We already have the business side come with requirements in the form of 'solutions' that they have thought up, which more often than not are Rube Golberg-esque contraptions, that you have to conversationally reverse engineer to arrive at the actual requirements.

In the future they will come with their 'ready' solution, already 'working' and be even less receptive to look at design and architecture holistically. Just make it like that. And why do you need to spend X man hours? The thing is basically already done!

I have seen this already. Vibecoded top to bottom.

The downside is that the business people don't understand why you can't just put their app in production as is. And then there's a lot of pressure to make it happen quickly "because we can use AI to move fast". This is going to come down to healthy organization dynamics, and hopefully represents a learning opportunity for leadership.

The upside is that the idea has already been proven out much more thoroughly than a sketch on a napkin. Claude has already prompted them about edge cases and design decisions. It's very likely that at some point they had to explicitly tell Claude "don't worry about that and just make an assumption", or "I actually don't like that interaction after trying it a few times, can you do a differently". They had to write out much of their idea in clear and direct language in order to prompt the AI. They've probably been playing with their own toy because it's fun to play with toys you summoned from thin air, so they've had a chance to discover the experience and refine their own preferences.

It's probably a net negative right now because the "ship it what's the problem team" pressure is intense and stupid and demoralizing and miserable to work under. But I think it will stabilize and it might be a net positive in future projects.

I've working on a small side project with a non technical friend for a couple months. It's really small but we are selling it to some clients.

The other day my friend discovered lovable and vibe coded an entire app and he started feeling like I was scamming him. Why would I take weeks or months in building our app if he could do it on hours?

He might be stubborn but ended up blindly believing me, but I couldn't find a good way of explaining that a prototype wasn't a final product. It has lots of errors, doesn't consider edge cases and it's impossible to fix if something breaks. Of course what I said didn't mean much because he didn't understand what I was talking about.

How do you communicate this problem? That there's much more than what you see in a frontend? Seems really hard to explain to non technical people.

It's the same problem we've had all along though, right? Maybe it's magnified now but the essence of the confusion is the same.

let them launch and fail

it’s the only way they learn

Show it. Pick a missed edge case or breaking point in his app and demonstrate the pain the customer is going to encounter. You don't have to live in the realm of hypotheticals. He has given you a concrete, but flawed, implementation that offers proof of your message.

I did it and he "fixed" it with AI, making him even more convinced of it.

I'm pretty sure something else must have broken but didn't see it immediately.

I guess eventually it will fall from its own weight but I'm surprised how far he was able to get.

You are convincing me of it too. It is clear that your friend still needs your system thinking to point out edge cases and whatnot, but if you applied that by spending a couple of days adding a test suite to provide the missing validation, it seems like together you could have a pretty robust product built in less than a week. What justifies a couple of months?

> business people don't understand why you can't just put their app in production

I’d flip that around and say that engineers don’t understand that sometimes you _can_ just put their app into production. It might take some cleanup, and some clever ways of deploying it in isolation, but some of these “vibe coded prototypes” — many made by technical business people (they do exist) – are much closer to production-ready than you might initially assume.

I’d encourage you to challenge your assumptions before dismissing the possibility. I’ve personally seen this workflow produce real production code, used by customers, in an extremely rapid feedback loop. Now is the time to adapt, not push back. Keep an open mind or you’ll be left behind.

> It's very likely that at some point they had to explicitly tell Claude "don't worry about that and just make an assumption",

Non technical folks vibe coding aren't explicitly telling Claude anything other than "Accept"

I honestly much prefer this to the old way where the only mode of communication was speech or text. I now often understand a lot more holistically what the person coming with their product wants with just a demo + a conversation.

Of course you need the person making that vibe product to understand it's just a mockup of their idea and that it'll change. But I would argue this has always been a necessary quality for a product person.

thats really sad that only way you can understand something is with pictures and demos. like a little toddler.

when they already come up with a working model it doesnt really leave any room for abstract thought because now you are in concerte world . They see you as a machine that turns mocks into impls ( maybe you youself see yourself like that).

its ok if you see yourself as a code monkey monkey doing menial job of implementing someones mockup. But that job wont be here long and you will be on the streets holding "can turn working mocks to production code for food" signs.

honestly your attitude scares me more than some business guy building crap in lovable.

I can understand words, but having more diverse medias for communication lets a person express strictly more than before.

Sometimes words are better, sometimes a visual demo is better.

Is your solution to the problem you presented that you should artificially restrict what a person can express just to keep your own personal moat?

I prefer the alternative, let a person express themselves and grow thanks to AI, while keeping the necessary culture and boundaries to where it's also accepted for _me_ to cross boundaries and express my ideas to them in the same way. Or suggest other ways to express those ideas.

