Claude Design(anthropic.com) |
Claude Design(anthropic.com) |
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.
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
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.
If you treat it like a black box used to outsource your own thinking, you are holding it wrong.
I think we probably need less software, but higher quality, not more. Unfortunately AI only goes in one direction…
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.
Still human?
The design problem to solve post-ai isn’t this it’s how the space for thinking fits into all this, getting to the end result slower so human ideation can play out. This is just optimized for the first generic output + tweaks.
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
But try and design say an “An A4 poster with a hero image, main text saying this, details next to the image and fine print at bottom” and you end up with pretty poor results.
Reusable components. Shared styles. Auto layout. Variants. Design tokens. So many useful plugins! Interactive prototypes. Dev mode handoff. Versioned libraries. A single source of truth keeping designers, engineers, and PMs speaking the same language.
It's fucking bliss when you use it right. And best of all, anyone on the team can build with the legos the designers gave us!
Teams finally started treating the design system like infrastructure instead of decoration.
Then Figma Make showed up.
It generates pages that ignore your components, skip your tokens, and treat every screen like a fresh snowflake. Looks fine in the mockup. Lands like a brick on the dev team. Now every page is bespoke and every handoff is a rebuild. Fucking sucks.
We had it all figured out, then we fucked it up.
AI was supposed to accelerate momentum. But it just so completely lacks maturity. AI Tools are dragging teams back to 2010, when every page was a Photoshop file (with way too many layers and shitty names for them) and none of the designers can agree on what radius to assign to their buttons.
Good design systems are a discipline. If your AI tool doesn't respect the library, it's not a designer. It's an intern with a Molotov cocktail waiting to destroy your productivity.
I haven't used Claude Design yet, I'll try it, but I LOVE Figma, and I hate Figma Make. I don't have high hopes for Claude here.
Start with asking it to get up to speed on your design system, or build you a design system from your brand guidelines... and it does a pretty good job.
It also does a surprisingly good job of using some of the more advanced Figma tools that a lot of human designers struggle with...
3 days in, I've been really impressed.
> 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
Really hope Anthropic didn't notice my ingenious work and quickly copy it.
So far it's burned through 45% my design quota. On a positive note, I finally have my fonts rendering. I'm still waiting for it to figure out how it mangled the SVG versions of my logo. I've watched it trying a lot of stuff for 20 minutes and now I've got something that's not my logo.
Now its 5 Hour usage, Weekly Usage, Claude Design, Daily Routine Runs, and the Extra Usage portion...
You talk to it, it consumes "usage" and no design system created.
Had a similar experience with their online code sessions.
All this slop generated code is so freaking bad. We'll get drowned in so much slop code that at some point only these garbage machines will be able to "work" with it.
I explore designs in Claude Desktop, and once I’m satisfied, I’ll let Claude desktop handover prompts for Claude Code. Claude Code makes a review harness inside the actual application for each atom, molecule and organism, and I accept each of them one by one.
I wonder if this is something similar, but makes the whole process smoother. As someone who’s not particularly good at frontend, I’m quite happy with what all this accomplishes.
What I really don't like is that this tool maintains its own "state": I want everything as markdown files in my git repo, not as some arbitrary black box blob inside Anthropic's cloud.
The amount of hype is too much for me - its smoke and mirrors. A firm that knew it was on track to change the world (as much as they have been boosting) would not do this. Much like how Apple kept complete silence about the iPhone and then shocked the world.
Page not found Claude can help with many things, but finding this page isn’t one of them.
when logged in.
half the design problems I've seen weren't bad taste. they were bad communication between the person who knew what they wanted and the person who could build it.
> You've hit your usage limit. Claude uses a different usage limit. Resets Mon 12am
It's Tuesday. What are we doing here, Anthropic?
This was also the last day until my subscription ends. Good riddance.
Edit: I see they have a new token tier 'Claude Design' so that's good.
It is that in one case it is obvious for you that you don’t understand what you are looking at, and in another, for some reason, it is not.
The end product is SUPPOSED to be simple to digest and understand, but the process behind that artifact is enigmatic. It may have taken months to determine the proper layout structure for a government website, but a certain end user can still say "Well... I would rather have the navbar on the right side."
Some of it is probably vocabulary as well. Software has jargon - design has jargon, but laypeople know how to say "bigger, smaller, right, left, red, blue". Frustrating, and part of why I left the field.
Very true.
Anything but that
Ultimately, this really just shifts the focus towards product design and ideation rather than UI design.
Fed it my figma file to it and creating a design system. And yeah, it looks like it, but it's still wayyy off at the same time
Maybe AI is not good at everything, yet.
```
<YOUR APP IDEA HERE>
----
To get your credentials and learn about InstantDB, fetch this URL:
https://instantdb.com/llm-rules/create-app/AGENTS.md
```
Every cURL request to AGENTS.md spins up a new backend and splices in the credentials.
I used it to build this multiplayer pelican game:
https://349b7470-3747-49e7-8ece-960a45b0b2da.claudeuserconte...
Disclaimer: I am the founder of InstantDB
That link is redirecting me to https://claude.ai/404, anyone else?
Design usage shouldn't impact code usage.
Can't even test two designs. No idea if PDFs used up so much budget.
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.
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.
...
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.
However, there is of course a raw mechanical side to design that comes more into play on practical applications like a software UI vs. pure play memes/vibes like branding or a landing page.
Think hierarchy, leading, kerning, scale, contrast, balance, etc. These things remain constant throughout trend cycles and can absolutely get you half way there. Then aesthetic memes can be sprinkled on top by a human to make people believe "this feels cool."
>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/...
It's not X, it's Y! all over again?
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
Semi-relevant XKCD: https://xkcd.com/1425/
This will fail because it's already a forgotten side project within anthropic, and anthropic also has pretty bad product DNA as a company. Their headcount is already too large and the culture is already set. They grew revenue so fast they speedran the stage at which you could build software product chops into the company culture (think Google circa 2008 vs. Google circa 2018).
They should focus on what they're good at: the actual AI models and B2B sales. Let OpenAI play early Google and churn through 100 different consumer product experiences to see what sticks, they're better positioned for it anyways.
Maybe they realised its actually a dead-end? Why else would you not double-down and concentrate resources? This would be an amateur error if it turned out to be true.
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.
Like what they have some superior knowledge or ability to design ?
Let me remind you they weren't always tech giants, what if we said lets stop innovating before apple or any of these became a thing.
No, but they have the scale where that level of specialty makes sense. McDonald's has food chemists on staff, but the local burger joint does not.
> what if we said lets stop innovating before apple or any of these became a thing
It's important for any organization to know what its competitive advantage is and where to spend its innovation tokens. D.R. Horton is the number one homebuilder in the United States, but they don't make their own light switches.
Now they do, they didnt always, you have to start from somewhere, you always start small you dont just become a huge company instantly. Also wtf kind of an analogy is that ? Oh yeah chemists never innovate on your own or at a small scale we have big corpos doing it so you guys can stop now thanks
I think you have heard the rather famous quote "Its better to be a pirate than join the navy", small scale stuff can move a lot lot faster than some huge conglomerate.
I agree that not everyone needs to roll their own design but i think your conclusion is rather idiotic.
It's also just a beautiful product. The interaction model, styling and integrations via exporting is all super thoughtful
Deriving a bland average of creativity is the saddest thing you could do. I don’t even enjoy design and I find this offensive.
Exact Transcript as follows:
-- Claude: Let me fix these precisely: <empty>
-- Me: ok
-- Claude: <empty>
-- Me: hello?
-- Claude: <empty>
-- Me: there's still some issues with 01 live and 02 - your business.
-- Claude: <empty>
-- Me: hello?
-- Claude: Sorry about that. Let me look at those two and figure out what's still wrong. <empty>
--- Me: hello?
