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

811–819 of 819 posts

Re: Claude Design

#811

Post by nerptastic »

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.

I have a degree in design - it's one of those frustrating fields where laypeople really do believe they are experts. Mostly because... they can "see" it. It's easy to propose a change to a design. "Just move it to the right. Or left. Or make it green".

The end product is SUPPOSED to be simple to digest and understand, but the process behind that artifact is enigmatic. It may have taken months to determine the proper layout structure for a government website, but a certain end user can still say "Well... I would rather have the navbar on the right side."

Some of it is probably vocabulary as well. Software has jargon - design has jargon, but laypeople know how to say "bigger, smaller, right, left, red, blue". Frustrating, and part of why I left the field.

Re: Claude Design

#812

Post by ramon156 »

Gave it info about an existing project to do a redesign

> You've hit your usage limit. Claude uses a different usage limit. Resets Mon 12am

It's Tuesday. What are we doing here, Anthropic?

This was also the last day until my subscription ends. Good riddance.

Re: Claude Design

#813

Post by dbg31415 »

dbg31415 wrote: post #639

Modern Figma design libraries are one of the best things to happen to product teams in the last 20 years. Reusable components. Shared styles. Auto layout. Variants. Design tokens. So many useful plugins! Interactive prototypes. Dev mode handoff. Versioned libraries. A single source of truth keeping designers, engineers, and PMs speaking the same language. It's fucking bliss when you use it right. And best of all, any…

I can't edit that... but yeah, Claude Design is significantly better than Figma Make.

Start with asking it to get up to speed on your design system, or build you a design system from your brand guidelines... and it does a pretty good job.

It also does a surprisingly good job of using some of the more advanced Figma tools that a lot of human designers struggle with...

3 days in, I've been really impressed.

Re: Claude Design

#814

Post by a4isms »

alsetmusic wrote: post #777
a4isms wrote: post #766

Earlier quoted context omitted.

> they benefit from being familiar . “Intuitive Equals Familiar,” a classic from Jef Raskin, the man who started the Macintosh¹ project at Apple: https://www.asktog.com/papers/raskinintuit.html ——— ¹ Only to have Steve take it away. Jef left and created the Canon Cat, an opinionated computer that eschewed the WIMP interface in favour of anchoring n incremental search. Steve would also leave and create NeXT, and Canon…

> Steve would also leave and create NeXT More accurate to say that he was forced out. We (Mac nerds) were shocked when he came back. My father told me that I was super excited talking about his return, though I don't remember that. I do remember having a Mac Addict magazine with SJ portrayed as a priest on his return. Internet Archive ftw.[0] 0. https://ia601204.us.archive.org/BookReader/BookReaderImages....

Good comment!

When there is a boardroom battle over control, I think almost any take is fair. Sculley kicked him off Macintosh. Steve then tried to oust Sculley, who gave him a "window seat."

Sculley had the Board's support, and Steve resigned rather than quietly sit in the corner playing with "New Product Development" toys. The Board refused to accept his resignation and encouraged him to rescind it, but no they didn't give him meaningful authority, so he carried on to Plan B and negotiated the right to make "Education" computers.

Did he jump? Was he pushed? Yes!

And back to the point I was making... His trajectory had something in common with Raskin's trajectory, right down to raising money from Canon.

———

p.s. Fellow OG Mac developer here. I still have the SE/30 I used to write a classified ads app for QuarkXPress and Aldus PageMaker back in the day. I would describe classified ads software in the 90s as, "faster horses about to be eclipsed by automobiles."

Re: Claude Design

#815

Post by switchbak »

dwb wrote: post #785
switchbak wrote: post #431

Earlier quoted context omitted.

Man so much of this thread is full of such high minded philosophizing, it's like we're debating wine instead of talking about interfaces for doing things. Like, maybe I just want to make an interface to configure my homemade espresso dohickey, do I have to wear a turtleneck and read Christopher Alexander now? I just wanted a couple buttons and some sliders. We don't all have to be experts in everything, some people j…

Don’t be so anti-intellectual, there’s enough of that around. A simple problem is going to have a small set of simple design solutions; the philosophising readily admits that. Nothing’s getting in your way.

