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 valuable and nostalgic.
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 real value in the presentation. If you're making a website for, say, a VST plugin for musicians, your site may need to have a little more "pizzazz" to make your product more attractive to the target audience.
That's why I miss the days of old fashioned GUI toolkits (before the web thought of itself as an application distribution platform): you would just design any app as a bag of typical controls in typical containers, and you and your users would live with the expectation that they would look and feel just like the rest of the operating system, nothing more, nothing less. Frivolity would be generally frowned upon, with the result that applications were overall more homogeneous, effective, discoverable and efficient (also in dev time).
Of course, there is indeed no shame. There is also no pride.
Standardized interfaces are as exciting as kettle thermal switches or physical knobs in cars. Useful, probably optimal and will be around for decades to come. Also nobody talks about it, treats it with interest, or pays above market rate to work on it.
The value becomes the architecture of the value of the tool, not the interface. There is still value being generated, but the need for a highly paid UX designer evaporates, and is ultimately replaced by the above.
> nobody talks about it, treats it with interest, or pays above market rate to work on it.
Definitely needs a citation for this one. For so many products the user isn't paying for standout design. They're paying for insight, leverage, velocity, convenience, whatever. The market definitely supports this by paying above market salaries.
Good design can be a useful differentiator but it isn't the only way for a tool or product to "spark joy" and often _fancy_ design (not good design) is used as a crutch for a subpar product.
I don't take pride in having an original UI for most tasks: I take pride in having one that's easy to use and gets the job done. I am not disrespecting people who are making a creative/artistic UI: That adds fun and life to the world. But it's not required for every project.
There's a real problem with everything looking the same though. For a consumer product, you lose brand recognition. For a B2B product, you can confuse your users because Tool A and Tool B look exactly the same. You have to look hard at the name, kind of like prescription pill bottles.
There is little reason to invent a completely new design system if your goal is to encourage brand recognition and prevent an operator from confusing tools.
Apple/SwiftUI has accentColor for example where you can inject a brand colour. This is subtle but effective for UI differentiation - colour is a design primitive that evokes subconscious pattern recognition and can be more effective than a complicated design framework that forces a larger context switch in the user's mind.
The issue is that you actually don't want it to look like the modern ubiquitous UI we see everywhere, because it's some of the most jarring, least-intuitive crap we could possibly design. Even I struggle with it when trying to help my parents out, so of course they have no chance, and if they have no chance neither does the hospital lawyer. Modern UI is garbage, and thus this just outputs garbage. Believe it or not, creating good UI takes real skill and experience. You can't just slop it out and expect your tool to do what it's supposed to do.
This is reducing the role of Design as some lego-blocks assembling process. And higher quality being seen as adding ‘pizzazz’.
You are right, though. Many products don’t need more than that. But I fear that this will greatly impact design innovation and progress. We might get stuck in the current UI paradigm for a long time.
We can skip Web3... Web 4.0 is twilight gradients, glassmorphism, text size xs in tailwind, and cards and pills for every UI component. Along with self-explanatory help text acting as filler under every header.
It's no different to people trying to reduce the role of Programming to the same lego-block assembling process. And I believe the same conclusion follows.
> You'll get a competent UI with little effort but nothing truly unique or mind-blowing.
90+% of attempts at making a truly unique or mind-blowing UI produce a mind-blowingly bad UI. For 0.5 seconds of wow factor, you've added substantial unnecessary friction. Outside of art projects where that wow factor is the point, it really should not be attempted, most certainly not by someone without the appropriate skillset.
The old skool artisanal weirdness was not a purposeful stylistic choice, it was a bunch of people trying to do the best they could with crappy tools. There may be some je ne sais quoi which is lost with the shift to mass adoption, but the reason for the mass adoption of these particular design trends was that they were objectively superior.
> You'll get a competent UI with little effort but nothing truly unique or mind-blowing.
Which is exactly what I want. Do you have any idea how hard it is to get a competent UI?
Why do people celebrate consistency and uniformity in desktop apps, wanting to crucify developers for not following platform idioms and guidelines... and then suddenly want things that are "truly unique" or "mind-blowing" or "artisanal weirdness" when it comes to a web app?
There are still SO MANY insanely ugly, hard-to-use, absolutely horrible apps out there though. Sure, in consumer-focused apps, there's a lot of competition and pretty much everything popular is well-designed. But in enterprise? My god, it's still a massive shitshow.
The hilarious thing is that I would be willing to bet than in a decade, it's STILL a massive shitshow in enterprise. That's because the problem with enterprise software is not that good design is all that difficult to pull off (it just requires caring!) It's that the people making enterprise software have terrible taste and can't even see (I am convinced) that the thing they built is ugly and hard-to-use.
> It's that the people making enterprise software have terrible taste and can't even see (I am convinced) that the thing they built is ugly and hard-to-use.
Generally the issue with enterprise is that its designed to appeal to the stakeholders who will make the purchasing decision, not the person who is actually going to use it. The people making it may have great taste and know damn well what they could do to make it more usable, but if a clean and easy tool doesn't match someone's preconceived notion of what the purchaser thinks the tool ought to look like then it's not going to fly.
The remaining issue is that even an AI-generated UI needs considerable UX input in order to work well, especially when you have to fit it around domain specific knowledge, use-cases, and prior art. Is it for power users or not? All that.
At risk of shifting the goalposts on what I originally said, unique here isn't meant to mean quirky or weird but, simply, something that hasn't been done before, or hasn't been done as effectively.
This is the challenge for B2B startups that are switching to LLM-based development and are trying to offer more than the reselling of cloud compute at a markup with specialised functionality, because AI turns SaaS into a sexy version of MS Access.
I'd argue it's relatively unimpressive given the ability to create design systems and apply themes to them to create relatively generic content has existed for a long time now.
Sure, some prototypes will be spun up more quickly. But if this was a real problem large companies faced it would have been solved in software already.
I wasn't suggesting that the problem would be solved by large companies internally. If anything this is worse for smaller companies, who have already solved this problem for decades at this point by simply not caring about design too much and using the web UI framework du jour. We've already seen with Tailwind that moving to "just put money in the AI machine" comes at the expense of open source UI framework sustainability, with the upside of being slightly faster at making a first-pass boring design.
Sort of. At the moment there is a fad of websites that mess with your scrolling and have very low content density. They are all trying to imitate Apple's marketing pages. Most startup websites do this. It's not at all good design, it's user-hostile, but it's trendy and popular right now.
Homogenous design is a good thing. The internet isn't nearly homogeneous enough actually. The mid-90s desktop apps got it right and we've been regressing ever since then because web designers are like kids with crayons.
Music isn't really new either it's just recombining riffs already created. But the recombinations create new experiences. Might be the same with design?
It's a legitimate boon for throwing together little internal apps, mind.
I can slap something together with Claude over a few evenings to fill a gap on tooling, or I can wrestle with Jira and CI and all that to tie things together with their own integrations.
No thanks, I'll just take the API keys and build on top, to my exact specifications, and the interface will be passable even if it needs a lot of polish. Tailwind has worked wonders for that.
I hate it so much. Ah, your website/app/program is comprised of rounded-corner cards in four colors (color/pale color/white/grey), with a dark theme. Your clickable text isn't visually distinguishable from your non-clickable text. All of your logos are sans-serif SVGs. Your settings and action menus are split across four different primary hidden locations. Your scroll bars disappear even when there's text hidden offscreen. You try to guess what I want to click on by showing a series of competing horizontally-organized pills over the top of the content instead of just giving me a consistent set of action buttons.
AI companies: "good news, everyone! We've automated all those steps so they're even easier to generate!"
I think the same thing is happening in physical construction. Ah, I see you've designed a new box with four primary color tones and slightly offset vertical lines to break up the windows.