-- Claude: Screenshot _illo_check.html Viewing image illustration-pillar-1.svg Viewing image illustration-pillar-2.svg <empty>
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.
nature beckons its creatures to become whatever they must become to be useful in the greater living ecosystem (the loop)
when you can't be useful in the loop you get flushed out of existence
humans who can't be useful will also thus be buffered out of existence
This app is pretty slick, this will funnel a huge number of customers away from Figma + Canva imo.
In my example, I expected it to create UI elements for a business application / expert system. And it did fine. In fact, I believe its perfect for creating average and functional designs. Its a better way to test variations of UIs for expert systems. But I want to know what the actual costs are.
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.
BUt what it really shows is there's no vision. If you had a vision and coherent strategy you'd concentrate resources - not dilute them across a myriad of projects.
The US had the atom bomb for a few years before anyone else had it. Anthropic has mythos now before anyone else - they are probably using it to churn out as many software clones as possible before someone else catches up.
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.
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.
Im looking at this product and thinking - so...? Where's the vision?
Oh there is none. Its about spraying and praying that the hype continues and feeding off analysts who don't really understand most of the firms that they spend all day studying the valuation of.
A little misleading, as I thought they would showcase different types of site design entirely.
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.
As a dev manually typing I loved tailwind for sure, with LLMs not so much, and bootstrap in particular nails it the best IME. and yeah one can customize bootstrap quickly to look however it should, just tell your frontier LLM of choice your wishes.
I don't ever recall hearing about the specific, tangible benefits tailwind brings. Just a loose "it's faster", or "it's easier". It just feels like one of those things, in front end development, that are just hype-driven rather than actually bringing any ostensible benefit.
I'm not a big tailwind fan, but keeping styling in a separate file feels like a net negative
If code doesn't go this direction soon, I'd be surprised. PM builds a prototype with claude, or designer designs something in figma/canva - claude vibe codes 70% of the solution using your company's frameworks and design system, then hands it off to the developer who finishes it and productionizes it
Just like with code, AI will give you something to start with, but it's still going to require tweaking and manual input.
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?
Of course the articles are going to get to the top. It's all anyone is thinking about, and has been for the last few years. I keep wondering if we're going to reach some sort of inflection point where the hype starts to die down, but then another "tool" is released and everyone is convinced that this is the one that will take the jobs. It's a bit tiring, but this is the brave new world.
But they also desperately need users (and the data those users bring) to build their products, and the people who do have the power to manipulate this site are on their team. And it does get tiring to see a new Claude feature with like 1 comment and 25 points right at the top, multiple times in the last two week. Keeping their needs in mind, it has begun to look like manipulation, even if the above effect could explain it.
I'm glad the technology foments it excitement for you. The idea that we can share intellectual processes broadly and implement them without the previously requisite skills will obviously change the world. That it could change the world for the better, excites me too.
But many of us have our excitement tampered by the messaging, the questionable ethics behind how it has been done, and the fact that a real % of the space is basically driven by eschatological thinking. And it especially annoys me that Anthropic is the company whose messaging simultaneously encourages that eschatological thinking, and preys upon the emotional reactions it creates.
I think it is increasingly clear--if you look at recent public sentiment and feel what is in the air--that they are a villain in this aspect. I don't think we want the people who believe they are building the future to be doing so both out of fear--of China--and gaining power through others' fear of what they are doing.
But villains can ultimately do good in the world, despite their villainy. Let's hope that is how it plays out.
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.
The real world analog is this...
The reason people (especially Americans) stay in Marriott property hotels is because they are homogenous. If all I want to do is travel to Phoenix, AZ for work I want to know that the hotel room has the same mattress, desk, TV, customer service, etc. There is real legitimate value to that. So I'll book the Courtyard in Phoenix because I know exactly what I'm going to get.
On the other hand, when I'm traveling the Amalfi Coast in Italy, I want the Airbnb experience. Sure the bed is stiff, there's no A/C, and the 80 year old door frame is hard to close, but there is something magical about it.
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.
There have been studies showing aesthetics matter quite a bit for UX - users perceive things that are attractive as being easier to use and less frustrating.
Bootstrap was great for this. You got a clean web interface that was simple, yet didn't have to be completely ugly. Basic and functional. A form to submit POs doesn't have to stand out, be glassy, or have animations. It needs to be easy to parse and stay out of the way.
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.
But that said, for a UX'er I believe there should be a bit of shame in just doing the obvious amalgam of whatever 2-3 most popular things that already exist.
If you take on the UX lens, there's a lot of flaws in a lot of popular products, but they are accepted by the market because competition is not perfect. Copying that is not great, and I do think there is a point to be made on how "fine" shouldn't be the goal.
If people wanna have fun designing a cool, original website design, go for it. But if we need a fast, easy UI for someone that just needs get the job done, consistency/familiarity is obviously important.
Think of roads. It’s one of few things that humans have managed to agree on across the planet and there’s a good reason for that. The system (regardless of which side you drive on) works. Signs, markings and materials are all pretty much identical wherever you go.
But I reckon, nobody cares. Just let Claude decide and go with it... Sad state for UX designers / researchers.
Your users will never make it to your no-nonsense backend if your marketing is completely cookie cutter.
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.
And people sometimes overestimate their designs because beauty is subjective, and because all children are beautiful in the eyes of their parent.
Also, there’s a reason why the mass adopted plastic, monobloc, stackable chair design is worldwide common and is studied as a cornerstone of design.
Like haggling in the local market, or trying to "catch" that successful/awesome person that has limited availability.
Friction makes stuff feel valuable. Of course, not absurdly confusing, but just a bit.
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.
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.
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.
I guess post IPO, after the insiders cash in out of lock period its irrelevant.
I hear it all the time in the recent two years: web development is apparently dead now, because anyone can just slap together a web site or build a dashboard in minutes etc. because of LLMs.
But that has been true for decades: Templates, component libraries and so on.
But I guess it’s now easier to adjust them if you‘re not familiar with their configuration or something.
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.
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?
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.
When you say old school artisnal design and weirdness do you mean something like this: (shameless plug, but relevant to design)
https://swellslots.com (surf forecast site)
The design for this was literally "90s Arcade / street fighter 2 look"
Funny enough without AI, i would not have been skilled enough to make the graphics (background, logo etc)
This comment is just a rehash of the increasingly outdated and incorrect assertion that LLMs can't possibly exhibit any creativity -- and it's also incorrect.
If you're yearning for "old skool artisanal weirdness of yore", look up the trend on Twitter a month or two ago of people asking Claude to make YTPs. They ended up very weird and artisanal in a way distinct from how any human would do it.
So it's competent, for sure, but that is damning it with faint praise.
In fact, humans waste countless hours trying to figure out what is what and how things work, just because there's always some designer trying to do something nifty. And by "designer", I don't necessarily mean professionally trained designer - although the pros can be given to trying to make artistic rather than functional interfaces.
If you are an UI designer and want to create art then fine do that in your spare time. But at work be a professional and make the UI predictable and functional above all else.
but does it still exists? Even without AI everyone is utilizating the same css frameworks, same libraries and templates... design is pretty much boring these days. CSS Zen Garden anyone?
In a direction where the AI model basically serves you everything live. No sites, no front end, just databases and model embodying them.
I mean why even code anything in the future where it is cheap and fast enough to just come up with everything each time based on each user need.
I am not saying it’s good but it’s lazy. And if one thing is for certain is that laziness prevails. Some even mistake it for progress.
But then, is human programming language really the most optimal way for an ai to steer the silicon? Some kind of bare AI OS with kernel, drivers and there in the middle a fat specialised asic ai chip to orchestrate everything.
I think it's because Steve Jobs killed Flash.
You might just as well bemoan the homogeneity of Windows 95 apps. All those gray buttons in the bottom right of 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.
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.
* Massive token usage, some small tasks burned through $50 of credits and did not offer $50 of value.
* Terrible at logo work. Comically bad. This is something that is "hard" so it could add great value if it could deliver.