We then become a marketplace of ideas in a much deeper sense than before, where product managers would already expect you to implement what they want, but without them being able to convey it properly.

If I didn't have original ideas and didn't think I could compete in that marketplace of ideas, I would be scared like you convey in your message. But I'm confident that my value is not about translating things into code, it's because I have original thoughts I can convey to other people (and to AIs). (and about understanding architecture and systems to a degree that keeps me valuable even if all the code itself is written by AI without my direct involvement)

What an insane replay.

A (good) picture is worth 1024 words.

no business person will ever want to consider the right tradeoffs without being forced to

the ai making assumptions can’t get it right

I’ve seen that play out already as well

Then your job as SE just becomes reviewing and untangling vibe-coded stuff

I think Jane Street is an Anthropic investor, so take it fwiw.

With a huge pile of salt

> In July 2025, the Securities and Exchange Board of India (SEBI) alleged that Jane Street used multiple entities for market manipulation and barred it from accessing the market.

Anyone with knowledge of Indian regulatory culture would not take this as dispositive.

Such as them not paying the required bribes

And here's some rather more clueful analysis instead of what looks like AI-generated marketing blogspam:

https://www.bloomberg.com/opinion/newsletters/2025-07-07/jan... (https://archive.fo/0PQ2E)

That bloomberg which spread fake news about india selling gold which it had to retreat. I will sbi over foreign news peddlers.

Incompetent SEBI went after Jane Street for closing an arb, what about it?

As I understand Jane Street they have done great things for OCaml and they also do their own web framework (I guess that big money bin needs a lot of dashboards).

I think the designer here takes a wrong approach and sort of falls into engineer envy where he wants to make prototypes as deep and realistic as possible. And that is not really the most important part of the design job.

The most important thing is that the right thing gets build (why do we need a JSQL input box? what do we actually want? what are other ways to do this?). And this is often better done with pen and paper sketches, meetings, observation, discussions ... rather than too quickly narrowing on a particular design and spinning into discussions on whether buttons should be on the left or on the right, LLM intricacies etc.

Taking it slow with paper and interviews works if you think about what you're doing. The other option now is shut down brain and press the slot machine lever one more time. One of the designs has got to be good soon.

(I’m the author) making ideas legible and testing them with users is part of the design process regardless of tooling. You can summarize this article as “I find LLMs more effective at making ideas legible vs figma - for the work I’m doing at Jane Street”. This has helped me iterate and it helps me test with users and get better feedback from them. I’m not just prompting “make no design mistakes” over and over.

This. LLMs helping implement many ideas is a curse and the results speak for themselves.

As a non-designer I want to see a thought through 1-2 ideas, not 10 ideas you coded with llm and now the burden of thinking which one is better and why is for some reason is on me.

People are much better at saying what they don’t want rather than thinking about what they do. It’s more effective to throw everything in using LLMs, then using human judgment to sculpt away.

>> It’s more effective to throw everything in using LLMs, then using human judgment to sculpt away.

Not really. Maybe its effective from designer side but from other side that has to review all those ideas it is exhausting and counterproductive. Especially when it is in code.

You really don't need a real prototype for most things. Simple visual is more than enough to present an idea and explain etc. In fact, it is often much better as you can see all flows in canvas at once.

With interactive prototype to see all flows of a feature you have to go through each one, which again is very uneffective.

Even if they're not, I'm not sure if we should care a quantitative trading firm's opinions on frontend design...

Why not ? They might have client facing apps or internal research applications. Such a weird comment.

The whole HN is one huge AI ad now.

I think AI programming just has a bliss period for a lot of people where it feels like you can solve every problem with a prompt. And you can, for a time. Eventually the chickens come home to roost and you realise what a mess you made.

Give it some time. We’ll figure out what LLMs are good and bad at. I think vibe engineering will eventually go up on the wall next to static vs dynamic typing and vi vs eMacs.

At least, that assumes AI models won’t keep improving by leaps and bounds. We’re in a transition period. It’s gonna be chaos.

> eventually the chickens come home to roost and you realise what a mess you made

But a lot of times they don't. Devs building websites for small businesses used to be a thing, and it was almost universally a crap product. Practically every restaurant in my small town has been able to take control of their own website with AI, and it's a better experience for everyone.

Rapid digitisation meant a lot of low-value work wound up being done by high-value people. The economy is pivoting away from that configuration. The high-value folks getting displaced are pissed, partly rightly, partly out of spite. The folks who had to pay those bills are ecstatic, mostly overexuberantly, but in part correctly.

That era is already long gone. Those things have been built in Wix for over a decade. And since then, I haven't had any friends or family ask me for a simple site. The low-value work is already automated.

Your comment is valid, but not for the reason you think. What you should be talking about is the grunt work done in our field to non-trivial applications. Adding a search box to a table, or add an extra field to a form, etc.