What's great is I can take what you just said now and use it as context when generating my new DESIGN.md system and making sure it doesn't look like any of the other stuff. Thank you! Superpowers will show me all the options in their built-in visual companion when brainstorming. :)
that's how i've felt about all AI design. the harnesses get better and cooler, and the outputs up the baseline of utter crap to "whoa that doesn't look bad at all!" which works for probably 90% of the web, but anything truly unique still requires a lot of human taste. maybe that will change one day, but I hope it doesn't.
I am not so sure. I lean towards client work on desktop/mobile/web and while the initial output is workable as new requirements come in it starts to fall apart largely because the vibe coder doesn’t understand design basics. It is one of those you dont know what you dont know and not that ai cannot write workable css or w/e.
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 with multiple rounds because words don't convey layout well.
Now we throw a quick mockup together in Claude or Lovable and send it. The designer gets the idea in 30 seconds instead of a 45-minute call, then pushes it further with their own taste and the client's branding.
It's not replacing designers. Most clients don't know what they want until they see it. These tools collapse that feedback loop from weeks to minutes, so the designer actually spends their time on the parts that need human taste, not on decoding a vague brief.
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.
The folks at Wall Street do not understand this does not replace Figma.
Figma is targeted towards designers who create thoughtful design systems and cohesive UIs and who don't code, while this is targeted towards vibe coders who can't design. Two different circles that intersect to some level.
But like you said, if anthropic adds the tools in Figma, only then they can can take customers from Figma IMO.
>Figma is targeted towards designers who create thoughtful design systems and cohesive UIs and who don't code, while this is targeted towards vibe coders who can't design. Two different circles that intersect to some level.
The challenge is that this sets an expectation of what "design" is, de-valuing the former and shifting us culturally towards the latter and a space where "design" is seen as a subjective visual exercise with little intrinsic value.
I think there's a parallel here in advertising and what AI has done there. It's clearly used nowadays, a seasoned user can probably spot it straight away even if it gets harder over time. Still, it's deemed "good enough". The savings versus having a team and shooting on location etc. can be enormous. Even before this launch, I see it on the web. It's already happening.
Tools like Figma are for an era (and persona) who still wants to have all the various knobs and dials to dial in exactly what they want. And that is one way of working if, like you said people are trying to be more thoughtful and know exactly what they want.
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.
But then again I was never a "designer" – more a builder.
> Figma is targeted towards designers who create thoughtful design systems and cohesive UIs and who don't code, while this is targeted towards vibe coders who can't design. Two different circles that intersect to some level.
this overlap has been widening incredibly quickly. lots of designers are now writing code with the help of cursor, claude code, etc.
even if you believe "real designers" wont ever use this product, it's not hard to see how a low barrier-of-entry tool could affect Figams bottom line. slowing down Figma's adoption from the new wave of entry-level designers who dont already have muscle memory would not at all surprise me at all.
I think they understand that the people running businesses are going to look at this vs a human who uses Figma and realize how much more cost and time efficient it is to pay for a machine than a human.
Just last week, I asked the designer on my team to try working in Codex instead of Figma. It’s just not a great workflow to pass a figma file to a developer to implement. She hasn’t wanted to go back yet…
I started using Pencil for my UI designs and they just introduced animations and I was like they just kicked Figma and now this. Figma might just become another Blockbuster.
I use it all day every day with Claude Code. I sometimes wonder past code if this has had the biggest impact on my day to day productivity, either having to make do with semi-bad looking reports or have a designer design them (which is slow).
Sort of feel sorry for Figma in a way though, given all the "partnerships" (highlighting their MCPs) and case studies they've done with Anthropic and then they release this. I note there isn't a testimonial from them this time.
I'm surprised how poorly Figma have used "AI" in general - given they were the "gold standard" in taking emerging technologies (WASM etc) and making an incredible product. The Figma Make thing was incredibly underwhelming, I managed to extract the system prompt out and it's basically just Gemini 3 Pro with a design prompt. Perhaps the original team has left?
They are extremely exposed imo. While all the UI/UX designers will continue using it for the forseeable, I strongly suspect a lot of their (A/M)RR was coming from extra seats for PMs, developers, etc to view and export and do commenting on the files - not core designer usage. I think a lot of this just won't happen on Figma as much.
I think you hit the nail on the head - I bet Adobe and Figma get most of their sold seats from people who don’t really need the full tool and are basically just using it as a viewer and to make very small adjustments or notes
The more I think about it the more this isn't good for design [EDIT], for a few reasons:
- The best design is original, groundbreaking and often counterintuitive. An AI model is incapable of that, it's uninspired, it will absolutely converge to the norm and homogeneity (you see it everywhere now, just scroll on ShowHN and take a look at the UIs) and produce the safest design that appeals to its understanding of the ideal user.
- Good designers will reject this, they prefer to be hands-on and draw from multiple sources of inspiration which is what Figma boards and Canva is good for, also mainly for cross-collaboration. If you've seen how quickly a great design engineer can prototype you'll know that "speed" they advertise in this video is not worth the tradeoff.
- Creatives typically have a very very very high aversion to AI.
- Non-designers will not see a purpose for this tool, basic design can already be done through Claude Code and Claude.ai, I fail to see what this could offer unless they leverage a model that is more creative and unique by default (you can not prompt/context/harness engineer creativity believe me I've tried).
- Design is a lot more than just UI. Tools like this ignore so many other important aspects like: motion, typography, images, weight, whitespace, sound, feel.
> The best design is original, groundbreaking and often counterintuitive
Designing a user inteface involves thousands of small decisions. When trading off pros/cons for each of these decisions, in 99% of the cases, the right answer is ‘optimize familiarity.
That’s why Android and iOS look the same, and why the small differences between them are where contention happen.
If you adopt existing patterns, your users would be instantly familiar with your app, and the design will not get in their way.
You're arguing for familiarity in tactful design, while I agree that for most users this is a good thing, repeatability of existing patterns does create that immediate familiarity.
HOWEVER, that familiarity is only a virtue because someone, once, deviated hard enough that their deviation became the new familiar. AI can only optimise toward the current snapshot of "familiar". It cannot produce the next one. If designers outsource all their thinking to a model even in tactful design we would never have groundbreaking design concepts like "pull to refresh" or the command palette.
IMO AI will make plain the divergence between "good design" and what people actually want. You're absolutely right that from an artistic perspective, it will produce the heat death of UI. I just struggle to think if teams building will actually care. Boring but polished is completely fine for SaaS.
I could see there being an 80/20-style argument for this sort of tool being used for more generic usecases, with "good designers" using Figma et al. for programs where the UI itself is a selling point.
I will stand by the first point unless models start being trained with different objectives instead of RLHF's three objectives: Helpfulness, Harmlessness and Instruction-following
I noticed in your list that you didn't mention accessibility. I would personally rather have an accessible design than one which is "original, groundbreaking and often counterintuitive." and here we are.
I should have mentioned accessibility. It supports my argument more than yours. Accessibility like captions, voice, keyboard nav, dark mode are all a deviation from the norm by a minority (something AI is completely incapable of doing) and a fight against familiarity which now serves as a great benefit to the majority.
This ... This is simply not true. I use a screen reader. I am using it right now. I can confirm that AI-generated code, by default, is far, far more accessible, cares far more about keyboard nav, about DOM order, about using the right semantic HTML, about the things that I care about than your average human-designed slop.
And no, it doesn't just add ARIA to everything as is so typical by poor practitioners.
I think we're arguing two different points. You're arguing about implementation, AI is great at this given the existing defaults and the right prompting. AI was trained on 30+ years of accessibility standards that a minority of great humans fought to establish as a familiar practice.
I'm arguing about invention. It is extremely unlikely that AI will be the one to invent the next accessibility paradigm, because that requires deviating from the training distribution, which it CAN'T DO.