* Repeatedly forgot prior feedback - when iterating it would re-implement prior iterations after being told why we didn't want that result which made for a very frustrating UX.
* Prone to adding visual clutter - kept adding extra elements that look "pretty" but add no value to the user.
* Seems better at "pretty" vs user focused / UX.
* Did not do a good job at using my existing design / UI library
* REALLY wanted to start from scratch. Could not be coaxed into designing part of an application, it wanted to redesign the whole thing.
OK but what we really want to know, what's it like when it comes to drawing pelicans riding on bicycles?
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.
It can't render all your math in exactly the same way. If you need it to do that, it may not be for you.
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?
Our mission is to empower the world to design, and we believe in making Canva available in every place where ideas begin. Being the most interoperable platform creates mutually better products, more value for community, and more value and growth for our company.
We've been working closely with Anthropic for many years, and we see this as complementary. Our MCP, integrations, and plugins have already introduced millions of new users to the full power of Canva, and we're excited to continue doubling down here.
The big question is, of course, how invested will they (the companies) be in their products? Will it be a re-run of Google where far too many products end up being scrapped after a year or two?
My 76yo Dad just used Claude Design to make a simple commercial tenancy/lease management CRUD app. We handed what he built to Claude Code to implement within my existing business tech stack. It perfectly followed my coding & testing playbooks (basically a multi-file CLAUDE.md with prompt & command hooks to evaluate conformance). It works… exactly as my Dad imagined.
Now, mind you, my Dad had some outdated UI expectations (he asked Claude Design to style use a Windows 98 aesthetic!), but my point is: we just built a fully-functional, deeply tested, domain-expert-designed app, in less than a day.
Previous comment with the prior 3: https://news.ycombinator.com/item?id=47794419
I wonder what other features they're cooking right now.
With AI, I should be able to ask for things the product designers didn’t anticipate or left out and the system could query, create ui on the fly, etc…
Why would we want to move away from hard fought UX design lessons? Dynamic and fluid UX is infuriating.
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.
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.
Then look at the changelog of Claude Code. They are releasing daily.
The alternative is to not hop on the AI bandwagon, or run an "also ran" AI story, and both those scenarios (I expect) game out worse given the current zeitgeist.
Another thing: I realized how much I hate waiting for Claude to finish its thing. With UI designs, a quick interaction loop between tool and user feels much more important than with code.
Here's the prompt as of around release-time yesterday. You can verify in your own network requests.
https://gist.github.com/mcrowe/9da081f52e0740886d39e730852db...
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.
It’s 2026 and every web application has a different menu layout, date picker, etc.
Designs have been settling on a local maxima. If you are aware of a better hill to be climbed, please do let everyone know.
The shelf-life of unique and mindblowing has reduced to a week (being generous) before it's copied by slop artists looking for a resume booster or funding, and months tops before it's part of training data for everyone. Unless you find it in that small time window everything will seem homogenous.
It could just be a systemic result; unless you deliberately take the lonely road to parts of the internet where other people aren't, you will not see unique and mind blowing things. Which by definition you can't source from a place that has a lot of users, like social media or popular forums.
And rounded corners, of course! :)
This is most every corporate website.
Look up in an old city, look at the facades of the buildings. They have quirks, uniqueness, it makes the city almost a living thing. Every time we shave off another edge we lose that. Nevermind the fact that shoehorning everything into the same patterns is actually an antipattern and very good paradigms have been invented after the 90s.
It's not perfect, but I'd rather have a bit of a mess than boring emptiness.
p.s. Perhaps “quirky” is less because it’s simply not fulfilling? Too often it’s visual gaslighting pretending to be design?
Except it is. Plenty of places will say this is all good enough and not hire, or even lay off, the UI/UX person. I've seen this firsthand.
The average becomes the same shade of gray. Familiarity breeds contempt. New types of design will emerge that are expensive to copy, because differentiation drives competition
These tools don’t solve big design problems, but they do resolve all the little design decisions often left up to devs at implementation time.
This is just a really cool way of building.
I'm impressed. I tried Google Stitch but it was slow and useless. Sad, because Gemini has a pretty good creative flair, ironically enough.
But jeez, is it buggy, slow and unintuitive at times.
Complete shift in google's old engineering culture of high quality - they seem to be shipping quickly in favor of stability
If every designer takes less time to do their job, you need less designers. There’s no getting around that simple math.
2. Long term you can expect the minimum bar for aesthetically pleasing design to be raised and there to be overall less demand for human produced generic design.
3. This will mean all designers get pushed into the same corner or complex, unique, uninferable design and trying to fight it out.
Now, if I could only get a model to draw arch diagrams....
This is also true for entire applications. I vibecode apps in 2 days then say: is this what you want? Then they are enthusiastic and I will say that it will take 2 to 4 weeks to properly create it. They are always confused and then I start teaching them the conceptual basics of how apps are built and what corners are cut. Clients usually listen because they know we’re near the finish line
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.
Figma is for those who could design but can’t code.
This is for those who could neither design nor code.
It probably reduces the tasks which customers might engage an agency using Figma, though. Down the line, creeping onto Figma’s turf absolutely becomes a strategy for Anthropic.
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.
Its making alot of bold assumptions, but we live in interesting times so thats par for the course
Granted, I have not worked with that many designers so it’s maybe small N problem.
The gap between figma and where our front end teams work and design is still too large.
I think the more likely result of this is fewer designers and more work for developers with some design skills.
Not convinced Figma cares about traditional design craft anymore.
He should probably go and let someone else take the reigns.
How many such people does the world need? Probably less than 1,000. Not a very big market for Figma.
Not entirely but I would use this and not Figma. I am passionate about system design not visual design so I don’t want to waste time in figma.
> The folks at Wall Street do not understand
But for me, I will never use it again.
That's meeeee.
https://stitch.withgoogle.com/
I'm now pasting all my Stitch output into Claude Design to see what happens.
edit: First impressions are great. It asked me a ton of really great questions about my design aspirations and direction, which were incredibly relevant and insightful. Waiting to see what it makes.
edit2: It did astonishingly well with the first design pass. Really outstanding. This is probably going to be my primary prototyping tool until the Next Best Thing(tm) drops in a few weeks.
They're down 80% over the last year. Ouch.
Figma actually put the work in to make a great product that performs well and offers anything you could imagine to design just about anything you need, with AI integrations and deep manual editing to sweat the details.
Design work is already under a lot of pressure. I work with somebody that has an industrial design background and he's having a lot of fun with AI tools. There is still a need for good designers. But not to do a lot of the low end design work that has been common in a lot of front end teams. That stuff was always a bit questionable in value. I know some decent designers that were actually getting bored with that type of work. It's very repetitive.
Those partnerships and the MCP were intentionally always watered down. It was purely a play for some cheap exposure without providing anything meaningful.
The very obvious thing for the MCP to expose, that everyone asks for, is to be able to create and edit Figma designs. You can't, likely because they're scared it will kill their product. It's one way: Figma->Agent, no Agent->Figma. They will come around to this one day, potentially when it's already too late. Will be interesting to see how long they wait.
their seats system has always been brutal it’s extremely easy to have the seats balloon if you’re not careful and if they’re yearly there is only a 30 day window a year where you can cancel them when the banner to do so appears.
Nope. Figma Make first renders an HTML/React app with your design. Then you could convert to a Figma design file if you have a pro plan. Extremely underwhelming.
There's hardly any difference between using Figma and just designing it with Codex and Claude Code. And now, Claude Design seems to get it right.
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.
Which needs to be done intentionally in context, not homogeneously as a rapid output of a generative tool.
If you want to make a GUI, it should be familiar. Extremely familiar. It shouldn't invent new ways to interact most of the time.
It is well-known that "intuitive" in UX almost always means "what I'm used to". If you're regularly "innovating" in UI design, you may be making the product harder to use, maybe much harder to use.