So you think about a ticket that often might take a few hours, but in badly architected system might take a week, add a field to a class, edit the DB structure (maybe manually, maybe through via an ORM generated migration), add it to DTOs, add a validator, add it to the FE definitions, edit the page layout, etc..

Low value work that until now had to be performed by high-value employees.

> That era is already long gone. Those things have been built in Wix for over a decade.

I think there's still a lot more custom work than you'd expect. A recent example: My mum is ex-president of a small international NGO. When I visited earlier today, she was bemoaning how the lady who runs their NGO's website charges them an arm and a leg for small changes. As a result, the website is constantly out of date. The current site is entirely built on top of wordpress. There is, of course, politics. This lady holds the login credentials to everything. And she holds them close to her chest.

I showed my mum what we could do with claude design. Claude whipped up a much better looking, working version of (part) of the website in about 5 minutes. I think LLMs aren't quite at the point that my mum could manage the website herself. You do need a little technical knowledge. My mum just doesn't know what to ask for. But we're really close. I've offered to be a human frontend to LLMs for them going forward, if she can wrest control from the "webmaster".

I suspect conversations like this are happening everywhere at the moment. There are an incredible number of small websites out there. Most of them, claude or chatgpt could reimplement in 5 minutes tops.

> Low value work that until now had to be performed by high-value employees

The current trend is a proliferation of internal tooling. I've honestly found quite a bit of it useful. The rest is the usual should-have-been-a-Google-form nonsense.

Until what they need is free or has a heavily subsidized cost. We keep forgetting that

I can use a local model to build a restaurant website. The model generates code fast enough that even my 10 year old server can generate all the code needed in about an hour. It will use about 50 cents of electricity and be better than 90% of the restaurant websites out there.

I’m curious what you’re using for that (if you’re inclined to share).

I saw that blog post about running local models on a Xeon based server so I benchmarked a bunch of local models on it. The server is dual Xeons with 256 GB of DDR4 and I found it capable of running some things locally. It's slow but still faster than coding things manually. Also that was just an example. Even my 6 year old 6900XT is faster.

I think there’s a good chance low effort AI content and vibecoding effectively become an eternal September

Yesterday I needed a tool for a specific task. In 1 hour I created a working tool with antigravity. Is it something I'd publish or sell or offer to others? Probably not, but I found that quite impressive. It is an extension of the idea "now I can program and create everything."

Besides I remember what kind of code we had when we first started coding with AI and now with all these coding agents etc. it has become quite impressive.

However, at the end it is still a tool and needs to be used accordingly.

You can create anything you need as long as what you need is a disposable script, a scotch-taped together single page app, or a complex problem and you have thousands of dollars to throw at tokens.

I've been playing with local models for some time, and I've been pleasantly surprised of late. A meager rtx 5080 with 16gb can give pretty good results now. The ecosystem is also improving pretty quickly.

I have a feeling at some point we will have a "Windows 95" moment (when computing really became personal for the masses) in AI, and things will significantly change shape again.

What local model do you recommend these days? I’ve got a 4090, mostly sitting idle.

qwen 3.5 with 9b is being a pretty decent workhorse for me, even with context around 4k.

Hey, at least vi vs emacs is fun, no matter how crappy as an editor Emacs is, no one is getting paid by privacy invasive corporate, to sway people, to cash out more money

I was literally reading through another thread[0] where the OP claimed that HN is anti-AI. I guess HN is decently balanced afterall?

[0] https://news.ycombinator.com/item?id=48420827

And the comments you reply to prove the point made by Dang.

I thought we were too anti-AI?

Pro- or anti-AI, it's seemingly related or tangentially related to half of the discussions on HN.

Depends which agent you ask to cherry pick comments for sentiment analysis.

I’m looking for an alternative too..

The utility of current-era AI may well be overstated, and the business models of certain companies might be doubtful, but that doesn't make AI it a "cult".

An opinion held, in my estimation, by a tiny (but noisy) minority of people who have always existed; the trend obsessed rebuild-the-world types who probably think that AI will soon be able to write unaided a kernel in Rust superior in 100% of metrics to Linux.

AI is not a cult, HN regarding AI is.

It's boring and it's viral and if you refuse to participate, there are still people annoying you with their beliefs.

It's a fucking tool, like a fucking shovel.

"It's a fucking tool, like a fucking shovel."

The difference is, if you talk with your shovel, you are talking with yourself.

But talking to AI gives you answers and more smart ones, than most humans do. So it is still a tool, but of a very different kind.

And here is where we disagree.

https://en.wikipedia.org/wiki/ELIZA

https://en.wikipedia.org/wiki/ELIZA_effect

We are no further to general artificial intelligence than we were a decade ago.