I'm also arguing that this homogeneity in design will lead to an atrophy in inventive, unique and original thinking.
> The best design is original, groundbreaking and often counterintuitive
The best interface design cares about the best user experience, nothing more. It doesn't have to be original, groundbreaking and certainly not counter intuitive.
Plus: So much of excellent user interface design is done through iterating on feedback from live humans testing it with their human sensory system.
Until we have embodied AI's with eyes and hands that provide good enough approximations, the aspect of design bottlenecked on human experience will stay bottlenecked.
I hate to hand anything to Generative AI tools, but
While Great design breaks the mould, Very Good design is about surfacing the most expected outcomes for any action which reduces friction and lets people get work done. And this generation of Generative tools is very good at identifying the most common/most expected response to a prompt.
Web design / digital design is a dying field as businesses will start paying one person who does 3 to 4 roles (PM, UX Research, Design and UI Development - tho why use a design tool for web stuff when AI tools generate designs in code), as well now tons of ppl can do this work using AI tools. Further, is the future of digital experiences user interfaces aka the web or will there be an AI Phone where everything is done / seen on the lock screen (AI generates the visuals as you text or talk to it) and or its more of a text and voice digital experience less UI.
Overall after being laid off in January and a 17 year UX Research/Design/Dev career Im starting school in my early 50s to change careers.
You could have said the same thing about powerpoint vs high quality marketing departments. The "pros don't want this" argument doesn't really hold weight.
This is for non-designers to crank out slop with less effort. They can still be swayed by all the shiny knobs to feel in control.
"create polished visual work like designs, prototypes, slides, one-pagers, and more."
I use Opus to generate Typst for that and I'm already pretty happy with that approach. It gives me a degree of control I do not have with other methods, because
1. Typst is really powerful
2. Opus is really good at surgically modifying Typst
I basically never look at the Typst code for this. Telling Opus visually what I want changed is usually good enough.
Seems like Claude is actually building almost like a layered Figma wireframe that you can do fine grained adjustments afterwards (e.g. adjust font size).
Interesting that Canva provided a quote of support. I'm not familiar with the differentiation, but it seems like this will directly siphon customers from Canva, right?
There's an "export to Canva" button in Claude Design, so perhaps they're hoping this will be another entry point for new users, or that they'll be able to "lock in" as the default design software for Claude users.
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 brilliantly executed. No wholes could be poked in it for years and the extensibility shows, how brilliant it is.
Bootstrap will always be held dearly but it was about browser quirks etc first. Important milestone but stands no chance against TW.
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.
So how much of this is fully generated vs AI running through all the knobs on template widgets?
Is that globe made from whole cloth or is there a bespoke "telecom globe" widget that it dropped in? Could I ask for mock up of molecules with the same fidelity of knobs, down to nucleus size and such?
It's generated, when you try it you can see this is mostly a harness around claude opus 4.7 that helps it create a good design plan, it also supports asking you questions as it goes along, letting you review and feedback on mockups, etc, but ultimately if you look at what it's generating as it does it – it's just code
"Its just code" is meaningless to me. Is the code its generating using mostly well known widgets with predefined knobs, or is every element completely custom and the knobs are created on the spot with slightly different naming and function every time?
I actually think I would prefer the more boring "it composes well known widgets" because then there's a chance I could just use this to generate a presentation layer and integrate it instead of new blobs of code I need to essentially reverse engineer or remake.
It really feels like Anthropic's product area is extremely overextended at this point. If they want to extend themselves horizontally in an unlimited fashion, they will need unlimited focus, and agents can't supply that. Things will fall through the cracks. Why should I believe that Anthropic will care about this product in 2, 3 years? Whereas I firmly believe that Figma will care greatly about its product in that time
I think that's the wrong question. What kind of shadow spy network must exist around all these companies such that they all happen to be working on the same features at the same time.
> What kind of shadow spy network must exist around all these companies such that they all happen to be working on the same features at the same time.
Stuff like that happened even before the invention of the telephone, humans within the same geographic location is even more predicable, so surely this shouldn't come as a surprise.
Frequently, two movies with very similar concepts drop the same year. Is that because they're spying, or because the companies make decisions in similar ways based on similar input information?
It's possible and even likely there's industrial espionage going on. But imo, you don't need that. I've worked in cutting edge industries, and even when you don't know what your competition is doing, there are usually only so many logical next steps.
This. / Who remembers the "birth" of crowdfunding? Why did so much seem to happen at all once? The most likely explanation imo is that it was "in the air" -- we share culture and ideas. These ideas don't have to be stolen to co-occur... quite the opposite.
The human brain strikes again. It is built into our cognitive machinery to look for patterns and naively ascribe causation. We're not rational beings that sometimes mess up. We're a clusterf--k of cognitive biases all the way down.*
Cool pattern! Sure, maybe there is something there.** And/or maybe our brain is doing "conspiracy theorizing lite". Its all on the same spectrum -- the same flawed cognitive machinery trying to operate in a weird modern world quite different from where we came from.
A better way: write out your favorite hypothesis. But don't stop there... keep going... write out many hypotheses. Then find ways to test them. To tap into our best selves, I recommend The Scout Mindset (book). Here is an infographic summary of part of it: https://imgur.com/qN31PX8
Probably not a better way: float one's first gut feels to the Internet phrased as i.e. the better question and feed empty calories to our pattern-craving brains. There is reason some of our brain functions are considered higher order.
* Maybe I'm overstating this. Let me know? I want to read Rationality and the Reflective Mind by Keith Stanovich (https://academic.oup.com/book/5930) as a counterpoint to the usual suspects (such as Tversky & Kahneman)
It's rolling out progressively, it works for me – it actually seems very polished, the examples are really good; and it lets you create your design system from your codebase
The Anthropic team looks to be eating all the usecases and application layer. I personally know of many figma + AI startups that are going to feel shaken up with this launch.
Anthropic has distribution on their side, their engineers are excellent (I have ran with them across the ggb in the past and they work 12 hours plus a day regularly.)
I think what actually might be slowing them down is the public releases and pr lol, not ideas or execution
"Hot" companies with stupid managers often have such workdays.
In the case of engineers and programmers, the amount of useful completed "work" has only a very weak correlation with the length of the workdays.
Good engineers or programmers will think anyway most of the time about the problems that they must currently solve, regardless whether they are in the office or at home or in any other place, and regardless whether to an external observer they appear to be "working" or they appear to do nothing.
Programmers who spend all day typing lines of code into a computer, are more likely to not be competent programmers, because otherwise they would have found ways to automate such activities that require continuous physical involvement, making impossible the allocation of enough time for thinking about the right solution.
If whatever they do does not require true thinking, then that is the kind of job that can be done by AI agents.
> their engineers are excellent... they work 12 hours plus a day regularly
What? In my experience people who are good at their job can get it done in a reasonable amount of time. Working 12 hours a day is obsession, no competence. There can be overlap, but there is no causation.
Maybe I am using it wrong but it feels much closer to Lovable than Figma. I was expecting this to feel like the two products combined. Certainly better than Lovable though, but a little disappointing.
Really interesting response to Google's Stitch - and seemingly a better alternative given some of the features shown in the video. If everything actually works at least close to how it's advertised, this'll be useful. I'm sure it's no Dieter Rams, but it wouldn't be a surprise if it's already better than many devs at design work.
I've been spending the last two days building a large number of mockups for a new product. Literally the last two days.
I'm wondering how i can CONTINUE that in this design thing, can i import something? Because they show it the other way... you can start and edit, and then export to claude code.
> Import from anywhere. Start from a text prompt, upload images and documents (DOCX, PPTX, XLSX), or point Claude at your codebase. You can also use the web capture tool to grab elements directly from your website so prototypes look like the real product.