It certainly isn't unheard of for new ways to interact with computers to be better than the old, but they are usually tied to new physical aspects of our tools: Touchscreens needed new ways to interact, and maybe there's still some room for creativity there, but not much. The mouse obviously required innovative ideas for several years. But, also, the odds of your wacky new idea being the right way to change how people interact with computers are pretty low, unless you're working at FAANG and have a UX research team and budget to test it.
You can get creative in how it looks, but you cannot get creative in how it works.
Innovation comes from the ways people differentiate, without straying too far from the tried-and-true patterns. It's the tiny decisions that situate UI elements and yes, reinvent the wheel sometimes, that can tip users over to whatever you're building because you did it better, or in a way "most" (the average) never thought of.
If people aren't creative in how it works, then really they're all just making the same, boring products, without truly competing against anyone in a meaningful way in the problem space. Visual appeal isn't a sole differentiator.
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.
I think more expressive UIs are the future but i disagree with this sort of thing being accomplished with a non deterministic tool such as AI generating UIs, you are throwing stability and consistency along with familiarity out the window.
The idea of tools being almost UI-less and composable and modular has been a "dream" since xerox parc or see for example the book "the humane interface" which happens to also ahead of its time outline reasons why such generative interfaces would be a bad idea especially at such a large scale.
AI can potentially relieve some friction with that paradigm but definitely not in that way or even that extent.
"Good designers will reject this."
^ Famous last words.
I will very likely be wrong on the second point.
I have no idea how everything will play out, but this sounds a lot like the people saying "good programmers will reject this" six months ago.
Quite apart from anything else, it ignores the fact that—particularly within large organisations—designers (and programmers) frequently have very little say in the matter.
Jeez I hope fewer designers think like this (and if it's a traditional wisdom among designers, I hope fewer designers in general.) Perhaps web apps will stop moving their icons and buttons around every six months.
Not everyone is looking for unique design, 70% of the web is still using Wordpress. I would say majority prefer familiarity and appreciate uniqueness.
Most people using WordPress customise it with many of the thousands of plugins available though, and those plugins create menu items everywhere.
I guess that kind of thinking got us liquid glass - which everyone hates.
Except, ironically enough, enough people involved with both macOS and iOS at Apple didn't hate it enough — until it made it to launch.
Either there's a massive hierarchy issue there, or Apple is starting to suffer from groupthink that negatively affects a lot of their customers' experiences.
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.
most of those "breakthroughs" were just constraint hacks. no room for a reload button. no room for another menu.
enterprise buyers don't pay for counterintuitive. they pay so the new hire finds save without training.
You’re talking about art, not design.
If you want to talk in absolutes, I'd say the best design is the one that results in the desired behaviour of your audience.
Even the most deluded AI bulls don't say that AI is even meant to replace the best that humanity has to offer
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.
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.
When you deploy AI to build something, you wind up doing the work that the AI itself can't do. Holding large amounts of context, maintaining a vision, writing apis and defining interfaces. Alongside like, project management. How much time is spent on features vs refactoring vs testing.
Or it lets folks focus. My coding skills have gotten damn rough over the years. But I still like the math. Using AI to build visualizations while I work on the model math with paper and pen is the best of both worlds. I can rapidly model something I’m working on out algebraically and analytically.
Does that mean my R skills are deteriorating? Absolutely. But I think that’s fine. My total skillset’s power is increasing.
In fact, there's a palpable irony in your decision to make that comment, which only reinforces the OP.
If only all great works could just be an X post!
What if you don’t give a shit about design and it’s a means to an end for a project that involves something different that you do care about?
For example, I think design, as they mean it, could be described as "how to get that thing we care about". The correct amount of design depends on how exacting the outcome and outputs needs to be across different dimensions (how fast, how accurate, how easy to interpret, how easy to utilize as an input for some other system). For generalized things where there's not exacting standards for that, AI works well. For systems with exacting standards along one or more of those aspects, the process of design allows for the needed control and accuracy as the person or people doing the work are in a constant feedback loop and can dial in to what's needed. If you give up control of the inside of that loop, you lose the fine grained control required for even knowing how far you are away from theoretical maximums for those aspects.
the parent's point is that it doesn't work that way. The point is self reinforcing. Design is not a thing. it's the earned scars from the process. Fine to disagree but it reinforces the point.
Thank you for so succinctly demonstrating the problem with using AI for everything. You used to have to either care enough to do the design yourself or find someone who cared and specialized in that to do it for you. Now you quickly and cheaply fill in the parts you don't personally care about with sawdust, and as this becomes normalized you deprive yourself and others from discovering that they care about the design part. You'll ship your thing now, and it'll be fine. The damage is delayed and externalized.
I won't advocate against use of new technology to make yourself more productive, but it's important to at least understand what you're losing.
Like, maybe I just want to make an interface to configure my homemade espresso dohickey, do I have to wear a turtleneck and read Christopher Alexander now? I just wanted a couple buttons and some sliders.
We don't all have to be experts in everything, some people just need a means to an end, and that's ok. I won't like the wave of slop that's coming, but the antidote certainly isn't this.
I'm an engineer who also loves design. I've read a lot of the books (including the one referenced), I know some concepts and terminology, and I understand the general process — but I'll never be a professional designer. My knowledge is limited, and I find most design tools so complex they actually get in the way of problem exploration and creativity.
For people like me, this tools removes the friction which actually prevents me from being more focused on the valuable parts of the design process. I can more easily discover and learn new concepts, and ultimately spend more time being creative and exploring the problem space.
A whiteboard or a wireframing software would be better, because it lets you focus first on the interactive part. And once that’s solved, the visual part is easier.
I think the challenge will be everything else the person will be doing. Will this person also try to coding? And financial management? And marketing? And operational planning? Just because there are tools out there for them to synthesize implementations of that. If so then they wont be able to get good at any of those. But i think the backwards pressure from failing at those things will bring it back to a stable equilibrium where you have specialists who are good at the abstract ideas of their field leveraging these things as a new abstraction layer of work, analogous to the compiler
I think itll be fine
However, that’s not to say that many designer jobs will be going away, simply because for many cases, cost beats quality. We’ll just have more things with a much lower quality.
You can compare it with mass manufacturing. While some things are better had than not, even with low quality, we’d probably be better off with some things made to last, in lower quantity. But for 99% of the population, e.g. low quality clothing is the norm.
And if it’s LLM the prompt or the rework were very good because I really liked the flow and clarity. That, or you’re a really good writer ;)
This speed and variation wins for me. But yes without a designers eye laziness can get lost in slop design too..
To me the value of Gen Ai is an accelerant (not slop factory) for ideation and solutions not a replacement of the human owning the process.. but laziness ususally wins
when people wax philosophical/poetical about what is essentially capital production already i'm always so perplexed - do you not realize that you're not doing art/you're not an artisan? your labor is always actively being transformed into a product sold on a market. there are no "marvelous human experiences", there is only production and consumption.
> They’ll be impoverished and confuse output with agency
ironic.
The first time I used Mac OS/X, circa 2004-2005, I was blown away by the design and how they managed to expose the power of the underlying Unix-ish kernel without making it hurt for people who didn't want that experience. My SO couldn't have cared less about Terminal.app, but loved the UI. I also loved the UI and appreciated how they took the time to integrate cli tools with it.
I would say it was a marvelous human experience _for me_.
Sure it was the Apple engineers' and designers' labor transformed into a product, but it was a fucking great product and something that I'm sure those teams were very proud of. The same was true with the the iPod and the iPhone.
I work on niche products, so I've never done something as widely appreciated as those examples, but on the products I've worked on, I can easily say that I really enjoy making things that other people want to use, even if it's just an internal tool. I also enjoy getting paid for my labor. I've found that this is often a win-win situation.
Work doesn't have to be exploitive. Products don't have to exploit their users.