Thanks, but I don't need to click, that to know what is inside.

And to be honest, a LLM could have give me the same response.

(But I made no claims of AGI btw.)

> And to be honest, a LLM could have give me the same response.

It could, or it could've hallucinated something :)

But then again, I could too, if I smoked enough or fell on my head.

Plus it would've produced more CO2 than I did, hopefully :)

> if I smoked enough or fell on my head.

Did it hurt, you know, when you fell?

The problem here is you're complaining about cult members, then acting like one of the anthrocentric cult members yourself. I agree that we should build a human centered world, but ignoring our many faults won't get us anywhere.

I disagree that we should build a human centered world.

We already did that and it's hell for a myriad of other lifeforms.

In between some old family history and recent US politics, I think there are other things I'd rather reserve the weighty word "cult" for... However, should it arise, one of the features that might convince me is this:

In the name of "loyalty" or "faith" cults require members to burn their bridges, actively cutting off their own potential to escape to any other social support network. That may mean creating enemies out of former associates, humiliating rituals or blackmail material, or simply ruining their reputations through obvious lies.

I don't particularly care about the US or US politics since 2016.

Unless you invade a country again and we have to deal with the Fallout for years to come, that is.

For example: I have banned all news about Trump administration from my home.

It's simply not interesting. He is a toddler, and I have a toddler of my own.

I think I did quite enough to be vague and oblique on that context, so that it wasn't the focus, and any reader could avoid the topic... if they chose to.

What the leader of the free world says or does is definitely interesting to us.

Not to me. He turns around and changes his opinion more often than his underwear.

And he is not the leader of the free world.

Not since they bombed Vietnam.

Maybe a random employees mildly interesting blog post is not exactly where we need to look for a psyop. But that is maybe what they want you to think.

Gotta pump those numbers up. Those are rookie numbers in this racket.

I myself, I pump my investments at least twice a day. Once in the morning, right after I work out. And then once right after lunch.

I want to, that's not why I do it. I do it cause I fuckin' need to.

Most are. Some are paid for.

I'm not saying AI isn't a good tool. However the less you understand what you're using and what you're doing the further you stand to geopardize the business you're working for.

> Claude gave me free, unlimited iteration, unbothered when I changed my mind for the 50th time or asked for a small tweak

Do you not pay for Claude?

> free, unlimited iteration, unbothered when I changed my mind

I think they mean that specifically in working with 3rd party per-project / freelance designers you usually get a "first draft + one adjustment" price, then every modification costs more. Similar for small design shops. Prices aren't necessarily per hour, as you'd get from developers.

Free with an easy monthly payment of $20!

When you are used to ordering humans around that are paid a salary measured in tens of thousands $20 seems like nothing in comparison.

Yeah, for people that work in orgs that are < 150 people. For others it pay by token (API pricing).

20 dollars for this is practically free.

50 iterations on the Pro plan? You kidding?

50 iterations of CSS / layout? Easy, not even pushing it. A freelancer will cuss you out after 3-4 rounds of re-doing everything, but an LLM is happy to keep generating.

Free as in creative freedom without manual effort, not price.

Slightly related: I was in an interview once where it was the CEO, lead dev, and lead designer and inevitable "What are your weaknesses?" question came up. I answered honestly, which was that not only am I really bad at design, I also have issues extrapolating for design systems. It's really hard for me to land on something I think looks okay and in that process almost inevitably always makes it worse. The designer interviewing me took this personally and laid into me about it.

It's not the first time, either. They didn't like the non-stop questions about how things should look and really wanted it to be a one-and-done type of handoff. Even at marketing and advertising agencies, I was fighting with them to give me samples of how things not in their design spec should look. I'm not saying I was right, but that's just a huge Achilles heal for me.

So when someone says

> free, unlimited iteration, unbothered

That's immediately what comes to mind. Not necessarily money, but time and patience. Bolt (which is the tool I use for protyping) never gets mad me. It might not produce the best designs, but they are miles ahead of what I'm capable of. When I'm done, I'll have a real designer make it look better, but until then I don't have to worry about pissing someone off.

The benefit here is designers learning to code. It was always weird to me that designers were shaping software without knowing how it was built. I'm a designer btw.

However, designing in code is technology-first. One could argue that the purpose of design - to shape the artifacts for human purpose - is better done NOT starting with the strict rules of code. Pen and paper is still hard to beat, not for anything that looks nice, but for helping your mind forward.

I've been a full stack and frontend focused engineer for six years and got sick of writing code by hand. Moved to design. Now since I can code with my voice basically I'm getting back into vibe coding and building products. And it's awesome. My bosses still trying to figure out the new situation though, i think the old school separation of roles is starting to die.Being on the intersection I think is the best place to be right now. I feel like my whole life I've been preparing for this moment.