I've been using stich from Gemini, and just plain zAi for helping redesign my website. You can use the generated code to copy and paste the design to fit your own templates, but that's a pain. Unless you are ok with using tailwind and the dozen or so classes on every element and don't want to edit anything.
What I found valuable is the design.md that was produced. It's a guide for building each component. So using these tools becomes akin to PSD to html we used do. At least that's when I find them most effective.
I think we will have maybe 5 to 10 years of all this crap, devaluing human made art and human made products, vibe coding everything. But eventually it will all fall apart. Long term only a minority will be happy seeing AI generated crap everywhere and most people will pay for quality human made goods.
Unfortunately it's going to be a tough few years until that happens, where it really does feel like the idiots are winning.
The faster we commodify design the faster we can get back to some sane consistent normal interfaces. Only the very biggest platforms (e.g. Google, Microsoft, Apple) should be spending any time on "design systems".
Imagine if a designer were hired to custom design the lightswitches in every building. We need to get back to off-the-shelf interfaces and stop wasting smart people's time reinventing UI widgets.
Reminder that Claude's own AI design skill (which is probably incorporated directly into this product) says things like
>NEVER use generic AI-generated aesthetics like overused font families (Inter, Roboto, Arial, system fonts), cliched color schemes (particularly purple gradients on white backgrounds), predictable layouts and component patterns, and cookie-cutter design that lacks context-specific character.
> Interpret creatively and make unexpected choices that feel genuinely designed for the context. No design should be the same. Vary between light and dark themes, different fonts, different aesthetics. NEVER converge on common choices (Space Grotesk, for example) across generations.
We used to have RAD based IDE's and now I guess with AI we're going full circle, I'm curious how their mobile thing works, if its just React Native based or what.
What’s interesting here is that with AI, all our interfaces should evolve away from previous generation rigid forms / buttons / tables etc. towards something more fluid / dynamic / “natural”. Yet all the AI coding is geared towards producing more of the former.
Will give it a try but my experience with Claude and browser use so far is that it’s extremely lazy: it rarely notices or cares when something doesn’t look right, it needs lots of pointing out “hey you ignored that broken render” etc
Will be taking this for a spin imminently. What seems to be very unique here vs other canvas tools are the generative UI controls.
If you’re confused about why everyone is shipping their own canvas tool - this is what I wrote when I reviewed Stitch from Google in my newsletter:
“every SOTA (State-of-the-Art) model can already do this. Give it a prompt, it'll spit out an HTML design. Ask for 10 responsive variations, you'll get them. Stitch is a Ul and context harness on top of Gemini, in the same way Claude Code is a harness on top of Claude's models. This means every Al lab will likely ship their own version, and they'll all interoperate because at the end of the day it's all HTML and markdown.”
More generally, this is a competition of where the product development work starts and lives. The business value will accrue to those who become a destination, not a plugin.
AI can now power a new sort of tool that supports the entire process (not just coding or just design). So there’s no reason for Anthropic or any other lab to give that up to another tool.
Seems to me like Anthropic is desperately trying to find as many product-market fits as possible before they IPO. They're reaching a chaotic weekly release cadence--each new product chockful of unclear, overlapping capability with their previous.
Combine that with the obvious hackernews manipulation that somehow gets each and every haphazard release instantly to the top, and you can see they're starting to feel some real heat.
It’s interesting to claim that because everything they do goes to the top on hacker news that they must be in trouble. I haven’t heard that particular chain of effect before.
Feeling some heat != in trouble. Just that the pressure cooker is turning to a higher temp.
But, I'll gladly admit that I am bias: I'm tired of seeing blatant astroturfing by a company whose main marketing tactic is to play on societal fear, while simultaneously employing safety theatre to look like the "good guys".
It could also be that this is an exciting new, fast changing technology that happens to directly overlap and significantly impact the core audience of the site. I don’t think any form of maliciousness or secret astroturfing is required at all.
This stuff has changed a ton of what it means to exist in this whole “tech space”. The entire software development lifecycle got put into a stick blender and is in the process of getting mixed up in new and unusual ways.
It’s super cool. I haven’t been this excited about our industry since way back when the universe was just starting to get onto dialup and I grabbed my very first mp3 or wrote my first shitty program in VB or when AJAX was just entering the universe.
I think a lot of people forgot how fast shit changes in this industry and how learning new things is one of the most important skills to being successful. Everything changes all the time.
This is a tech site called hacker news. Where else would something like this be constantly discussed?
lmao at the idea of figma integrations, categorically. I don't ever want to look at figma again in my life. figma is what people used to ideate quickly because they couldn't build directly in the browser. we can now ideate quickly while working directly in the browser. figma's entire raison d'etre is dinosaur tier over.
With that said, this seems like it's just claude code + simplified devtools in a container? Will need to spend more time with it to see how EG commenting influences things, but 5 minutes in, this seems like it's needless formalization on top of how I already used claude for deisgn
This seems a bit fiddly... I gave it the ChatGPT iframe html for my (not yet released) Liveclip MCP server that's like tables [https://x.com/firasd/status/2039926453408776649]. And I had this chat in the sidebar and it popped up some questions in a form
> do you see our current html
Hi-fi design
Interactive prototype
html
> do you see our current html
Hi-fi design
Interactive prototype
html
● Claude
Yes — I can see your html/ folder. It has 7 files:
files-list.html
math-result.html
rows-view.html
table-view.html
text-editor-doc-view.html
trending-topics.html
unique-result.html
Want me to open them up and take a look at what's in there? And what would you like to do — polish them, turn them into an interactive prototype, build something new on top, or something else?
> yeah in table view i'm thinking about how to deal with cells that may be big. i guess we want to do something different than excel or sheets in that auto expand rows with cells that contain big values. we can show like the first -- what does twitter show, 280? so we can show 280 chars and then [...]
● Let me take a look at the current table view to understand what we're working with.
Got it — I see the current table view. Right now every cell is clamped to max-width:220px with white-space:nowrap and text-overflow:ellipsis, so long values just get cut off at whatever ~30 chars fits the column. You're thinking about the opposite end: what if a cell genuinely holds 2,000 chars of text? Neither pure clip nor Excel-style row expansion is quite right.
Before I start sketching, a few quick questions so I don't guess wrong:
> Questions answered:
- truncation_threshold: ~280 chars (new tweet)
- expansion_ux: nothing right now -- it's not interactive
- row_height_policy: Grow freely like Notion/Airtable
- content_types: Not sure yet
- indicator_style: [...] at the end of the text
- newlines: Render them (row grows)
- copy_affordance: no interaction right now
- column_width: Fixed width, all columns equal
- variation_count: 2 variations
- aesthetic_direction: Same bones, but let you push it a bit
● Got it — so: non-interactive, rows can grow freely, 280-char cap with [...], newlines render, same bones but push it a bit, 2 variations. Let me sketch this out.
Set up variations file with two table treatments
V1: Notion/Airtable-style free-grow with [...] cap
V2: pushed aesthetic variant
Wire both to the same sample data w/ long cells
Let me peek at a couple of the sibling files so the variations stay in-family with the rest of the widget set.
Good — now I have the visual family. The shared vocabulary across widgets:
#f5f5f3 page, #fff card, #d0d0cc borders, #f0f0ec headers
System font, 12–14px
Subtle alternating row tints, no drop shadows, flat corners
Color used sparingly; #666 for secondary text
My plan for the two variations (side-by-side in a canvas so you can compare on the same rows):
V1 — "Notion-ish, stay in family"
Keep current palette, borders, zebra striping
Rows grow vertically as needed; white-space: pre-wrap so newlines render
Cap each cell at 280 chars; if longer, slice to 280 + […] inline
Same fixed column widths, everything else identical
V2 — "Same bones, pushed"
Tightens the grid (hairline borders instead of panels, more whitespace, denser typography)
Column rail with sticky row numbers
Soft fade on the bottom of ultra-tall cells instead of mid-text […] when content is really long (hybrid: char cap + visual)
Monospaced tabular digits for row numbers; type column ⌾ / ▤ markers subtly hinting content type; column width slightly wider for breathing room
Let me build it.