Viewing everything through the lens of production and consumption is like viewing the whole world as a big constraint optimization problem: (1) you end up torturing the meaning of words to fit your preconceived ideas, and (2) by doing so you miss hearing what other people are saying.
They realized they have no product or ground to stand on. Once such model drops and once chip manufacturers catch up with demand, they are dead, if their only product is inference.
So OpenAI decided to do weird things like buying up all the hardware that exists or will exist in the next 2 years to buy time to build the product. Then launch things like Sora, ChatGPT shopping, ads etc. They seem to be struggling with this.
Anthropic, being late to the game of hoarding up all the hardware, decided to "buy time" by hiding CoT, implementing KYC (especially for Chinese users), to delay the efforts of distillation. The products they build in the interim are SaaS clones designed from the POV of AI agents and tight integrations with their models.
And it seems like Google is just sitting aside, watching things unfold, since their business model doesn't stand on inference.
The most likely scenario is that OpenAI and Anthropic will still crash and burn when such open model is released.
Figma's survival is still questinable though. Most likely scenario is likely that there's going to be an open source alternative that has AI integration at the core level, rather than an afterthought.
Models are going to commodities - just switch the most affordable.
Longer term, running models locally is going to be increasingly available.
Anyone remember Google's social media platform??? Google Plus?
This is a good era to be in! Its the era of product experimentation.
As long as you realize that 90% of the products will not be supported long term if it doesn't contribute to bottom line revenue, then just appreciate it for what it is, a bunch of smart people trying to create useful products.
Just don't be surprised if Anthropic goes the Google route, which is shutting down the majority of the products that are too small / not successful enough to impact their revenue.
Not every Google product release used Google search. Some of them were completely outside of Google's domain.
Keeping the hype alive through to IPO is critical now.
There's no reason to believe Anthropic will stop caring about this product--they're not Google [1] after all.
> It really feels like Anthropic's product area is extremely overextended at this point.
I don't think so. They have one core product: the Claude model; they're enabling different ways of accessing it. Claude Code for developers, Cowork for general business tasks, and chat for consumers.
This is their first graphic design product, but it fits nicely because once you create a prototype, you can hand it over to Claude Code to make the website, mobile app, or whatever.
The advantage Anthropic has is their ecosystem. A Claude user will be way more productive using Design because all of their context is with Claude; other AI tools don't "know you" the way Claude does. Claude already knows your style and your preferences; it's much more likely to create designs you'd like.
When you go to an AI you don’t normally use, you essentially have to start from scratch.
This is a success story I've been hearing more recently. Restaurants, contractors, plumbing, 1 person startups... I'm wondering if this is because the barrier to entry is now lower - or if these tools are actually moving work away from small software teams or individual devs.
IMO this is the crux of the "AI Eating SWE" scenario (along with other knowledge work...) I'm sure it's a little bit of both. If this was something you were going to pay a designer and a developer for, it changes the outlook.
From my perspective, it feels more likely that with cheaper software we'll see a rush of people building their own, but once it gets sufficiently complex it then needs to be maintained, or improved, and it becomes more work than the initial weekend POC.
I’ve been trying to find a good way to let my Dad keep tweaking the new version but haven’t so far. For now he continues to work (using CD) on the jsx prototype. I can do another export later and CC could use git diff to see what changed and realise those same changes in the “real” version. But there has to be a better way.
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...
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.
Maybe it's true that yellow is just the best, and should be used in 99% of circumstances?
/s
On the other hand, right turn on road now seems to be universal unless a sign prohibits it. And all states apparently enforce slowing down or moving to the adjacent lane for stopped emergency vehilces.
With the core programming skills atrophying, who’s going to have the skills to audit AI’s work?
of course but that's well within the scope of the whole paradigm (as opposed to how it is originally phrased it in relation to a loss of "marvelous human experiences"): if i use a bad tool to solve my customer's problems in an unsatisfactory way then my customers will no longer be my customers (assuming the all knowing guiding hand of the free market). so there's no new observation whatsoever in OP.
Web Components were a bit too slow to take off so the mental model of JSX has stuck with me, even if the ecosystem with hooks and various approaches towards reactive state are in many ways inferior to a problem Smalltalk already solved back in the day.
Obviously a product of its time and laid out similar to how it'd be printed in a magazine (the characters slightly overflowing the borders and such like). Accessibility wasn't a thing back then.
If a different company did that in 2018 you'd be seeing the G-man in corporate memphis, downloading about 500mb of assets, with 178 separate ad trackers in a consent popup, and then you'd be scrolling like mad to get through all sorts of animations that hijack the scrollbar, in order to get to any useful info.
[0] https://www.reddit.com/r/HalfLife/comments/10sx4ve/what_stea...
So, less jobs for sure, but not like 50% less jobs.
Why do people feel that each and every tool they use needs its own unique look and feel? And why are people willing to pay more for that? In some cases, sure. For my smart sprinkler app.. I don’t give a damn if it looks like 1000 other apps.
Had they not included support for it, where would they be now? I'd wager a critical mass would be screeching to High Heaven for integrations, seeing as a Figma document is effectively a config file that can be translated to real code.
These areas obviously tie into engineering very closely, but the thinking that goes into them happens at the design stage, at a lower cost than starting with engineering. AI models suck at getting every facet of this process right, because designers are achieving a balance between branding, usability, standards, taste, and differentiation -- the exact opposite of a model trained to reach for the most average outputs.
So I helped her look into it and I was shocked to find out that it just a react slop generator, not a Figma file generator. And extremely limited at that, too.
Who is Figma targeting with this exactly? Developers, who are interested in react apps will simply use claude code, and UX designers don't really care for react apps.
(Same for car interior design, or things like even doors that some swivels on one axis, some split on multiple, some slide.)
I don't think that us humans really actually like/want standarts. We think we do, but there are 100+1+1 standart from which to choose. So Claude becoming "standart" iš just +1 standart to choose from. Unique is fun!
The Anthropic video on that page at 0:53 literally shows them clicking a "knobs" button and adjusting the pixel CSS value.
I know it's not exactly the same ... but it has that functionality to a degree.
Same here. I work in Claude Code all day long on slightly complex b2b apps, and the builder MVP for what I want to do with Claude.ai, to work on ideas is far simpler.
I just want to be able to create a React artifact prototype on claude.ai, then share it privately with a stakeholder (internal or external.) I want to allow those users to prompt changes, then see their changes in the artifact.
The bespoke design is not what I am really worried about at this phase. For b2b prototype stuff, claude.ai already does an excellent job with just a bit of project-specific prompting.
Why is this shared artifact building not yet doable? This seems "so simple." Yes, maybe some shared artifact specific git to allow version control is required, but is my ask really that hard, or unique?
I've never paid for a figma seat. A couple of employers have so that I can collaborate with designers in the product, but I don't think this changes that.
In an era where it's cheaper and more common to end up at that undifferentiated state, the ability for companies to make their products go above and beyond it is more valuable, not less.
I see this across the board with AI. It lowers the bar to get to passable, but as slop fills the internet we're already seeing people place more value in good products, good writing, good art, thoughtful code architecture, etc. Everyone and their cousin's uber driver is vibe coding a SaaS startup no one's going to pay for right now.
If you are talking about a consumer product, one of these is not like the others.
That’s not necessarily what happened though. Apple innovated not out of sheer daring but because they also had the best metaphysical paradigm for GUIs that people could also just intuitively grasp. There was a structural correctness to their approach, underlying all the things that we find visually appealing. In the beginning, Google dared and deviated hard from Apple’s design language to establish their own unique identity, but anyone who’s working in the mobile space would Have noticed that Android coalesced into roughly the same patterns over time because of that structural correctness.
Tailwind is an abstraction on top of CSS and you can create with it whatever website you want (almost).
I understand the idea behind your comment but feels to be that it sound better than it is true :)
Actually there’s some interesting problems here because a huge part of music marketing is in a visual medium, like a poster or album cover. It is literally impossible to include a clip of your sound.