> without knowing how it was built

It helps to understand the constraints of a medium, but you really don't need to know every level down to the electrons moving through the silicon.

Certainly, it helps the architect to know the constraints of concrete and bricks, but you don’t really have to know every level of down to the chemistry.

LLM usually make you forget coding, it doubt it's good for learning if you use in this way. For a designer it would be similar to Figma where he see the result and can edit it using language instead of visual editor

> The benefit here is designers learning to code.

Designers aren't learning to code.

My wife works as a product manager in a FAANG and her team has leaned extremely heavily in using AI to vibe-code some pieces of software that they would have done on Word, Excel or similar otherwise.

They're not learning to code, they don't even look at the code a single second.

Generalising sure feels good doesn’t it?

You need designers that have worked closely with engineers and have their head screwed on.

Of course but sometimes designers like architects design something that can’t easily be built.

But then you „design like software developers”.

What's wrong with a good cli?

My mum doesn't know how to use a cli.

having an llm produce code isn't learning how to code, it's learning how to use a tool to produce code

maybe that doesn't matter though, I suspect many developers will no longer look at all the code they produce either

Many nuances and “it depends” here in my experience. Is learning git part of “learning to code”? Some learn, others don’t.

Of course hammering away prompts aren’t learning at all.

indeed, I know some great developers that use git but haven't ever learned it

I’ve been using Claude Design for my front ends. The output looks and feels good enough, but the designs often look very similar and generally adhere to contemporary web tropes.

Keen to hear if anyone has had unconventional creative adventures with it.

I've had that experience and I've started testing different prompts and inputs.

I find it funny about meeting requirements when you give them, and making safe choices when you don't give direction. So if you're going to rate the output aesthetics and UX/content, but you don't prompt especially much around the aesthetics, you're only getting the safe assumed defaults. It's good at making bootstrap/tailwind clone designs unless you work that angle. For simple web pages, I've started making this the only focus for initial iteration.

any tips for design/aesthetics prompts?

Most applications don't need unconventional creativity though.

Most applications are years long projects that already have styling and code structure done by humans so if the mock up is not perfectly aligned it doesn't even matter because when you finally approve the design and get to building it; that's where the pixel perfect tweaking comes in. And again if it's a mature code base with an existing stylesheet it tends to come out with all the expectations you'd have of it because it's re-using components that already exist 99% of the time.

Same, you can instruct it specifically to look non-standard and give it examples of website styles I want. After some wrangling it feels a bit more creative but takes prompting.

Do you have any like dyes or work clothes describing this process?

I don’t know what prompted to get it away from the base model and any of like the non-standard web design like styles are a little bit too harsh for me if that makes sense. Like for example I like brutalist design, but it just feels heavy sometimes on the apps that I’m making.

I’ve tried to get the AI to describe a style based on the product name or you know it seem that I wanna have for example travel. But then it creates us like steal, amorphic design where everything looks like a boarding pass airplane ticket.

I use claude design too. It has been suggested to me by some very respected and experienced designers which now prototype almost exclusively in claude and then when happy refine in figma.

By the way, you can always tune your prompts to not be generic, if you ask for generic UIs without detailed styling prompts you will get generic designs.

But then how do they get it back out from Figma and make it live?

It would seem a circuitous process and I'd suggest another workflow, but Claude Design can ingest Figma files.

That was never a designer's concern?

By the way figma has a decent mcp that you can connect your LLMs to and extract the design tokens from.

I’ve done a few different things, some different presentations, web mockups etc. They all look more or less identical out of the box, and in every single case of a presentation, Claude Design has zero concept of layout boundaries, happily making slides that expand 200% or more out of the visible viewport (I have a lot of content and it just can’t figure out nice ways of presenting it).

There’s still value in it for me, I get decent enough output to convey my intent and I sometimes manually tweak the HTML.

Defining fonts is a good way to at least not get the same typography as everyone else.

Sort of, I've given it examples of unconventional UI's and then had it sort of create a mashup of them and it's been decent. But I feel like that's cheating.

>>> prototypes are living proposal docs, the code is disposable, and a reviewer’s job is to give feedback about the design and user experience. Eventually, reviewers still take over the idea and implement it in a separate feature, referencing the prototype but owning the production code

That’s solves an issue I have with all POC - a really good approach

The article does not come from someone who relies of Figma for a living. It's easy to call it a "proposal doc" when you're working on a specific issue for a specific product. There are still millions of designers who use Figma to define and maintain design systems that span across products and platforms, where Figma is the source of truth.

> workflow improvements that would have taken days or weeks of engineering

It's a nice article and good point but I feel "design" in the title is misleading - the example given has an extremely reduced visual or spatial scope (something models are still not good at). The post is more about rapid prototyping.

