Live data from Hacker News

Claude Design

anthropic.com

491–500 of 819 posts

Re: Claude Design

#491

Earlier quoted context omitted.

Agreed on your take on the parent, although I have to say I feel that AI has had the opposite effect for me. It has only accelerated learning quite significantly. In fact not only is learning more effective/efficient, I have more time for it because I am not spending nearly as much time tracking down stupid issues.

Sounds like you're talking about research AI and not generative AI. You can't learn artistic/creative techniques when you're not practicing those techniques. You can have a vision, but the AI will execute that vision, and you only get the end result without learning the techniques used to execute it.

Okay, this is a pet peeve of mine, so forgive me if I come off a little curt here, but-- I disagree strongly with how this was phrased.

"Generative AI" isn't just an adjective applied to a noun, it's a specific marketing term that's used as the collective category for language models and image/video model -- things which "generate" content.

What I assume you mean is "I think is misleading, and would prefer to make a distinction".

But how you actually phrased it reads as " doesn't mean , but rather . What you mean is "

I see this all the time in politics, and it muddies the discussion so much because you can't have a coherent conversation. (And AI is very much a political topic these days.) It's the illusion of nuance -- which actually just serves as an excuse to avoid engaging with the nuance that actually exists in the real category. (Research AI is generative AI; they are not cleanly separable categories which you can define without artificial/external distinctions.)

Re: Claude Design

#492

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…

Dawg, I'm just trying to keep my managers happy so I can get a paycheck and have health care and hit the trails on the weekend.

Re: Claude Design

#493
post #472

Earlier quoted context omitted.

> But for the other 95% of people, being able to just say "ok can you make it look more modern" and have 4 variants in 5 mins, (like me) Figma will lose users like me. Perhaps this phrasing is what invited the interpretation you seem to be annoyed with. There is not much to gain by suggesting everyone is simply bad faith.

No the bad faith part comes from assuming that the output is low quality, and that just because I get _feedback_ in five minutes (read again what I said) it somehow implies that I spent 5 minutes on it and then moved on, never to revisit. I think you like the other person is assuming that 5 minutes = low quality. Instead of thinking "5 mins means you can make 8-10 iterations in an hour" or "5 minutes making the front…

There are many ways to interpret this, yes. I only mean to disrupt the framing you keep asserting of good and bad faith, I'm still not sure I understand what you are getting at.

No one is assuming the output is strictly low quality from what I can tell. I am personally evaluating the method you provided, which suggested you are championing a sloppy but highly iterative design flow against a seasoned curated suite for defining design. I dont see any reason to assume the other comment was doing anything otherwise.

You made a broad generalized strong claim and were met with the opposing force, which is actually acting from their own understanding of good faith, believe it or not (see how this analysis is void of meaning?).

Re: Claude Design

#494

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…

> * Terrible at logo work. Comically bad. This is something that is "hard" so it could add great value if it could deliver.

OK but what we really want to know, what's it like when it comes to drawing pelicans riding on bicycles?

Re: Claude Design

#496

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.

Yes but that’s why you ask it to teach you what it just did. And then you fact-check with external resources on the side. That’s how learning works.

Re: Claude Design

#497

Earlier quoted context omitted.

I'll still die on this hill, but I think that the reason there's a computer literacy problem is because we moved away from following OS conventions (when they existed) and into bespoke, branded UIs for everything, and then eventually to web where every site and webapp behaves differently. In the early days, if you learned the OS, those usage patterns and skilled transferred to every app on that OS. They all looked ro…

Not all OS's, unfortunately. I'm on the boat that says conforming to Gnome HIG's is a bad idea. Just today I had the disk usage analyzer (baobab) open and I was navigating inside directories so I want to go up a directory and clicked on the " If this app had a traditional menubar and a toolbar this wouldn't have happened. This is a common type of experience I have every time I use a Gnome app. It almost feels like so…

omg yes, I felt crazy the first time I experienced this "feature"

Re: Claude Design

#498
post #351

To people saying its replacing Lovable. It's still missing the ability to deploy right from the app with a backend ready to go. I'm sure it will get there tho.

Here's a 2-line prompt that gives Claude Design a backend:

```

----

To get your credentials and learn about InstantDB, fetch this URL:

https://instantdb.com/llm-rules/create-app/AGENTS.md

```

Every cURL request to AGENTS.md spins up a new backend and splices in the credentials.

I used it to build this multiplayer pelican game:

https://349b7470-3747-49e7-8ece-960a45b0b2da.claudeuserconte...

Disclaimer: I am the founder of InstantDB

Re: Claude Design

#499

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…

> * Terrible at logo work. Comically bad. This is something that is "hard" so it could add great value if it could deliver. OK but what we really want to know, what's it like when it comes to drawing pelicans riding on bicycles?

To be fair, i did not ask for a logo with a pelican in it.

Re: Claude Design

#500

Earlier quoted context omitted.

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

I find it intellectually exhausting to describe to a machine what I want, when I could build something better in the same amount of time, and it isn't for lack of understanding how the LLM works. It takes a lot of cajoling to get an LLM to produce a result I want to use. It takes no cajoling for me to do it myself. The only time "AI" helps is in domains that I am unfamiliar with, and even then it's more miss than hit…

My experience is mostly the opposite. Provided the right context and prompt, CC will generally produce code, even in domains I know, 10-20x faster.

Quality is a different issue, sure.

Post reply on HN