So you should be really interested in how to capture the “vibe” of your music in a visual medium.
But if you don’t care at all whether ppl actually listen to your music, then yeah you don’t have to deep dive.
The term you are looking for is 'aesthetic'.
And indeed.. music is far more than just a sound or whatever simple thing one tries to boil it down to.
Im convinced many (especially here) really dislike that - they want it just be a case of typing in a few things in an LLM and bam... there you go. They have zero clue about the nature of the economy, what's really going on in various markets etc etc.
just repeating the same mistake as op: sadness/happiness is completely outside the scope here. these are aspects of a job - "design" explicitly relates to products not art. and wondering about the sadness/happiness of a job is like wondering about the marketability of a piece of art - it's completely besides the point!
1. Good design is innovative 2. Good design makes a product useful 3. Good design is aesthetic 4. Good design makes a product understandable 5. Good design is unobtrusive 6. Good design is honest 7. Good design is long-lasting 8. Good design is thorough down to the last detail 9. Good design is environmentally friendly 10. Good design is as little design as possible
Generative AI just tries to predict based on its training data.
a product can be a piece of art and design can and does in practice often go hand in had with art, practically most designers also other than the utilitarian role practice the artistic one, wether you would want to group art within design as one is a matter of definitions
But I don't think that's how it plays out. I think you still need to imbue talent, skills and direction into these tools and I don't see management, who did not have the skills initially, being able to do that task across multiple business aspects and agents simultaneously.
I think for now and perhaps until/if AGI, the sweet spot is having skilled individuals with experience using the tools to known good results. You still can't really delegate to the tools, you have to work with them. The benefit to management that a human has is they can delegate to a human, even when they completely lack the skillset they are delegating.
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.
What is it about our own architecture that lets us innovate beyond our training distribution?
The SWE people I know at SW companies now heavily using these agents complain to me how their workday is nothing but code-reviews of the agents output and tedious prompting to prod it back into line; they say they don’t get to actually write code until they get home to work on their personal projects.
3 years ago I never would have believed this capability was possible; I’ve since adjusted my expectations to now assume that in another 3 years the models/agents will have improved enough to reduce the amount of code-review required, leaving us with precious little else to do for our shareholders, or the opposite: they don’t improve and we’re stuck doing thankless PR reviews until the end.
Please tell me where and how in this future I’m supposed to find satisfaction and pride in my work when what-gets-produced isn’t my own work anymore?
I also understand that our wonderful quality of life is due to automation, and sometimes that means I draw the short straw. That's okay.
Or worse, you gave up because you did not have the time to learn the skill or the money to hire somebody. In this case, your dream just died.
If Grok didn't create the fake nudes users were dreaming about but couldn't create with Photoshop,
would my headstone crumble down?
As "intel" dashboards stay a dream,
the Hollywood wind's a howl
As photos are just still
The Kremlin's falling
As Einstein is not wrong
Radio 4 is static
You think most UI/UX designers, or the artists creating slop for content marketing spam factories for the past decades, cared? Some, maybe. Most probably had higher ambitions, but are doing what actually pays their bills.
It's similar to software developers. Most of those being paid to code couldn't care less, they're in there for the fat paycheck; everyone else mostly complains the work is boring or dumb (or worse), but once you have those skills, it makes no economic sense to switch careers (unless, of course, you're into management, or into playing the entrepreneurship roulette).
The paychecks weren’t great. Everyone was offering to pay designers with “exposure”. If they didn’t innately care about the field they would have done something more lucrative.
...
> Work doesn't have to be exploitive. Products don't have to exploit their users.
bruh do people have any idea what they're writing as they write it? you're talking about "work doesn't have to be [exploitative]" in the same breath as Apple which is the third largest market cap company in the world and who's well known for exploiting child labor to produce its products. like has this comment "jumped the shark"?
> Viewing everything through the lens of production and consumption
i don't view everything through any lens - i view work through the lens of work (and therefore production/consumption). i very clearly delineated between this lens and at least one other lens (art).
Ultimately the exploitative pyramid always terminates in a peak, and the guys working up there can for sure be having a hecking great time doing their jobs.
It's true that design theory writing is annoyingly verbose and intangible, but that doesn't make it wrong. Give someone a concrete language spec and they will not really know how it feels to use the language, and even once they do experience its use they will not be able to explain that feeling using the language spec. Invariably the language will tend to become intangible and likely very verbose.
But to answer your question: no, it's of course perfectly serviceable to just copy the interface others have created, and if the needs aren't exactly the same you can just put up with the inevitable discomfort from where the original doesn't translate into the copy.
It’s not the science and intellect I take issue with, engineering has plenty of that. It’s the art-adjacent navel gazing post modern bullshit I don’t like.
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.
Now I struggle to even define what an "operating system's standard visual appearance" is. Apple's still the best but not what they used to be on that front even so.
In the early days, if you learned the OS, those usage patterns and skilled transferred to every app on that OS. They all looked roughly the same, shared the same menus, shame shortcuts, same icons, etc. You didn't have to learn how to use Apps x, y, and z. You just had to learn Windows (to an extent).
Then marketing got involved, and then the web, and then suddenly every piece of software had to stand out and look and behave as unique as possible, throwing years of HIG research out the window.
Just today I had the disk usage analyzer (baobab) open and I was navigating inside directories so I want to go up a directory and clicked on the "<-" left arrow in the headerbar, which went "back" a screen, discarding all the work done scanning the filesystem.
If this app had a traditional menubar and a toolbar this wouldn't have happened.
This is a common type of experience I have every time I use a Gnome app. It almost feels like someone deliberately researched how to make desktop apps as counter-intuitive as possible and implemented that as the policy for some reason.
And locked your thinking into the OS' way of thinking. Every software vendor had to do their application a few times over with a different release for each OS, because the design is completely different.
As someone who uses multiple OSes (work macOS and iOS, home Windows and Ubuntu, Android) I hate nothing more than apps that behave differently on the different OSes, with different logic or features.
Years ago, I remarked to a friend that I'd spent half of my (computing) life post-high speed Internet, yet almost all my happy memories are from before that. It was the same for him, and we both explored why that was.
The homogeneity of interfaces was actually one of the reasons we came up with on why doing work at a computer is a lot less appealing.
I understand your feelings but it is extremely tipical in human history to keep remembering "the good old times"
Wasn't Winamp 2 the gold standard? I remember plenty of music lovers switching to foobar2000 when Winamp 3 came out, because it was, as you said, slow(er).
The parent is talking about toolkits like Swing where things looked[1] almost, sort of, but not quite like the native system. That wanted to be native, but for technical reasons fell short. These are what many considered to be completely unfit for use. Whereas today, designers wouldn't think twice about applying the same kind of almost-native-but-not-quite theme to match their arbitrary whims and think they are doing the world a service by doing so, the UI conventions (to the extent that there remains any) of the host system be damned.
[1] https://upload.wikimedia.org/wikipedia/commons/c/cc/Gui-widg...
It is a truism that the majority of effort and time a software dev spends is allocated toward boilerplate, plumbing, and other tedious and intellectually uninteresting drudgery. LLMs can alleviate much of that, and if used wisely, function as a tool for aiding the understanding of principles, which is ultimately what knowledge concerns, and not absorbing the mind in ephemeral and essentially arbitrary fluff. In fact, the occupation hazard is that you'll become so absorbed in some bit of minutia, you'll forget the context you were operating in. You'll forget what the point of it all was.
Life is short. While knowing how to calculate mentally and/or with pen and paper is good for mastering principles and basic facility (the same is true of programming, btw), no one is clamoring to go back to the days before the calculator. There's a reason physicists would outsource the numerical bullshit to teams of human computers.
"Generative AI" isn't just an adjective applied to a noun, it's a specific marketing term that's used as the collective category for language models and image/video model -- things which "generate" content.
