Live data from Hacker News

Claude Design

anthropic.com

581–590 of 819 posts

Re: Claude Design

#581
post #450

Earlier quoted context omitted.

> There's no shame in being homogenous and obvious, though. The real world analog is this... The reason people (especially Americans) stay in Marriott property hotels is because they are homogenous. If all I want to do is travel to Phoenix, AZ for work I want to know that the hotel room has the same mattress, desk, TV, customer service, etc. There is real legitimate value to that. So I'll book the Courtyard in Phoeni…

It is actually a rational choice. It is a defense against extremely bad experiences. A personal example from a few weeks back. My SO booked a hotel for a weekend as a birthday present. We went there, it had a fantastic spa, dinner was delicious, the room great, clean, and so on. Individually designed, well thought out, friendly staff. Breakfast came around and the coffee was abysmal. Really truly abysmal. What did we…

> Marriott is basically the same for hotels.

Marriotts are sadly not the same between countries, and that's probably a good thing.

The standard for large chain hotels in the US are much, much lower than everywhere else in the world. Full-service Hiltons in the US don't even have executive lounges anymore.

Re: Claude Design

#582

Earlier quoted context omitted.

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

That culture died forever ago, google has been launching half-baked shit that they kill in 18 months after no updates for a decade now.

Re: Claude Design

#583
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 don't remember people complaining about Winamp being a non-standard UI, but if it were slow then there'd be tons of complaints - and many of the "fancy" UIs were terribly slow (or the programs were, hard for a user to tell the difference).

> I don't remember people complaining about Winamp being a non-standard UI, but if it were slow then there'd be tons of complaints - and many of the "fancy" UIs were terribly slow (or the programs were, hard for a user to tell the difference).

Wasn't Winamp 2 the gold standard? I remember plenty of music lovers switching to foobar2000 when Winamp 3 came out, because it was, as you said, slow(er).

Re: Claude Design

#584
post #450
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…

> There's no shame in being homogenous and obvious, though. The real world analog is this... The reason people (especially Americans) stay in Marriott property hotels is because they are homogenous. If all I want to do is travel to Phoenix, AZ for work I want to know that the hotel room has the same mattress, desk, TV, customer service, etc. There is real legitimate value to that. So I'll book the Courtyard in Phoeni…

Good homogenous experience is the hallmark of good design. There are no surprises with good design. It just works the way you expect it to work. Good design should not generally challenge your expectations.

Re: Claude Design

#585

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…

> It's not replacing designers. Except it is. Plenty of places will say this is all good enough and not hire, or even lay off, the UI/UX person. I've seen this firsthand.

Especially if you’re working on an established product with an existing design system. New features / layouts are really easy now.

These tools don’t solve big design problems, but they do resolve all the little design decisions often left up to devs at implementation time.

Re: Claude Design

#586

Earlier quoted context omitted.

I assure you, working with LLMs is intellectually challenging, and becomes more so as the technology matures.

It really really really depends on how you are using it and what you are using it for. I can get LLMs to write most CSS I need by treating it like a slot machine and pulling the handle till it spits out what I need, this doesnt cause me to learn CSS at all.

But were you trying to learn CSS in the first place?

Re: Claude Design

#587
post #418

Earlier quoted context omitted.

If we expect Anthropic not only trying to replace just all software developers with Claude, but also all software product companies with Claude, then i really wanna know why the fuck are we cheering here for Anthropic on Hacker News? What kind of dumb sheep would do this?

Automation allows us to do more.

Up until you feel automated.

Re: Claude Design

#588
post #557

My feedback for whatever it's worth as a 25yr design veteran. * Massive token usage, some small tasks burned through $50 of credits and did not offer $50 of value. * Terrible at logo work. Comically bad. This is something that is "hard" so it could add great value if it could deliver. * Repeatedly forgot prior feedback - when iterating it would re-implement prior iterations after being told why we didn't want that re…

I'm curious, is there anything out there that will get you the 80% of logo work? Claude opus always came closest to me as a non-designer, but it was always still something far from usable.

Haven’t found it yet. The component parts seems to be close. Opus is much better at drawing SVG than it used to be.

Re: Claude Design

#589
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…

IMO it doesn't flatten design into one thing. it splits it. cheap obvious work at scale, and a way smaller premium tier for real authorship. the middle is what actually gets crushed.

this is true of AI in general

Re: Claude Design

#590
post #418

Earlier quoted context omitted.

If we expect Anthropic not only trying to replace just all software developers with Claude, but also all software product companies with Claude, then i really wanna know why the fuck are we cheering here for Anthropic on Hacker News? What kind of dumb sheep would do this?

Automation allows us to do more.

Yes; more depression and anxiety about an uncertain future.

The SWE people I know at SW companies now heavily using these agents complain to me how their workday is nothing but code-reviews of the agents output and tedious prompting to prod it back into line; they say they don’t get to actually write code until they get home to work on their personal projects.

3 years ago I never would have believed this capability was possible; I’ve since adjusted my expectations to now assume that in another 3 years the models/agents will have improved enough to reduce the amount of code-review required, leaving us with precious little else to do for our shareholders, or the opposite: they don’t improve and we’re stuck doing thankless PR reviews until the end.

Please tell me where and how in this future I’m supposed to find satisfaction and pride in my work when what-gets-produced isn’t my own work anymore?

Post reply on HN