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?
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 :)
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.
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.
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.
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.
Still human?
The catch is that the person making the decision might not know or care about the difference.
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.
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
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...
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 :/
And money aside, it is certainly one of the most exciting companies in the world to work for.
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.
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.
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.
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.
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?
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.
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
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.
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.
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.
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.
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.
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.
I think it's because Steve Jobs killed Flash.
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.
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.
Very interesting though
- 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.
Not everyone is looking for unique design, 70% of the web is still using Wordpress. I would say majority prefer familiarity and appreciate uniqueness.
"Good designers will reject this."
^ Famous last words.
I will very likely be wrong on the second point.
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.
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.
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.
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.
Previous comment with the prior 3: https://news.ycombinator.com/item?id=47794419
That link is redirecting me to https://claude.ai/404, anyone else?
Maybe AI is not good at everything, yet.
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.
This app is pretty slick, this will funnel a huge number of customers away from Figma + Canva imo.
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.
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.
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.
How many such people does the world need? Probably less than 1,000. Not a very big market for Figma.
Why would we want to move away from hard fought UX design lessons? Dynamic and fluid UX is infuriating.
> 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
Deriving a bland average of creativity is the saddest thing you could do. I don’t even enjoy design and I find this offensive.
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 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.
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.
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.
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
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/...
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.
albert_e•1h ago
Boss0565•1h ago
Sol-•1h ago
svnt•1h ago
frankdenbow•1h ago
netdevphoenix•1h ago
strickjb9•1h ago
Then Claude came for the designers with Claude Design, and I did not speak out— Because I was not a designer.
...
yard2010•1h ago
https://en.wikipedia.org/wiki/First_They_Came
alpb•1h ago
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.
diatone•44m ago
weatherfun•44m ago