What I assume you mean is "I think <term> is misleading, and would prefer to make a distinction".
But how you actually phrased it reads as "<term> doesn't mean <accepted definition of the term>, but rather <definition I made up which contains only the subset of the original definition I dislike>. What you mean is <term made up on the spot to distinguish the 'good' subset of the accepted definition>"
I see this all the time in politics, and it muddies the discussion so much because you can't have a coherent conversation. (And AI is very much a political topic these days.) It's the illusion of nuance -- which actually just serves as an excuse to avoid engaging with the nuance that actually exists in the real category. (Research AI is generative AI; they are not cleanly separable categories which you can define without artificial/external distinctions.)
I can get LLMs to write most CSS I need by treating it like a slot machine and pulling the handle till it spits out what I need, this doesnt cause me to learn CSS at all.
It takes a lot of cajoling to get an LLM to produce a result I want to use. It takes no cajoling for me to do it myself.
The only time "AI" helps is in domains that I am unfamiliar with, and even then it's more miss than hit.
I'm not saying iTunes (Music.app bleh!) would be better reimagined as Winamp 2 but I'm not not saying it.
The other 10% of the design world? Actual useful, and can help create truly better things. And typically offered honestly because there really is something of substance being shared. To be clear: there can be tremendous value in the design world.
And nice false dichotomy there - if someone disagrees with the snooty extravagances of the design world, then they only care about science and engineering. That is not what I said, and your twisting of my statements is either a shallow read or disingenuous.
But:
I would have still said I enjoyed using computers. And I wouldn't have said "Today's interface sucks" (well, other than my HW not being able to keep up with eye candy...)
I simply don't enjoy using the computer these days. And I do think the interface sucks. Pretty much anything that involves using the web browser sucks - be it a local app or a web app.
I don’t even bother. Most of my use cases have been when I’m sure I’ve done the same type of work before (tests, crud query,…). I describe the structure of the code and let it replicate the pattern.
For any fundamental alteration, I bring out my vim/emacs-fu. But after a while, you start to have good abstractions, and you spend your time more on thinking than on coding (most solutions are a few lines of codes).
Quality is a different issue, sure.
But there's is "pride" in making tools people actually use without issue
why do we build with right angles, straight lines, regular curves, etc? Why not random angles, crooked lines, etc for style and "excitement"?
Why don't we assemble a furniture set from a random assortment of pieces from flea markets? People sense that that is ugly.
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.
Design is much harder for power user tools compared to consumer. There is far more complexity and the expectation often is users must be trained to even use the tool.
Design only goes so far.
Why ? Since its so notoriously bad why have there been no attempts to improve it ?
Describe the idea of what you want to do, not the inscrutable steps the application requires to get there.
Correct, they are paying for work done by people in other roles, who's title isn't UI or UX designer. It's on the backend person for velocity, it's for business development for leverage, it's on data scientists for insight, it's on logistics for convenience. Those people will be paid for solving those problems, not for tweaking CSS. My team, who falls into this category of more invisible work, has not hired UI or UX person at all. Which by mathematically speaking by default, is simply below the average rate for that work. Meanwhile Apple will pay easily mid six figures for someone in a more flashy role.
Respectfully disagree.
You should feel pride when you deliver the easiest-to-use system that the hospital lawyer has ever used. When you get them in and out of the system quickly because it's intuitive and has an appropriate architecture.
If there is no person in the team who prides themselves to deliver interesting/elegant product, then it is very unlikely the product will be interesting/elegant.
I believe this is not something we want to happen, a world with no interesting/elegant products.
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.
A cold American convenience store may be delivering the fundamental value at American prices, but there's something to be said about that "extra" human or creative element. One might say the same thing about the changing nature of the web over time, less individual CSS chaos and more Facebook aesthetics.
But I really don't need that quirkiness at Home Depot, the DMV or my bank (or Amazon, or government websites, or my banking site). I'm there to purchase some screws, register my car or pick up some checks. I just need a storefront (or a website) that lets me do that as fast and homogenously as possible.
99.9% of stores (and UIs) are the latter, not the former.
This allows me to focus my attention on important learning endeavors, things I actually want to learn and are not forced to simply because a vendor was sloppy and introduced a bug in v3.4.1.3.
LLMS excel when you can give them a lot of relevant context and they behave like an intelligent search function.
The real fun of programming is when it becomes a vector for modeling something, communicating that model to others, and talking about that model with others. That is what programming is, modeling. There's a domain you're operating within. Programming is a language you use to talk about part of it. It's annoying when a distracting and unessential detail derails this conversation.
Pure vibe coding is lazy, but I see no problem with AI assistants. They're not a difference in kind, but of degree. No one argues that we should throw away type checking, because it reduces the cognitive load needed to infer the types of expressions in dynamic languages in your head. The reduction in wasteful cognitive load is precisely the point.
Quoting Aristotle's Politics, "all paid employments [..] absorb and degrade the mind". There's a scale, arguably. There are intellectual activities that are more worthy and better elevate the mind, and there are those that absorb its attention, mold it according to base concerns, drag it into triviality, and take time away away from higher pursuits.
> It's annoying when a distracting and unessential detail derails this conversation
there is no such details.
The model (the program) and the simulation (the process) are intrinsically linked as the latter is what gives the former its semantic. The simulation apparatus may be noisy (when it’s own model blends into our own), but corrective and transformative models exists (abstraction).
> No one argues that we should throw away type checking,…
That’s not a good comparison. Type checking helps with cognitive load in verifying correctness, but it does increase it, when you’re not sure of the final shape of the solution. It’s a bit like Pen vs Pencil in drawing. Pen is more durable and cleaner, while Pencil feels more adventurous.
As long as you can pattern match to get a solution, LLM can help you, but that does requires having encountered the pattern before to describe it. It can remove tediousness, but any creative usage is problematic as it has no restraints.
Are you really going to do that though? The whole point of using AI for coding is to crank shit out as fast as possible. If you’re gonna stop and try to “learn” everything, why not take that approach to begin with? You’re fooling yourself if you think “ok, give me the answer first then teach me” is the same as learning and being able to figure out the answer yourself.
Qua formal system, yes, but this is a pedantic point as the aim - the what - of a system is more important than the how. This distinction makes the distinction between domain-relevant features and implementation details more conspicuous. If I wish to predict the relative positions of the objects of our solar system, then in relation to that end and that domain concern, it matters not whether the underlying model assumes a geocentric or heliocentric stance in its model (that tacitly is the deeper value of Copernicus's work; he didn't vindicate heliocentrism, he showed that a heliocentric model is just as explanatory and preserves appearances equally well, and I would say that this mathematical and even philosophical stance toward scientific modeling is the real Copernican revolution, not all the later pamphleteer mythology).
Of course, in relation to other ends and contexts, what were implementation details in one case become the domain in the other. If you are, say, aiming for model simplicity, then you might prefer heliocentrism over geocentrism with all its baroque explanatory or predictive devices.
The underlying implementation is, from a design point-of-view, virtually within the composite. The implementation model is not of equal rank and importance as the domain model, even if the former constrains the latter. (It's also why we talk about rabbit-holing; we can get distracted from our domain-specific aim, but distraction presupposes a distinction between domain-specific aim and something that isn't.) When woodworking, we aren't talking about quantum mechanical phenomena in the wood, because while you cannot separate the wood from the quantum mechanical phenomena as a factual matter - distinction is not separation - the quantum is virtual, not actual with respect to the wood, and it is irrelevant within the domain concerning the woodworker.
So, if there is a bug in a library, that is, in some sense, a distraction from our domain. LLMs can help keep us on task, because our abstractions don't care how they're implemented as long as they work and work the way we want. This can actually encourage clearer thinking. Category mistakes occur in part because of a failure to maintain clear domain distinctions.
> That’s not a good comparison. Type checking [...]