Now let me build the two variations. I'll set up realistic sample data with a mix of short values, tweet-length values, long-long values, and ones with newlines, so the behaviors are visible.
Now the two table components.
Clean. Two variations on the canvas, both rendering the same 7 rows so you can compare directly:
V1 — in-family. Your current widget, with white-space: pre-wrap so rows grow, newlines render, and a soft grey […] appended when a cell goes past 280 chars. Row 3's summary (double-long prose) and row 4's URL show the cap.
V2 — same bones, pushed. Hairline borders instead of filled header panels, monospaced tabular row gutter, column letters as uppercased small-caps above the header names row, tighter typographic rhythm, cells > 280 → […] legend in the footer. Row 7 shows how newlines render naturally.
Both slice at the nearest word boundary when one is within ~40 chars of the 280 cap, otherwise hard-cut — so […] never lands mid-word.
A couple of things worth calling out, not changed:
280 is pretty generous when a row has multiple long cells side-by-side — row 3 is ~2 cells × 280 = a very tall row. If that ends up being painful in real usage, dropping to ~180 or adding a per-row max-height with fade might be worth a follow-up.
Neither variation is interactive per your answer; there's no click-to-expand, hover, or copy. Easy to bolt on later.
Fork verifier agent
Both variations are live on the canvas. Let me know which direction feels right and I'll fold it back into html/table-view.html."
-----
It's basically similar to their Artifacts system in a harness I guess
This largely appears to be a HTML generator at its core, not necessarily what Figma does with layers/canvases etc. There's no collaborative nature to it either.
It feels like a lightly designed product that moves claude CLI to their backend, generates the HTMLs and renders them in browser on claude.ai website for you. Sure, it accepts your design system as an input from you or imports from your repo, but you could feed the same into claude CLI as well?
I'm curious what exactly it gives besides having claude CLI + prompting it well with your design system + skills.
The IBM/Microsoft analogy is a classic. It’s always fascinating to watch these 'frenemy' dynamics play out. In these cases, the one who owns the direct interface with the end-user usually wins the long game, while the 'infrastructure' partner risks becoming just another utility. Will be interesting to see if Canva can maintain its identity or just become a shell for Claude's output.
Yep agree it looks like it’s taking the existing generated artefact, parameterising it within an inch of its life, exposing a pseudo WYSIWYG for the parameters and calling it a day with a few export options. Not a huge leap from what they’ve got already but it’s a clever adjacent step for sure. Same product new chrome.
Postmodernists are annoying because they are right about design. "Taste", aesthetics, design, vibes they're all as socially-constructed and post-truth as that annoying sophomore says everything is. The world is design is an isekai manga in which Derrida's delusions are the rules of physics. It's weird.
Part of this weirdness is the continual relativism of design. A taste-meme is good or cringe only relative to the prevailing social environment, never itself. An AI can never do "design", properly understood, because design is the work done by a reluctance motor, spinning endlessly in a Sysphean quest to align itself with a moving magnetic field and producing torque by side effect.
All efforts like this can do is capture the field alignment at an instant in time. It cannot do work. It cannot produce motion, not as long as its weights are as fixed as the field lines of a neodymium magnet. The instant AI design is good, it becomes bad through the act of becoming good.
Producing work through motion of taste may be one of the last human endeavors to be absorbed.
And another step toward a world, where product managers/owners/whatever and other boring people can generate what they once needed creative, passionate and skilled people for. Go ahead, its just the natural evolution of extreme capitalism.
I don't agree. For novel use cases, yes there's some truth to that. But consistency is huge in a UX. If basic controls work well for a situation, they should be used. Designers should not be getting "creative" or "original" for those sorts of things.
I don't think you are really disagreeing. I'd guess mikeaskew4 would include the constraints of following platform conventions / HIGs and using native widgets for any GUI. Those constraints do not preclude original thought.
Having furniture made by a master designer and artisan woodworker is great. But sometimes, you don't have the budget for that and Ikea furnitures does the job just fine. Most of the time, actually.
Transparently, I'm not a designer, I'm a biologist. That said, the things I want designed by Claude don't need great design. I need a slide format that is consistent from one study to the next so the reader can follow. I need a tool that tracks the number of mice in each lab and flags if someone is using more resources than we expect. I need a personal site that is easy to work with that tracks my pet geckos' feed and environment.
If I have a product out of my lab that makes it to human trials, there will be a full team of marketers and designers tasked to the brand image.
I doubt you’d be singing the same tune if Anthropic released Claude Researcher and a bunch of people were saying “I’m a designer, not a biologist. I don’t need great research. I just need X”
Ironically I think AI will replace researchers before it replaces artists.
But the mass market (who this is ultimately for) doesn't care about great design. They care about "seeing something on the screen." If they can get something that looks 80-90% aligned with what they observe to be modern design, they won't think twice (even if the end result is clunky or not on par with what a professional designer would produce). It's the Ikea Effect on steroids.
Tell this to the 99% of designers who are designing the 5th page in some RBAC modal or some obscure settings page. Design is like code - there are a few people doing really groundbreaking stuff, but vastly more doing the utilitarian plumbing everyone depends on.
It’s honestly been my experience. I think I’ve vibe coded one thing that I’ve found to be genuinely useful to me, everything else has ended up as useless slop given time.
I think we probably need less software, but higher quality, not more. Unfortunately AI only goes in one direction…
> Great design is original thought. AI is wholly incapable of that
This is entirely accurate, however I fear there's a lack of perspective:
If you're in the middle of the desert and need to sit down, that random rock looks and feels great because there's nothing even close, around!
One issue that a lot of experts fail to recognize is that "great" is relative: It's not apparent to the experts because they are only pulled in when their expertise is needed. Most of the time when experts are pulled in, requirements are clear, you have traction, scale and now you need to optimize.
Once you're spoiled for choices, you have lots of options and then that random rock doesn't look appealing at all: now you're considering other factors like budget - IKEA vs Adirondack.
What AI is making a huge difference are places where "great" isnt that valuable:
- people in the desert: Someone wants to track what words their toddler is saying or their groceries or how much kitty litter they should buy soon and Claude will spit something out reasonable even if it makes the skin of experts crawl.
- commodity and bean counters: in cut throat industries like power or insurance, it's all commodity services competing on price. Most people arent going to pay a premium for a better looking, more intuitive insurance app. It just needs to not suck and fall over. Or you're making a knockoff of an existing, well understood product
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 valuable and nostalgic.
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 real value in the presentation. If you're making a website for, say, a VST plugin for musicians, your site may need to have a little more "pizzazz" to make your product more attractive to the target audience.
Standardized interfaces are as exciting as kettle thermal switches or physical knobs in cars. Useful, probably optimal and will be around for decades to come. Also nobody talks about it, treats it with interest, or pays above market rate to work on it.
The value becomes the architecture of the value of the tool, not the interface. There is still value being generated, but the need for a highly paid UX designer evaporates, and is ultimately replaced by the above.
But there's is "pride" in making tools people actually use without issue
Is the pride not in solving the users' problems?
> nobody talks about it, treats it with interest, or pays above market rate to work on it.
Definitely needs a citation for this one. For so many products the user isn't paying for standout design. They're paying for insight, leverage, velocity, convenience, whatever. The market definitely supports this by paying above market salaries.
Good design can be a useful differentiator but it isn't the only way for a tool or product to "spark joy" and often _fancy_ design (not good design) is used as a crutch for a subpar product.
I disagree completely. The pride should come from the value that is delivered. Specifically, this:
>> Useful, probably optimal and will be around for decades to come.