I use the same approach a lot. Before AI I also did this manually. First sit down with a user and just paper and pencil, then hack together a frontend POC / demo, have them play with it and adjust until it works as they wanted.

For me building a quick (not production quality) frontend demo in code was already often faster than getting the right interaction working in Figma. And it allowed to make it fully interactive so you can catch much more edge cases on the UX side.

Now with Claude Code it's even faster to build the throw away prototype. But not a huge difference since discussing with the users and thinking about how it should work is 80% of the time. Claude maybe halves the other 20% compared to quickly doing it yourself. Faster to first version, slower to iterate if it didn't fully get it.

We are doing this on my team (I am the frontend engineer) and honestly I really miss the old way of doing things.

Written specifications are being reduced in favor of these working prototypes, and now there’s this extra cognitive burden of reading the code and trying to determine what were the intended changes, and what’s the slop that needs to be tossed aside.

We also have to figure out, should we take over this generated PR and make any needed changes? Or do we start over from scratch? There’s often a sense of friction either way.

There have been times where a bunch of unintended changes were generated and I took time to port them over on my reimplementation, and then later on it’s “oops! Sorry! We didn’t mean to change that.”

I get it’s empowering but it does take away from some of the joy I used to find in my work and replaced it with some headaches.

I am in a similar boat. Design and product use Claude to vibe design/code a feature/experience and rapidly prototype it, getting it in front of customers to get feedback with minimal engineering time. Amazing! However, you might be surprised to find out it hasn’t really helped us ship stuff faster overall.

The reason, I believe, is we’ve lost something along the way. Thinking. A non-trivial amount of which is now outsourced to a language model. It paints over the cracks in the prompt, hallucinates how things should work when unspecified, what would normally make someone stop and say “this isn’t quite working”, “how should I communicate this idea” or “what happens when…” has gone. Now, these details are left for after it’s been built proper.

Sure, we can improve the process and reflect more on how to utilise this new technique … but is it better than how things used to be? Yeah nah

I did this before AI though. I'd sometimes just build mockups directly in React using real components because it was quick and easy to put a form together with existing UI elements. I remember one project where the whole team was waiting on designs and I just came into stand up and was like "I built this yesterday. Is this what we wanted?"

My experience has been there’s more “what did it make and does it work?” overhead. It’s like a junior developer throwing stuff over the wall and I’m responsible for seeing if it sticks.

> So why are you looking at this code?

Because I am getting the call to fix it when it breaks. I don't have to fix assembly by hand because compilers are deterministic and I have maybe encountered a single real compiler bug in my whole career. Compilers have earned my trust. LLMs are eroding that trust more and more every day I work with them. I encounter LLM-created problems in basically every single diff they surface for me, just over the months the diffs are getting bigger and harder to review and uncover the problems.

LLMs are not an abstraction(not even a bad one) because by design what they are doing is disambiguation. Compilers are not doing that, what you put IN the compiler has to be unambiguous in the first place.

Disambiguation is not a functionality of an abstraction layer. A good abstraction layer is the one I don't have to understand and can trust, if I have to understand its inner workings to use it it ceases to be an abstraction. Except with LLMs you can't even do that, they are a black box you can have no hope of understanding.

And it is not to say LLMs and agentic coding tools are not useful, they are absolutely very useful. They are just not an abstraction layer.

> We have pushed up the abstraction layer.

That's not what "abstraction" means. You wouldn't hire a designer and then call their work an "abstraction", would you?

It's something, but "abstraction" it aint.

Good engineers should understand what goes on underneath them in the stack (at decreasing accuracy probably the more layers away it is) if they care about their craft and the quality of it, even if not in perfect detail, if you're just acknowledging that you've never even tried, then perfect! The AI "revolution" is just right for you.

your two statements can be true at the same time: I do not need to look at the code because I know exactly what it does.

do I care for every snippet? every call's signature? no I do not.

do I understand what it does 100%? yes, because I directed it to be built like that.

I don't get people like you. "care about their craft" - what craft? my job is to make ideas into reality, how I get there is irrelevant. this is what I get paid for and this is what gets me satisfaction.

I've always disliked spending weeks arguing with people about every little detail and having an ideaological war. From the end output most of the decisions that people who "care about their craft" care about are utterly irrelevant.

I catch so much shit when I read the code. I’ll take this into consideration when I’m no longer catching poorly made slop all the time.

Even for the large products, figma is not the starting point for new concepts anymore. I start with a quick prototype on dev environment and then share it with designer for further improvements in figma or in the app itself. With every new model or agent improvement, going back to figma for polishing the ui is decllinig. If we can find a way to keep the frontend code static templates without complex logic, need for this polishing in figma will go away completey as llms can understand it one context window. With the modern frameworks designed for client side rendering, keeping everything in one context is still tricky.

