Obviously this is a personal preference, but the multiple layers of beveled grey on the Qt UI is not something I like, as it forces a lot of grouping on the eye where it doesn't serve any purpose.
I would go with the original, Apple or the Win11 one. Material would be good, what's with the lavender shades?
I always try to reduce the palette: say two background shades max, no drop shadows, only as many foreground colors as needed and if it seems to bland, add more bells and whistles.
Only a small anecdote, but I'm 2 projects into telling Claude to "make it look like Google podcasts" and getting satisfactory results. Still smells like llm in parts, but overall it is not screaming low effort.
Qt is heavily represented in training data. Qt has existed for decades and the model has likely seen Qt tutorials, screenshots, source code, discussions, etc. As a result, "Qt application" is a highly coherent concept in the latent space. "Qt app" is almost like a named distribution.
I thought that AI would at least be good at 2 things: writing (text) and doing UI. It's not good at either. Text it generated reads like slop and UI it creates looks like slop. The way I approach it now is this: for text, I have to write it myself and only use AI to check grammar and catch weirdly phrased passages. For UI, it's like with the rest of the code. You have to stay on the top of it and keep demanding changes to match your vision/architecture/taste until it gets it close to what you want. In both cases, not knowing what "good" looks like is a real problem, because AI definitely has no idea.
If you're just having fun with it, there are a whole bunch of other things that produce interesting options, like asking it to theme according to a movie (think Clockwork Orange, Backrooms, anything with a strong aesthetic), or throw screenshots and photos at it and use it as a "design system" (magazine/print layouts can work well with this on stronger models).
When making small tools for myself, I just tell it to use Svelte and then wrap it up using Tauri - no graphical cues whatsoever. And they usually comes out pretty good by my taste.
That's just the "original" they mentioned here without a prompt (https://envs.net/~volpe/projects/ai-design.html) but these ofen are easily identified as AI generated. I don't think it's too bad but it's definitely a tell.
Can you quantify what it is you don’t like? Like, to my eyes ‘original’ is fine - and it’s very similar to ‘QT’ expect with rounded corners and brighter colours.
I find it such a hard thing to quantify, I know it's not helpful but you can just feel the slop seep through.
I'm not sure if it's because I've iterated through so many sites that LLMs have produced that "slop" is instantly recognisable and it just feels soulless.
Not like web pages ever had a soul, but it's not there on the generic LLM generated sites.
I think this says more about "modern" UI than it does about AI slop. The awfulness of all this comes mostly from the fact that widgets no longer have consistent shape, theme or interaction behaviour ever since desktop paridigms and original Xerox/Parc research were abandoned in favour of web slop. So yeah, this is much more Web Slop than AI Slop. AI is just amplifying it.
This one works well. I think it's because there's no shine to it, it's just the data, what you need, right there without trying to fluff it all out with rounded edges and superfluous stuff.
All of these look quite terrible to my eyes. None of them really resemble the classic AI slop landing page, either (of which this [1] is a decent illustration). I'm no huge fan of that style, but it's at least readable and functional, and thus better than the results you got by a mile.
It seems like you were starting with an existing HTML file you asked it to redesign. Generating from scratch with strict guidelines could be more representative.
I've been doing this recently - working with Qt on a local app.
I've had good luck providing a png "design board" with all of the template colors and having the first task be to build out a design gallery with all of the ui widget. Then have the design docs specify which component to use. Ensure that the documents specify to only use pre-existing components and have a list of each component and their intended use cases.
Of course, this learning came after seeing how awful V1 of the app was. Initially, it looked really impressive, but once you started clicking around it became obvious how incoherent the design was.
Claude's new frontend-design plugin is solid for web apps in my testing. My wife and I have been using it to build her an app and her discerning design eye is largely impressed with what it's done.
My experience with this is 180 degrees opposite. It's been really easy to create really nice UIs for all kinds of one-off apps I've made for myself with AI. In fact, it has been one of the most fun parts of this whole AI thing. ¯\_(ツ)_/¯
This has also been my experience. I do find it takes a review pass with a direction including things like "make sure text isn't overlapping." "Make sure text isn't overflowing out of buttons" - I find that's a really common one.
Even the example apps in the post seemed like AI slop to me. Common markers are too noisy/busy (mainly repeated or rephrased information). Text being a bit too big (Codex-only?).
Yes in my experience, AI designs might look okay on first glance but when you really start to look you start to see strange and inconsistent things. Similar to looking at generated code.
This article is purely subjective. I'm sure there are some academics that could explain ways to objectively score usability but this article is purely subjective.
The whole "AI slop" noise is, at its core, human slop. It is people applying a hopefully pejorative label, trying to appeal to other slop aficionados that like whatever the current trendy slur is, in an objectively undefinable way.
In this case this guy likes the way Qt apps, they think it looks better, but it isn't a big trick they are revealing: They made it conform to the style they like, but this doesn't translate to anyone else in any measurable way. I think web apps looking like Qt apps feel like the late 90s and it's just weird, but my taste also is entirely subjective and mine alone.