Is something to be proud of, full stop.
Apple/SwiftUI has accentColor for example where you can inject a brand colour. This is subtle but effective for UI differentiation - colour is a design primitive that evokes subconscious pattern recognition and can be more effective than a complicated design framework that forces a larger context switch in the user's mind.
You are right, though. Many products don’t need more than that. But I fear that this will greatly impact design innovation and progress. We might get stuck in the current UI paradigm for a long time.
90+% of attempts at making a truly unique or mind-blowing UI produce a mind-blowingly bad UI. For 0.5 seconds of wow factor, you've added substantial unnecessary friction. Outside of art projects where that wow factor is the point, it really should not be attempted, most certainly not by someone without the appropriate skillset.
The old skool artisanal weirdness was not a purposeful stylistic choice, it was a bunch of people trying to do the best they could with crappy tools. There may be some je ne sais quoi which is lost with the shift to mass adoption, but the reason for the mass adoption of these particular design trends was that they were objectively superior.
Which is exactly what I want. Do you have any idea how hard it is to get a competent UI?
Why do people celebrate consistency and uniformity in desktop apps, wanting to crucify developers for not following platform idioms and guidelines... and then suddenly want things that are "truly unique" or "mind-blowing" or "artisanal weirdness" when it comes to a web app?
A competent UI with little effort is a godsend.
The hilarious thing is that I would be willing to bet than in a decade, it's STILL a massive shitshow in enterprise. That's because the problem with enterprise software is not that good design is all that difficult to pull off (it just requires caring!) It's that the people making enterprise software have terrible taste and can't even see (I am convinced) that the thing they built is ugly and hard-to-use.
Generally the issue with enterprise is that its designed to appeal to the stakeholders who will make the purchasing decision, not the person who is actually going to use it. The people making it may have great taste and know damn well what they could do to make it more usable, but if a clean and easy tool doesn't match someone's preconceived notion of what the purchaser thinks the tool ought to look like then it's not going to fly.
This is exactly what I want in a UI.
At risk of shifting the goalposts on what I originally said, unique here isn't meant to mean quirky or weird but, simply, something that hasn't been done before, or hasn't been done as effectively.
This is the challenge for B2B startups that are switching to LLM-based development and are trying to offer more than the reselling of cloud compute at a markup with specialised functionality, because AI turns SaaS into a sexy version of MS Access.
Or “2000s aesthetic” for something before Web 2.0 (although you’ll get a generic 2000s aesthetic unless you provide more detail).
Sure, some prototypes will be spun up more quickly. But if this was a real problem large companies faced it would have been solved in software already.
Good for everybody who isn't a large company then?
You might just as well bemoan the homogeneity of Windows 95 apps. All those gray buttons in the bottom right of windows.
I guess post IPO, after the insiders cash in out of lock period its irrelevant.
I can slap something together with Claude over a few evenings to fill a gap on tooling, or I can wrestle with Jira and CI and all that to tie things together with their own integrations.
No thanks, I'll just take the API keys and build on top, to my exact specifications, and the interface will be passable even if it needs a lot of polish. Tailwind has worked wonders for that.
I think it's because Steve Jobs killed Flash.
AI companies: "good news, everyone! We've automated all those steps so they're even easier to generate!"
I think the same thing is happening in physical construction. Ah, I see you've designed a new box with four primary color tones and slightly offset vertical lines to break up the windows.
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 with multiple rounds because words don't convey layout well.
Now we throw a quick mockup together in Claude or Lovable and send it. The designer gets the idea in 30 seconds instead of a 45-minute call, then pushes it further with their own taste and the client's branding.
It's not replacing designers. Most clients don't know what they want until they see it. These tools collapse that feedback loop from weeks to minutes, so the designer actually spends their time on the parts that need human taste, not on decoding a vague brief.
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.
Figma is targeted towards designers who create thoughtful design systems and cohesive UIs and who don't code, while this is targeted towards vibe coders who can't design. Two different circles that intersect to some level.
But like you said, if anthropic adds the tools in Figma, only then they can can take customers from Figma IMO.
The challenge is that this sets an expectation of what "design" is, de-valuing the former and shifting us culturally towards the latter and a space where "design" is seen as a subjective visual exercise with little intrinsic value.
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.
But then again I was never a "designer" – more a builder.
this overlap has been widening incredibly quickly. lots of designers are now writing code with the help of cursor, claude code, etc.
even if you believe "real designers" wont ever use this product, it's not hard to see how a low barrier-of-entry tool could affect Figams bottom line. slowing down Figma's adoption from the new wave of entry-level designers who dont already have muscle memory would not at all surprise me at all.
But for me, I will never use it again.
How many such people does the world need? Probably less than 1,000. Not a very big market for Figma.
I use it all day every day with Claude Code. I sometimes wonder past code if this has had the biggest impact on my day to day productivity, either having to make do with semi-bad looking reports or have a designer design them (which is slow).
Sort of feel sorry for Figma in a way though, given all the "partnerships" (highlighting their MCPs) and case studies they've done with Anthropic and then they release this. I note there isn't a testimonial from them this time.
I'm surprised how poorly Figma have used "AI" in general - given they were the "gold standard" in taking emerging technologies (WASM etc) and making an incredible product. The Figma Make thing was incredibly underwhelming, I managed to extract the system prompt out and it's basically just Gemini 3 Pro with a design prompt. Perhaps the original team has left?
They are extremely exposed imo. While all the UI/UX designers will continue using it for the forseeable, I strongly suspect a lot of their (A/M)RR was coming from extra seats for PMs, developers, etc to view and export and do commenting on the files - not core designer usage. I think a lot of this just won't happen on Figma as much.
- The best design is original, groundbreaking and often counterintuitive. An AI model is incapable of that, it's uninspired, it will absolutely converge to the norm and homogeneity (you see it everywhere now, just scroll on ShowHN and take a look at the UIs) and produce the safest design that appeals to its understanding of the ideal user.
- Good designers will reject this, they prefer to be hands-on and draw from multiple sources of inspiration which is what Figma boards and Canva is good for, also mainly for cross-collaboration. If you've seen how quickly a great design engineer can prototype you'll know that "speed" they advertise in this video is not worth the tradeoff.
- Creatives typically have a very very very high aversion to AI.
- Non-designers will not see a purpose for this tool, basic design can already be done through Claude Code and Claude.ai, I fail to see what this could offer unless they leverage a model that is more creative and unique by default (you can not prompt/context/harness engineer creativity believe me I've tried).
- Design is a lot more than just UI. Tools like this ignore so many other important aspects like: motion, typography, images, weight, whitespace, sound, feel.
Designing a user inteface involves thousands of small decisions. When trading off pros/cons for each of these decisions, in 99% of the cases, the right answer is ‘optimize familiarity.
That’s why Android and iOS look the same, and why the small differences between them are where contention happen.
If you adopt existing patterns, your users would be instantly familiar with your app, and the design will not get in their way.
HOWEVER, that familiarity is only a virtue because someone, once, deviated hard enough that their deviation became the new familiar. AI can only optimise toward the current snapshot of "familiar". It cannot produce the next one. If designers outsource all their thinking to a model even in tactful design we would never have groundbreaking design concepts like "pull to refresh" or the command palette.
"Good designers will reject this."
^ Famous last words.
I will very likely be wrong on the second point.
And no, it doesn't just add ARIA to everything as is so typical by poor practitioners.
I'm arguing about invention. It is extremely unlikely that AI will be the one to invent the next accessibility paradigm, because that requires deviating from the training distribution, which it CAN'T DO.
I'm also arguing that this homogeneity in design will lead to an atrophy in inventive, unique and original thinking.
Not everyone is looking for unique design, 70% of the web is still using Wordpress. I would say majority prefer familiarity and appreciate uniqueness.