I’m not being anti-intellectual, I’m being anti-elitist and anti-obfuscation.

It’s not the science and intellect I take issue with, engineering has plenty of that. It’s the art-adjacent navel gazing post modern bullshit I don’t like.

Re: Claude Design

#816

Post by dwb »

switchbak wrote: post #815
dwb wrote: post #785

Earlier quoted context omitted.

Don’t be so anti-intellectual, there’s enough of that around. A simple problem is going to have a small set of simple design solutions; the philosophising readily admits that. Nothing’s getting in your way.

I’m not being anti-intellectual, I’m being anti-elitist and anti-obfuscation. It’s not the science and intellect I take issue with, engineering has plenty of that. It’s the art-adjacent navel gazing post modern bullshit I don’t like.

Well I think that art is good, thinking about design is good, that using a couple of terms that aren’t immediately clear to you isn’t “obfuscation”, and that postmodernism can be a useful analytical lens. Seeing the world only through science and engineering (as useful as they can be when applied well) is cold, dead, and sad.

Re: Claude Design

#817

Post by slederer »

rvz wrote: post #118
GenerWork wrote: post #64

If you look at Figmas stock price, it started falling right at 11 AM as this news was released. Anyways, this is 100% a shot at Figma, but also catching Lovable in the crossfire. If anybody from Anthropic is reading this, if you keep developing this with features in Figma and other design tools, you'll have a major hit on your hands.

This tells me that Lovable is certainly not worth $6.6B.

We independently scanned 500+ Lovable-deployed apps as part of a larger study of 1,764 vibe-coded apps. The RLS problem is systemic — not a one-off. X% of Lovable apps we tested had wide-open Supabase tables where the anon key could read/write everything. The $6.6B question isn't whether the product is useful, it's whether the security liability of millions of deployed apps becomes a material risk. We published the full breakdown: securityscanner.dev/reports/2026-q2

Re: Claude Design

#818

Post by switchbak »

dwb wrote: post #816
switchbak wrote: post #815

Earlier quoted context omitted.

I’m not being anti-intellectual, I’m being anti-elitist and anti-obfuscation. It’s not the science and intellect I take issue with, engineering has plenty of that. It’s the art-adjacent navel gazing post modern bullshit I don’t like.

Well I think that art is good, thinking about design is good, that using a couple of terms that aren’t immediately clear to you isn’t “obfuscation”, and that postmodernism can be a useful analytical lens. Seeing the world only through science and engineering (as useful as they can be when applied well) is cold, dead, and sad.

Well, I think that typically 90% of engineering is bullshit, that 90% of everything is almost always bullshit, and that 90% of the high minded nonsense you're talking about can be tossed with no loss whatsoever.

The other 10% of the design world? Actual useful, and can help create truly better things. And typically offered honestly because there really is something of substance being shared. To be clear: there can be tremendous value in the design world.

And nice false dichotomy there - if someone disagrees with the snooty extravagances of the design world, then they only care about science and engineering. That is not what I said, and your twisting of my statements is either a shallow read or disingenuous.

Re: Claude Design

#819

Post by dwb »

switchbak wrote: post #818
dwb wrote: post #816

Earlier quoted context omitted.

Well I think that art is good, thinking about design is good, that using a couple of terms that aren’t immediately clear to you isn’t “obfuscation”, and that postmodernism can be a useful analytical lens. Seeing the world only through science and engineering (as useful as they can be when applied well) is cold, dead, and sad.

Well, I think that typically 90% of engineering is bullshit, that 90% of everything is almost always bullshit, and that 90% of the high minded nonsense you're talking about can be tossed with no loss whatsoever. The other 10% of the design world? Actual useful, and can help create truly better things. And typically offered honestly because there really is something of substance being shared. To be clear: there can be…

I can only read as deep as what is written. I have a low opinion of anyone who dismisses “snooty extravagances” of any field – it’s incurious and disrespectful. Either admit you don’t know enough to engage, or read up and engage on the substance.
Post reply on HN