It reduces cognitive load vis-a-vis understanding code. When I want to understand a function in a dynamic language, I often have to drill down into composing functions, or look at callers, e.g., in test cases to build up a bunch of constraints in my mind about what the domain and codomain is. (This can become increasingly difficult when the dynamic language has some form of generics, because if you care about the concrete type/class in some case, you need even more information.)
This cognitive load distracts us from the domain. The domain is effectively blurred without types. Usually, modeling something using types first actually liberates us, because it encourages clearer thinking upfront about the what instead of jumping right into how. (I don't pretend that types never increase certain kinds of burdens, at least in the short term, but I am talking about a specific affordance. In any case, LLMs play very nicely with statically-typed languages, and so this actually reduces one of the argued benefits of dynamic languages as ostensibly better at prototyping.)
> As long as you can pattern match to get a solution [...]
Indeed, and that's the point. LLMs work so well precisely, because our abstractions suck. We have lot of boilerplate and repetitive plumbing that is time-consuming and tedious and pulls us away from the domain. Years of programming research and programming practice has not resolved this problem, which suggests that such abstractions are either impractical or unattainable. (The problem is related to the philosophical question whether you can formalize all of reality, which you cannot, and certainly not under one formal system.)
I don't claim that LLMs don't have drawbacks or tradeoffs, or require new methodologies to operate. My stance is a moderate one.
Users don't need to think about how to use them; they are ubiquitous and familiar, and therefore intuitive and automatic.
If every set of stairs (or, worse, if every stair in a set) was radically different, every time you approached some stairs you would have to think carefully about how to use them so you don't fall.
My point is that I don't find this to be case. Rather, consistent UIs, while functional, are also beautiful to me. The constituents of the UI can be designed with aesthetic taste, but the way it is all put together consistently and functionally has a beauty all its own.
A personal example from a few weeks back. My SO booked a hotel for a weekend as a birthday present. We went there, it had a fantastic spa, dinner was delicious, the room great, clean, and so on. Individually designed, well thought out, friendly staff.
Breakfast came around and the coffee was abysmal. Really truly abysmal. What did we do? While eating breakfast we looked for a McDonalds, as we know for sure, that regardless where you are - you will at least find an okay and drinkable coffee at McDonalds. It is not a great coffee. And will never be. But the likelyhood is very low that you will find a shit coffee.
Marriott is basically the same for hotels. Or MotelOne in Germany. It is the power of brand - you get a solid 7 out of ten. And to be honest - when I am traveling for work, this is all I want. I want to know, that I will have a clean room, a bed that is good to sleep in. And the knowledge, that I will likely wake up rested the next day when I have to be at my best for my clients.
The risk of ending in a shit-hole got smaller because nowadays people write their experiences - but on the other hand, having seen how many of my reviews were being deleted by Google, Yelp, TripAdvisor and the likes because some lawyer requested it - I don't give a rat's shit for online reviews.
Marriotts are sadly not the same between countries, and that's probably a good thing.
The standard for large chain hotels in the US are much, much lower than everywhere else in the world. Full-service Hiltons in the US don't even have executive lounges anymore.
Some (at least one) don't even have breakfast facilities...
this is true for fast food as well. mcdonalds in poland and spain were MUCH better than the slop in america. I had taco bell here in srilanka recently. it was DELICIOUS and tasted like real food. same goes for popeyes and pizza hut here. pizza hut in america on the other hand tastes regrettable and left me feeling like shit.
Canonical UX patterns are generally beneficial and most 'design' attempts are well-meaning dark patterns.
Xerox figured out windows, scroll bars, buttons, groups in the 1970s and most web interfaces are STILL not up to that standard!
Heck - they're not as good as Visual Basic apps from the 1990s.
Largely due to lack of design discipline.
Good pizza in Italy, goos ramen in Japan, grilled Picanha in Brazil, that's why you go there and want it different/original.
But in software UI this is often overdone. I want the pizzazz in my audio software in what it produces, not in how the UI looks like.
Besides the bun, it is noticeable in every part. The amounts and quality of the sauce, vegetables, and meat. And finally how the burger is presented.
So if this difference can occur within 1000km of each other in the same continent, I fully accept that it is even more varied in the whole world.
In other countries the do have a lot of additional meals which are specific to their local taste (rice/fried chicken/different sauces) but the core burgers like a Big Mac, mcChicken and sides such as fries are there.
Real design would be changing how beds, showers, toilets, keys, etc etc work.
Yes there is familiarity in the truly banal, but progress in design happens when we really question how things work.
That's [design] engineering.
Rather than aesthetics/ergonomics. Like writing your own widgets in JS, generally a bad idea.
“Intuitive Equals Familiar,” a classic from Jef Raskin, the man who started the Macintosh¹ project at Apple:
https://www.asktog.com/papers/raskinintuit.html
———
¹ Only to have Steve take it away. Jef left and created the Canon Cat, an opinionated computer that eschewed the WIMP interface in favour of anchoring n incremental search. Steve would also leave and create NeXT, and Canon would invest in NeXT as well.
More accurate to say that he was forced out. We (Mac nerds) were shocked when he came back. My father told me that I was super excited talking about his return, though I don't remember that. I do remember having a Mac Addict magazine with SJ portrayed as a priest on his return. Internet Archive ftw.[0]
0. https://ia601204.us.archive.org/BookReader/BookReaderImages....
I travel 300 days a year work for and stay in hotel apartments, and I still miss the Hyatt I stayed in Manchester in 2021… last place I stayed that had gotten everything right.
Unfortunately, Airbnb itself have turned into an IKEA showroom experience …
Because it turns out, the type who don’t want fun little differences are exactly the types who will gladly go on a business trip to Phoenix Arizona and stay at a Marriott hotel.
I don't want more pieces of flair in my life, thanks
You generally won't get to know someone well enough to appreciate their unique aspects unless you see them in person at least sometimes, unless that person has the habit of letting their freak flag fly in all circumstances, which has its own downsides.
Then don‘t. My boss didn’t require me to put a minimum of 15 pieces of flair in my status, and personally I just put blur on my background... scrap that, I didn’t turn on my camera at all and just used my standard avatar (which I consider fun in fact).
What made these Delphi programs so unique in their UIs?
When there is a boardroom battle over control, I think almost any take is fair. Sculley kicked him off Macintosh. Steve then tried to oust Sculley, who gave him a "window seat."
Sculley had the Board's support, and Steve resigned rather than quietly sit in the corner playing with "New Product Development" toys. The Board refused to accept his resignation and encouraged him to rescind it, but no they didn't give him meaningful authority, so he carried on to Plan B and negotiated the right to make "Education" computers.
Did he jump? Was he pushed? Yes!
And back to the point I was making... His trajectory had something in common with Raskin's trajectory, right down to raising money from Canon.
———
p.s. Fellow OG Mac developer here. I still have the SE/30 I used to write a classified ads app for QuarkXPress and Aldus PageMaker back in the day. I would describe classified ads software in the 90s as, "faster horses about to be eclipsed by automobiles."
It used to be the new, western chain that you only saw in American movies, and then you could experience it for yourself. When I was a kid (middle / solid working class family), we'd semi-regularly do mcDonalds trips as a treat. The experience of going to mcDonalds because you were too poor to do anything else was unthinkable to us.
Other brands that are staples of the American experience were also like this. CocaCola definitely comes to mind here; most of our tapwater is drinkable, and bottled water is much cheaper than coke, so that was the default option for most people, along with coffee and tea of course.
Somebody did the calculations on Polish Twitter recently, and apparently taking a 4-person family to Pizza Hut in the early 2000s used to cost more than our average daily wage.
And yes: I talked to them.
Thatis, if you happen to go to a random McD in some country and the big mac was great that day and you go to a different restaurant in a different country on a different day and the big mac was bad, then that difference has likely least to do with them being in different countries. It's not like they actually use different recipes.