The best interface design cares about the best user experience, nothing more. It doesn't have to be original, groundbreaking and certainly not counter intuitive.
Until we have embodied AI's with eyes and hands that provide good enough approximations, the aspect of design bottlenecked on human experience will stay bottlenecked.
While Great design breaks the mould, Very Good design is about surfacing the most expected outcomes for any action which reduces friction and lets people get work done. And this generation of Generative tools is very good at identifying the most common/most expected response to a prompt.
Overall after being laid off in January and a 17 year UX Research/Design/Dev career Im starting school in my early 50s to change careers.
This is for non-designers to crank out slop with less effort. They can still be swayed by all the shiny knobs to feel in control.
I use Opus to generate Typst for that and I'm already pretty happy with that approach. It gives me a degree of control I do not have with other methods, because
1. Typst is really powerful
2. Opus is really good at surgically modifying Typst
I basically never look at the Typst code for this. Telling Opus visually what I want changed is usually good enough.
Seems like Claude is actually building almost like a layered Figma wireframe that you can do fine grained adjustments afterwards (e.g. adjust font size).
Interesting that Canva provided a quote of support. I'm not familiar with the differentiation, but it seems like this will directly siphon customers from Canva, right?
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 brilliantly executed. No wholes could be poked in it for years and the extensibility shows, how brilliant it is.
Bootstrap will always be held dearly but it was about browser quirks etc first. Important milestone but stands no chance against TW.
Page not found Claude can help with many things, but finding this page isn’t one of them.
when logged in.
Is that globe made from whole cloth or is there a bespoke "telecom globe" widget that it dropped in? Could I ask for mock up of molecules with the same fidelity of knobs, down to nucleus size and such?
I actually think I would prefer the more boring "it composes well known widgets" because then there's a chance I could just use this to generate a presentation layer and integrate it instead of new blobs of code I need to essentially reverse engineer or remake.
I wonder what other features they're cooking right now.
Stuff like that happened even before the invention of the telephone, humans within the same geographic location is even more predicable, so surely this shouldn't come as a surprise.
Cool pattern! Sure, maybe there is something there.** And/or maybe our brain is doing "conspiracy theorizing lite". Its all on the same spectrum -- the same flawed cognitive machinery trying to operate in a weird modern world quite different from where we came from.
A better way: write out your favorite hypothesis. But don't stop there... keep going... write out many hypotheses. Then find ways to test them. To tap into our best selves, I recommend The Scout Mindset (book). Here is an infographic summary of part of it: https://imgur.com/qN31PX8
Probably not a better way: float one's first gut feels to the Internet phrased as i.e. the better question and feed empty calories to our pattern-craving brains. There is reason some of our brain functions are considered higher order.
* Maybe I'm overstating this. Let me know? I want to read Rationality and the Reflective Mind by Keith Stanovich (https://academic.oup.com/book/5930) as a counterpoint to the usual suspects (such as Tversky & Kahneman)
** But what is there. What kind of pattern? What kind(s) of causation could be at work? See Judea Pearl's "ladder of causation". Nice write-up here: https://samuel-book.github.io/causal_inference_notebook/pear...
Previous comment with the prior 3: https://news.ycombinator.com/item?id=47794419
Anthropic has distribution on their side, their engineers are excellent (I have ran with them across the ggb in the past and they work 12 hours plus a day regularly.)
I think what actually might be slowing them down is the public releases and pr lol, not ideas or execution
What a toxic workplace :/
In the case of engineers and programmers, the amount of useful completed "work" has only a very weak correlation with the length of the workdays.
Good engineers or programmers will think anyway most of the time about the problems that they must currently solve, regardless whether they are in the office or at home or in any other place, and regardless whether to an external observer they appear to be "working" or they appear to do nothing.
Programmers who spend all day typing lines of code into a computer, are more likely to not be competent programmers, because otherwise they would have found ways to automate such activities that require continuous physical involvement, making impossible the allocation of enough time for thinking about the right solution.
If whatever they do does not require true thinking, then that is the kind of job that can be done by AI agents.
And money aside, it is certainly one of the most exciting companies in the world to work for.
What? In my experience people who are good at their job can get it done in a reasonable amount of time. Working 12 hours a day is obsession, no competence. There can be overlap, but there is no causation.
As someone who's thinking about side project-ing a game, this caught my eye.
I am curious to explore what Claude can yolo in terms of a retro style indie game... One who's audience might only be me.
Very interesting though
I'm wondering how i can CONTINUE that in this design thing, can i import something? Because they show it the other way... you can start and edit, and then export to claude code.
Until then, I guess it's back to just using CC
> Import from anywhere. Start from a text prompt, upload images and documents (DOCX, PPTX, XLSX), or point Claude at your codebase. You can also use the web capture tool to grab elements directly from your website so prototypes look like the real product.
What I found valuable is the design.md that was produced. It's a guide for building each component. So using these tools becomes akin to PSD to html we used do. At least that's when I find them most effective.
Unfortunately it's going to be a tough few years until that happens, where it really does feel like the idiots are winning.
THE IDIOTS ARE WINNING
Imagine if a designer were hired to custom design the lightswitches in every building. We need to get back to off-the-shelf interfaces and stop wasting smart people's time reinventing UI widgets.
>NEVER use generic AI-generated aesthetics like overused font families (Inter, Roboto, Arial, system fonts), cliched color schemes (particularly purple gradients on white backgrounds), predictable layouts and component patterns, and cookie-cutter design that lacks context-specific character.
> Interpret creatively and make unexpected choices that feel genuinely designed for the context. No design should be the same. Vary between light and dark themes, different fonts, different aesthetics. NEVER converge on common choices (Space Grotesk, for example) across generations.
[1] https://github.com/anthropics/claude-code/blob/main/plugins/...
Why would we want to move away from hard fought UX design lessons? Dynamic and fluid UX is infuriating.
If you’re confused about why everyone is shipping their own canvas tool - this is what I wrote when I reviewed Stitch from Google in my newsletter:
“every SOTA (State-of-the-Art) model can already do this. Give it a prompt, it'll spit out an HTML design. Ask for 10 responsive variations, you'll get them. Stitch is a Ul and context harness on top of Gemini, in the same way Claude Code is a harness on top of Claude's models. This means every Al lab will likely ship their own version, and they'll all interoperate because at the end of the day it's all HTML and markdown.”
More generally, this is a competition of where the product development work starts and lives. The business value will accrue to those who become a destination, not a plugin.
AI can now power a new sort of tool that supports the entire process (not just coding or just design). So there’s no reason for Anthropic or any other lab to give that up to another tool.
This app is pretty slick, this will funnel a huge number of customers away from Figma + Canva imo.
I have been doing fine just instructing Claude code to use Tailwind and reference design documents
Combine that with the obvious hackernews manipulation that somehow gets each and every haphazard release instantly to the top, and you can see they're starting to feel some real heat.
But, I'll gladly admit that I am bias: I'm tired of seeing blatant astroturfing by a company whose main marketing tactic is to play on societal fear, while simultaneously employing safety theatre to look like the "good guys".
So take my opinion with a grain of salt :)
This stuff has changed a ton of what it means to exist in this whole “tech space”. The entire software development lifecycle got put into a stick blender and is in the process of getting mixed up in new and unusual ways.
It’s super cool. I haven’t been this excited about our industry since way back when the universe was just starting to get onto dialup and I grabbed my very first mp3 or wrote my first shitty program in VB or when AJAX was just entering the universe.
I think a lot of people forgot how fast shit changes in this industry and how learning new things is one of the most important skills to being successful. Everything changes all the time.
This is a tech site called hacker news. Where else would something like this be constantly discussed?
That link is redirecting me to https://claude.ai/404, anyone else?
