> 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.
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.
It's also a huge ad for microprocessors. I mean don't people realize we did math before microprocessors? We even had mechanical machines which were much more elegant than these electronic abominations. /s
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'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.
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.
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.
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.
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)…
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 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.
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.
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
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.
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.
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.
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.
Yeah trust wallstreet over regulatory bodies /s
Even if they're not, I'm not sure if we should care a quantitative trading firm's opinions on frontend design...
This is why hn is the best. First comment helps to decide if we need to read the article or not .
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.
I thought we were too anti-AI?
Depends which agent you ask to cherry pick comments for sentiment analysis.
Well, confirmation bias. You see what support your beliefs, ignoring anti AI articles being promoted.
I’m looking for an alternative too..
It's also a huge ad for microprocessors. I mean don't people realize we did math before microprocessors? We even had mechanical machines which were much more elegant than these electronic abominations. /s
It's a cult. And frankly, I am not interested in churches or cults.
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.
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.
You should note that Claude Design is most likely a DPO play: https://arxiv.org/abs/2305.18290
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.
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.
> 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 as in creative freedom without manual effort, not price.
Free with an easy monthly payment of $20!
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.
But then you „design like software developers”.
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 eat shit, I’ll use my laptop processor instead,
or phone,
and wait a few hours as needed.
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.
Why not ask Claude design to write a document fully specifying the prototype?
old way that was clunky, long feedback cycles and gate keeping UI
no thanks. BE boys do FE now
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.
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.
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
I don't see how a coding model competes with figma TBH, an image model maybe but that's a stretch too.
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.
Most applications don't need unconventional creativity though.
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.
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.
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'm my work as an FDE this week, Copilot did the initial UI. Feedback was given and tells were adjusted all through prompting.
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
> Oh no, Figma ER was actually positive, release mode SaaS FUD
Is it just me or the bar to publish janestreet blogposts has been lowered recently?
It is not just you.
This is a very disappointing post from Jane Street.
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.
I use codex
Great story.