I use LLMs to design things and build wireframes. Product people can actually play with the wireframes and it's trivial to implement changes. And same LLM generated files can be used to guide the LLM to build the actual pages too.

At work we are now in the process of migrating away from Figma. We had spend years perfecting our Figma based design workflow. Currently we are moving all the designs into the code itself using Storybook. The gap currently is reviews and feedback which is addressed by Chromatic now.

You should note that Claude Design is most likely a DPO->PPO->Actor-Critic bootstrap play: https://arxiv.org/abs/2305.18290 / https://en.wikipedia.org/wiki/Proximal_policy_optimization / https://spinningup.openai.com/en/latest/algorithms/sac.html

It's much harder to RL out design taste because it's not self-grounding, and human labelers have no real skin in the game, so this (having a human with a vested outcome in the process directing a model's work) is the best way to get LLMs better at design/"taste"/aesthetic judgment themselves. We were working on the same thing 7 months ago and then I realized that winning over designers to do this would be a huge uphill battle setting up an inevitable fall from grace later on.

What makes me most suspicious of Claude Design is that when you disconnect and reconnect later, it loses context and nags you that the product doesn't work like that. Bullshit. It's at best an anti-abuse/implementation detail (to keep you from launching 10 at once and coming back to them later) or product shortcoming that just so happens to be optimized for keeping you from continuing your design in better tools than theirs for the inevitable followups.

It's great for one shots and it makes sense when you're trying to build a vertical product development stack like Anthropic but I'm disappointed it feels more like a tool optimized for keeping you in their product than for what you're working on. If a company other than Anthropic had shipped this - it's not that hard to build a visual self-eval loop, just use Chrome Devtools Protocol to run headless chrome and take screenshots -> feed into a judge LLM for feedback -> continue - I don't think it would really have seen much adoption.

That said, AI trained on Actor-Critic with a tight human feedback loop definitely seems like the right approach to solving the problem, just not something I want to spend my time training for someone else unless I can do so with higher "entropy" ie high parallelism/optionality

Where does the article mention Claude Design? It seems to me the author is using LLMs as a tool for iteration, given he is a designer.

Also, you're mentioning a lot of unrelated tech. DPO, PPO, actor-critic, visual self-eval loops, Anthropic's "vertical product development stack" may be interesting, but they are mostly orthogonal. The article's point is simply that a designer can now turn design proposals into working prototypes faster than with Figma.

Also, you mention what seems to be a random product bug about disconnect and reconnect that doesn't have anything to do with this workflow. It seems to me that you're post-rationalising some insights that are not really there.

Good to think things through and in public, not discouraging it. I hope this reads as constructive.

Sounds like desk strat RAD work is moving to LLM gen code at JS. My recentish experience of that kind of work has been Athena at JPMC and Quartz at BoA; both Python with functional style via DAG or pixie with py ui framework to match. Which enables quick dev of the parts of trading workflow that don't need to be quick, like booking tools or EOD risk. I know first hand Athena and Qz are crufty when you get into the weeds. The bonsai framework with Elm inspired ocaml impl sounds v cool. So I can see how this approach can accelerate a lot of trading tech dev. But does it have any traction over the hard problems where we turn to C++ or Rust: near real pricing and risk across multiple instruments and markets?

Figma make and gpt designer have a bunch of catching up to do. I couldn’t even import our brand guidelines into make which is already a .fig like what are we even doing here, guys? CD crunches through ungodly amount of tokens and is really slow on iteration but at least you can get some really nice prototypes extremely quickly there. GPT beats any Anthropic models on illustrations so they really should get a grip on multimodal. Overall, it seems like we’re still super early but you can already see glimpses of what may come

Claude is pretty great at designing certain images. For favicons, logos, og cards, it does extremely well. For full image generation, I go elsewhere.

I worry about Figma stock, I know some who bought during the IPO who are now underwater. Figma launched their own design agent but not sure how well that's doing.

> I know some who bought during the IPO who are now underwater

Yeah you don't say. High of $124, currently $22. But hey: that's ~~gambling~~ stock trading for you.

https://au.finance.yahoo.com/quote/FIG/

No sympathy from me. I just wish it happened more to people who overpay for stuff like houses or Tesla stock.

> I just wish it happened more to people who overpay for stuff like houses or Tesla stock

That's pretty mean. I disagree with a lot of people on their investment choices and evangelism. That doesn't mean I want them to suffer for it.

It’s not that I want them to suffer, it’s that them being rewarded incentivizes suboptimal behavior and outcomes. Markets don’t work anymore. Which results in even more suffering.