With that said, this seems like it's just claude code + simplified devtools in a container? Will need to spend more time with it to see how EG commenting influences things, but 5 minutes in, this seems like it's needless formalization on top of how I already used claude for deisgn
Deriving a bland average of creativity is the saddest thing you could do. I don’t even enjoy design and I find this offensive.
> do you see our current html
Hi-fi design Interactive prototype html
> do you see our current html
Hi-fi design Interactive prototype html
● Claude Yes — I can see your html/ folder. It has 7 files:
files-list.html math-result.html rows-view.html table-view.html text-editor-doc-view.html trending-topics.html unique-result.html Want me to open them up and take a look at what's in there? And what would you like to do — polish them, turn them into an interactive prototype, build something new on top, or something else?
> yeah in table view i'm thinking about how to deal with cells that may be big. i guess we want to do something different than excel or sheets in that auto expand rows with cells that contain big values. we can show like the first -- what does twitter show, 280? so we can show 280 chars and then [...]
● Let me take a look at the current table view to understand what we're working with.
Got it — I see the current table view. Right now every cell is clamped to max-width:220px with white-space:nowrap and text-overflow:ellipsis, so long values just get cut off at whatever ~30 chars fits the column. You're thinking about the opposite end: what if a cell genuinely holds 2,000 chars of text? Neither pure clip nor Excel-style row expansion is quite right.
Before I start sketching, a few quick questions so I don't guess wrong:
> Questions answered: - truncation_threshold: ~280 chars (new tweet) - expansion_ux: nothing right now -- it's not interactive - row_height_policy: Grow freely like Notion/Airtable - content_types: Not sure yet - indicator_style: [...] at the end of the text - newlines: Render them (row grows) - copy_affordance: no interaction right now - column_width: Fixed width, all columns equal - variation_count: 2 variations - aesthetic_direction: Same bones, but let you push it a bit
● Got it — so: non-interactive, rows can grow freely, 280-char cap with [...], newlines render, same bones but push it a bit, 2 variations. Let me sketch this out.
Set up variations file with two table treatments V1: Notion/Airtable-style free-grow with [...] cap V2: pushed aesthetic variant Wire both to the same sample data w/ long cells Let me peek at a couple of the sibling files so the variations stay in-family with the rest of the widget set.
Good — now I have the visual family. The shared vocabulary across widgets:
#f5f5f3 page, #fff card, #d0d0cc borders, #f0f0ec headers System font, 12–14px Subtle alternating row tints, no drop shadows, flat corners Color used sparingly; #666 for secondary text My plan for the two variations (side-by-side in a canvas so you can compare on the same rows):
V1 — "Notion-ish, stay in family"
Keep current palette, borders, zebra striping Rows grow vertically as needed; white-space: pre-wrap so newlines render Cap each cell at 280 chars; if longer, slice to 280 + […] inline Same fixed column widths, everything else identical V2 — "Same bones, pushed"
Tightens the grid (hairline borders instead of panels, more whitespace, denser typography) Column rail with sticky row numbers Soft fade on the bottom of ultra-tall cells instead of mid-text […] when content is really long (hybrid: char cap + visual) Monospaced tabular digits for row numbers; type column ⌾ / ▤ markers subtly hinting content type; column width slightly wider for breathing room Let me build it.
Now let me build the two variations. I'll set up realistic sample data with a mix of short values, tweet-length values, long-long values, and ones with newlines, so the behaviors are visible.
Now the two table components.
Clean. Two variations on the canvas, both rendering the same 7 rows so you can compare directly:
V1 — in-family. Your current widget, with white-space: pre-wrap so rows grow, newlines render, and a soft grey […] appended when a cell goes past 280 chars. Row 3's summary (double-long prose) and row 4's URL show the cap. V2 — same bones, pushed. Hairline borders instead of filled header panels, monospaced tabular row gutter, column letters as uppercased small-caps above the header names row, tighter typographic rhythm, cells > 280 → […] legend in the footer. Row 7 shows how newlines render naturally. Both slice at the nearest word boundary when one is within ~40 chars of the 280 cap, otherwise hard-cut — so […] never lands mid-word.
A couple of things worth calling out, not changed:
280 is pretty generous when a row has multiple long cells side-by-side — row 3 is ~2 cells × 280 = a very tall row. If that ends up being painful in real usage, dropping to ~180 or adding a per-row max-height with fade might be worth a follow-up. Neither variation is interactive per your answer; there's no click-to-expand, hover, or copy. Easy to bolt on later. Fork verifier agent Both variations are live on the canvas. Let me know which direction feels right and I'll fold it back into html/table-view.html." -----
It's basically similar to their Artifacts system in a harness I guess
It feels like a lightly designed product that moves claude CLI to their backend, generates the HTMLs and renders them in browser on claude.ai website for you. Sure, it accepts your design system as an input from you or imports from your repo, but you could feed the same into claude CLI as well?
I'm curious what exactly it gives besides having claude CLI + prompting it well with your design system + skills.
Then Claude came for the designers with Claude Design, and I did not speak out— Because I was not a designer.
...
https://en.wikipedia.org/wiki/First_They_Came
Now its 5 Hour usage, Weekly Usage, Claude Design, Daily Routine Runs, and the Extra Usage portion...
Maybe AI is not good at everything, yet.
Part of this weirdness is the continual relativism of design. A taste-meme is good or cringe only relative to the prevailing social environment, never itself. An AI can never do "design", properly understood, because design is the work done by a reluctance motor, spinning endlessly in a Sysphean quest to align itself with a moving magnetic field and producing torque by side effect.
All efforts like this can do is capture the field alignment at an instant in time. It cannot do work. It cannot produce motion, not as long as its weights are as fixed as the field lines of a neodymium magnet. The instant AI design is good, it becomes bad through the act of becoming good.
Producing work through motion of taste may be one of the last human endeavors to be absorbed.
Go ahead and roast me.
I don't agree. For novel use cases, yes there's some truth to that. But consistency is huge in a UX. If basic controls work well for a situation, they should be used. Designers should not be getting "creative" or "original" for those sorts of things.
If I have a product out of my lab that makes it to human trials, there will be a full team of marketers and designers tasked to the brand image.
Ironically I think AI will replace researchers before it replaces artists.
Also, a lot of very good software developers are bad at design and unwilling or unable to pay for a designer. This will be an improvement for them.
But the mass market (who this is ultimately for) doesn't care about great design. They care about "seeing something on the screen." If they can get something that looks 80-90% aligned with what they observe to be modern design, they won't think twice (even if the end result is clunky or not on par with what a professional designer would produce). It's the Ikea Effect on steroids.
I think we probably need less software, but higher quality, not more. Unfortunately AI only goes in one direction…
Is there also a place in the world for not-great-but-good-enough design?
not really, great design in a web application is no surprises.
Still human?
This is entirely accurate, however I fear there's a lack of perspective:
If you're in the middle of the desert and need to sit down, that random rock looks and feels great because there's nothing even close, around!
One issue that a lot of experts fail to recognize is that "great" is relative: It's not apparent to the experts because they are only pulled in when their expertise is needed. Most of the time when experts are pulled in, requirements are clear, you have traction, scale and now you need to optimize.
Once you're spoiled for choices, you have lots of options and then that random rock doesn't look appealing at all: now you're considering other factors like budget - IKEA vs Adirondack.
What AI is making a huge difference are places where "great" isnt that valuable:
- people in the desert: Someone wants to track what words their toddler is saying or their groceries or how much kitty litter they should buy soon and Claude will spit something out reasonable even if it makes the skin of experts crawl.
- commodity and bean counters: in cut throat industries like power or insurance, it's all commodity services competing on price. Most people arent going to pay a premium for a better looking, more intuitive insurance app. It just needs to not suck and fall over. Or you're making a knockoff of an existing, well understood product
The catch is that the person making the decision might not know or care about the difference.