>> Slop is not a distinct style, it can be overlaid on top of many others. Even when I got it to make a page to look like X, it looked like X with slop.
Today, I can visit a website and instantly tell it was generated using LLMs and agents from A to Z:
1. Everything is in blue or mauve gradient, with a white background, and a single JavaScript-heavy page that lags as soon as you scroll a little.
2. There are always a ton of 404 pages.
3. Third, the HTML comments often expose credentials and to-do lists—sometimes even right above the login page (true story...).
This kind of website is a hard pass for me, and I add the company (and its founders) to my personal blacklist of people and companies I’ll never use anything from.
I don't think that is true, in the way that it always wasn't: How would you be able to tell when it's done properly?
Think WordPress installations: Depending on how it's done you can either tell at a glance (probably ~90% of WP installations at some points in time) or you have no clue until you look at the html source.
Of course the option to not do it properly is always alluring and then you can tell.
I had to read the post about five times and still didn't see the link to the actual examples - I actually had to view source to see the URL.
I like the idea - all of the designs are pretty meh though. If I had to pick one, I'd pick the HIG one (apart from that cursed glass effect on scroll) and then probably the Win11 one.
auth0 does get close to slop. If I were them I'd definitely change things up. Devcycle and Datadog are nothing like generated slop. I haven't seen Fable websites yet - supposedly a lot better - but Opus and GPT can't design anything even close to those two. They can implement it if you give them a screenshot, but that's not designing something. Micro.com shows me a domain sale page.
Tailwind is the answer. Always pure Tailwind, not custom classes + utilities. It makes a massive difference vs. stylesheets. The LLM is able to actually reason about your UI in discrete chunks with a semantic layer over the styling, vs. bouncing back and forth between CSS/HTML and trying to reason about custom classes generated on the fly.
Does anyone have good examples of well designed web applications - not landing pages or peoples tech blogs, which are often listed here on HN. But like actual applications that do a complex task with the user using it as a tool.
I would go with the original, Apple or the Win11 one. Material would be good, what's with the lavender shades?
I always try to reduce the palette: say two background shades max, no drop shadows, only as many foreground colors as needed and if it seems to bland, add more bells and whistles.
guess it's a matter of taste
When making small tools for myself, I just tell it to use Svelte and then wrap it up using Tauri - no graphical cues whatsoever. And they usually comes out pretty good by my taste.
I'm not sure if it's because I've iterated through so many sites that LLMs have produced that "slop" is instantly recognisable and it just feels soulless.
Not like web pages ever had a soul, but it's not there on the generic LLM generated sites.
Edit: https://retr0.id/stuff/deslop/
It seems like you were starting with an existing HTML file you asked it to redesign. Generating from scratch with strict guidelines could be more representative.
[1]: https://vorpus.github.io/performativeUI/
I've had good luck providing a png "design board" with all of the template colors and having the first task be to build out a design gallery with all of the ui widget. Then have the design docs specify which component to use. Ensure that the documents specify to only use pre-existing components and have a list of each component and their intended use cases.
Of course, this learning came after seeing how awful V1 of the app was. Initially, it looked really impressive, but once you started clicking around it became obvious how incoherent the design was.
Claude's new frontend-design plugin is solid for web apps in my testing. My wife and I have been using it to build her an app and her discerning design eye is largely impressed with what it's done.
Even the example apps in the post seemed like AI slop to me. Common markers are too noisy/busy (mainly repeated or rephrased information). Text being a bit too big (Codex-only?).
is there a way to quantifiably measure how much better one design would be from another?
The whole "AI slop" noise is, at its core, human slop. It is people applying a hopefully pejorative label, trying to appeal to other slop aficionados that like whatever the current trendy slur is, in an objectively undefinable way.
In this case this guy likes the way Qt apps, they think it looks better, but it isn't a big trick they are revealing: They made it conform to the style they like, but this doesn't translate to anyone else in any measurable way. I think web apps looking like Qt apps feel like the late 90s and it's just weird, but my taste also is entirely subjective and mine alone.
Today, I can visit a website and instantly tell it was generated using LLMs and agents from A to Z:
1. Everything is in blue or mauve gradient, with a white background, and a single JavaScript-heavy page that lags as soon as you scroll a little.
2. There are always a ton of 404 pages.
3. Third, the HTML comments often expose credentials and to-do lists—sometimes even right above the login page (true story...).
This kind of website is a hard pass for me, and I add the company (and its founders) to my personal blacklist of people and companies I’ll never use anything from.
Think WordPress installations: Depending on how it's done you can either tell at a glance (probably ~90% of WP installations at some points in time) or you have no clue until you look at the html source.
Of course the option to not do it properly is always alluring and then you can tell.
I like the idea - all of the designs are pretty meh though. If I had to pick one, I'd pick the HIG one (apart from that cursed glass effect on scroll) and then probably the Win11 one.
Do the landing pages of auth0.com, devcycle.com, micro.com, or datadog.com not look like slop to other people?