> them being rewarded incentivizes suboptimal behavior and outcomes

What if they're choosing correctly? Like, I've been pretty consistently critical of crypto. Yet I'm glad my index funds have to buy Coinbase.

Their efforts at AI have been really sad to see. They tried making an Everything Bagel and seem to have hit a wall, hard.

It's a shame because if they'd taken an iterative approach of automating various parts of a normal Figma workflow to speed things up for users, that would have helped them discover where the value was; lots of little ideas, failing fast, testing and updating.

Maybe they just got too big and lost their mojo.

QQ is your insight from first-hand experience using it in an enterprise production environment? If not, then how did you get to this realization?

amyone know how to use claude design more effectively I always alhave a feeling I use a slot machine

from 6 sessions and 5 projects only one template that I choose anything else is really really bad

Same here. I mostly use Figma for logos and random assets now.

i gave claude code my design system that i built in figma and haven't opened it again. it's much faster designing with your voice.

I use Claude code a lot for design too but it just does a lot of regurgitation in design too

Even if this is ad only - are we really ready for a rug pull from Anthropic? Maybe I’m completely unaware in this tools space, but I feel like it’s last tool that’s worth (and not pricey)…

For SVG and html/css generation?

When they paywall hard, I’ll use a local model on my laptop processor instead,

or phone,

and wait a few hours as needed.

For design tools and website builders tough times ahead. Wix for example lay down 20% of staff in some countries. All due to “optimization” with LLM.

Klankers will fix everything. Right?

I'm my work as an FDE this week, Copilot did the initial UI. Feedback was given and tells were adjusted all through prompting.

honestly, for me, chatgpt has more replaced dribbble than it has figma.

where i'd normally spend hours combing through dribbble looking for inspiration for layouts for specific components (most of the time finding nothing), now I use chatgpt to come up with a number of different designs, then port them over to figma.

most designs produced by cgpt arent production-ready, especially for mobile. figma allows me to set proper constraints (screen size, for example), that give it a more grounded "shape"

for that reason, the actual final design is still by hand for now. however, the translation from design to implementation is greatly sped up by codex, which basically does it pixel-perfect.

all the same, still lots of tweaks needed before the final implementation is ready. design to code still has a bunch of issues that often need figuring out/standardising - font sizes, weights, etc.

this is on mobile btw, where space is very limited. havent worked on a website in a while, but i'd imagine the extra space would allow for far more liberty. i do not miss having to craft ten different designs just to ensure responsiveness. massive pita.

I don't see how a coding model competes with figma TBH, an image model maybe but that's a stretch too.

You aren't designing.

Is it just me or the bar to publish janestreet blogposts has been lowered recently?

true it is much more easier using claude design rather than Figma yet it does not produce the same output quality.

They are not using design. They vibe code the feature.

I still prefer Figma for collaboration

And how much of these designs are used in the end compared to when they where done with Figma?

Claud design burns lots of tokens

Yea I mean okay JaneStreet. World wide renowned to be a tech design powerhouse...

> Oh no, Figma ER was actually positive, release mode SaaS FUD

Honestly, I'm not really pro or anti llm and I think there are a ton of limitations for using it to generate code, but UI has been probably the only thing I've been able to vibe code. It helps that I've done a lot of UI work over the years, but I think the combination of defects being easily visible through normal usage, the UI being a non-critical component of a system (bugs don't cause vulns or data corruption (usually), combined with the amount of churn that UI's see, make it a somewhat uniquely good candidate for vibe coding. Also a lot of UI toolkits are declarative, and I think language models do much better with declarative code.

In a way it's not much different from copy-pasting components from templates or whatever, just with more customisability. And for stuff that isn't HTML-based like React it does worse. It's also not great at building component libraries, I still write those myself with little LLM involvement, but that makes sense because the architecture is actually relevant with that, unlike generating CSS and xml-derived components, which is mostly just declarative templating anyways.

I've had decent success writing the core logic myself and then delegating the UI to AI. I think if I didn't write the core logic it would not work very well, but since it's designed well by myself the AI has a much smaller scope to work in which constrains it enough where vibe coding works. Pretty cool.

> Having joined Jane Street this past summer, I’m finding AI support indispensable. There’s just so much that’s new to me, and so much I’m not good at yet, like OCaml and Bonsai.

Using AI for things you aren't good at, or not experienced with, is literally the worst way to use AI. You WANT to struggle when learning a new language, and use reliable documentation to solve your problems, not circumvent them entirely by using AI.

This is extreme incompetence, I'm shocked that Jane Street would advertise it.

They apparently pressure their new hires to blog and talk their book. It happens a lot in U.S. corporations.

Great story.

codex can do UI well if you know what you are doing.

Add a detail on how, and you’re contributing!

"hey codex make me a nice UI" not enough for you ?