude Design

#383

Post by raviisoccupied »

hkpack wrote: post #343
raviisoccupied wrote: post #335

I am not an engineer, I can't look at code and determine if it is good, performant, or elegant. However, I can look at designs and make a judgement. I'm curious to see how Claude Design changes how I think about AI and its capabilities.

If you are not a software engineer you can judge code the same way as you can judge design while not being a designer. It is that in one case it is obvious for you that you don’t understand what you are looking at, and in another, for some reason, it is not.

>If you are not a software engineer you can judge code the same way as you can judge design while not being a designer.

Very true.

Re: Claude Design

#384

Post by gbalduzzi »

BeetleB wrote: post #283
jerf wrote: post #256

Earlier quoted context omitted.

I remember when people would vigorously complain that Toolkit X was simply unsuitable for any task because it did not conform to the operating system's standard visual appearance. Now I struggle to even define what an "operating system's standard visual appearance" is. Apple's still the best but not what they used to be on that front even so.

I miss the days when there was no "standard visual appearance" for the OS (e.g. DOS). I liked the diversity of interfaces. Years ago, I remarked to a friend that I'd spent half of my (computing) life post-high speed Internet, yet almost all my happy memories are from before that. It was the same for him, and we both explored why that was. The homogeneity of interfaces was actually one of the reasons we came up with o…

Everyone remembers fondly the time they were young, I believe it is more about that then everything else.

I understand your feelings but it is extremely tipical in human history to keep remembering "the good old times"

Re: Claude Design

#385

Post by bobkb »

The design process was completely dictated by Figma. After the demise of Adobe XD, Invison etc they were the only option. Happy to see alternatives entering to save us from the curse of Figma !

Re: Claude Design

#386

Post by kbenson »

eric_cc wrote: post #319
pilgrim0 wrote: post #285

On Notes on the Synthesis of Form, Alexander defines design as the rationalization of the forces that define a problem. You’ll won’t find a better definition. But people tend to think design is the synthesis and its results. This misunderstanding of the role of design and the designer is responsible for all the unfit designs we encounter on a daily basis. Anyone equipped with a synthesis tool and feeling empowered to…

> I feel sorry for anyone that will think using tools equals doing design, because of the truly marvelous human experiences that they’ll miss, and that could never be replaced by the shallow pride of empty achievement. What if you don’t give a shit about design and it’s a means to an end for a project that involves something different that you do care about?

I think maybe how you are conceptualizing design and how the GP meant it are not in agreement, and if you came to agreement on what it meant you wouldn't really disagree about the point either.

For example, I think design, as they mean it, could be described as "how to get that thing we care about". The correct amount of design depends on how exacting the outcome and outputs needs to be across different dimensions (how fast, how accurate, how easy to interpret, how easy to utilize as an input for some other system). For generalized things where there's not exacting standards for that, AI works well. For systems with exacting standards along one or more of those aspects, the process of design allows for the needed control and accuracy as the person or people doing the work are in a constant feedback loop and can dial in to what's needed. If you give up control of the inside of that loop, you lose the fine grained control required for even knowing how far you are away from theoretical maximums for those aspects.

Re: Claude Design

#387

Post by MisterPea »

mickeyp wrote: post #296
Growtika wrote: post #199

For my agency this won't replace Figma or designers. It's just a really useful tool to express yourself and communicate intent. Before these tools, when a client wanted a specific section built, we'd spend hours hunting references across the web. The output always ended up feeling like a mesh of 2-3 sites, never fully unique. Then we'd burn more time explaining the intent to the client's designers and devs, usually w…

Indeed. Kitbashing is a thing, and it was always a thing. Designers I worked with would spend hours doomscrolling pinterest, google images, etc. looking for their, uh... 'spark' when they were given a briefing. This is just a really cool way of building. I'm impressed. I tried Google Stitch but it was slow and useless. Sad, because Gemini has a pretty good creative flair, ironically enough.

Stitch has been very good for me to prototype some designs, and the exporting design feature is great.

But jeez, is it buggy, slow and unintuitive at times.

Complete shift in google's old engineering culture of high quality - they seem to be shipping quickly in favor of stability

Re: Claude Design

#388

Post by rirze »

necatiozmen wrote: post #373

https://getdesign.md/ provides more accurate design system extraction than Claude design. Could be use vice-versa

The sites seem to be all of the same format-- with different color palettes as the main offering point here.

A little misleading, as I thought they would showcase different types of site design entirely.

Re: Claude Design

#389

Post by Draiken »

Nice video but the expectations vs reality is brutal: provide it with an actual PDF with a design system, wait for 30min and the entire thing is stuck.

You talk to it, it consumes "usage" and no design system created.

Had a similar experience with their online code sessions.

All this slop generated code is so freaking bad. We'll get drowned in so much slop code that at some point only these garbage machines will be able to "work" with it.

Re: Claude Design

#390

Post by simonreiff »

oaxacaoaxaca wrote: post #216
_the_inflator wrote: post #201

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 brilliantl…

Am I the only one who doesn't like Tailwind? The way it totally pollutes your html makes it seem like, while the benefits are impressive, they're not worth the collateral damage.

Tailwind is fantastic precisely because the biggest benefit (tree-shaking to minimize the CSS that ships) massively outweighs the fact that Tailwind syntax "looks like" an anti-pattern and makes your code "look" ugly. Also, you get used to bundling your styling and JS code in one place with any component-driven framework like Next.js/React, and Tailwind works seamlessly with all of them. I guess I just prefer the benefits to the alternative, and I feel like the collateral damage of the alternative is definitely not worth trying to make front-end design code look simpler.
Post reply on HN