[HN Gopher] Beyond Text: On-Demand UI Generation for Better Conv...
       ___________________________________________________________________
        
       Beyond Text: On-Demand UI Generation for Better Conversational
       Experiences
        
       Author : fka
       Score  : 68 points
       Date   : 2025-05-16 09:23 UTC (13 hours ago)
        
 (HTM) web link (blog.fka.dev)
 (TXT) w3m dump (blog.fka.dev)
        
       | exe34 wrote:
       | I was hoping to do this over IRC but never got around to
       | implementing it. I hate the idea of implementing a whole
       | website/chat system, when they already exist. I'd like to use it
       | for my (currently in-existent) home automation communication.
        
         | fka wrote:
         | Perfect home automation never exists.
        
       | maxcan wrote:
       | Video isn't loading.
        
         | fka wrote:
         | I think it's because of the video format.
         | 
         | https://x.com/fkadev/status/1923102445799927818?s=46
        
       | casey2 wrote:
       | If it could have been done it would have by now
        
         | fka wrote:
         | You can say this for all kind of inventions and new ideas.
        
         | revskill wrote:
         | Startups fo not have enough efforts to impriove ux, that is why
         | we have jira.
        
       | utku1337 wrote:
       | looks very useful
        
       | joshstrange wrote:
       | Related, it's crazy to me that OpenAI hasn't already done
       | something like this for Deep Research.
       | 
       | After your initial question, it always follows up asking some
       | clarifying questions, but it's completely up to the user to
       | format their responses and I always wonder if people are sloppy
       | if the LLM gets confused. It would make much more sense for
       | OpenAI to break out each question and have a dedicated answer
       | box. That way the user's response can be consistent and there's
       | less of a chance they make a mistake or forget to answer a
       | question.
        
         | fka wrote:
         | OpenAI would implement this within a minute or smth I guess.
        
         | wddlz wrote:
         | Sorry for the shameless plug but, we recently published this
         | research on 'Dynamic Prompt Middleware'
         | (https://www.iandrosos.me/images/chiwork25-27.pdf) as a
         | potential approach for this. Basically, based on the user's
         | prompt (and some other bits of context), we generate UX
         | containing prompt refinements for users to quickly select
         | answers to and do the prompting for the user.
        
           | fka wrote:
           | Didn't read the paper but sounds like a similar idea.
        
           | ics wrote:
           | Very neat paper, thanks for sharing. Being able to interact
           | with a model through, say, Jupyter Notebook in this way would
           | be amazing especially.
        
       | aatd86 wrote:
       | that's not a very innovative idea or even better UX. I think that
       | the future wil have to do with voice commands and mcps will be
       | the backend, exposing capabilities.
        
         | ActionHank wrote:
         | Because we are all going to be in our open planned offices
         | shouting into the void hoping it poops out the app we want?
        
           | aatd86 wrote:
           | because you really think the AI can predict the perfect UX
           | for human consumption out of the blue instead of simply using
           | human made components?
           | 
           | AI or not won't change these sorts of UI too much.
        
         | fka wrote:
         | We don't do most of our jobs with our voice. "Click"
         | interaction is still an important one.
        
           | aatd86 wrote:
           | there is no benefit in it being AI generated though. There is
           | a closed set of interaction behaviors.
           | 
           | When you want to order a pizza, you won't have to click. Just
           | browse and ask the AI assistant to place an order as you
           | would in a restaurant. Better UX.
        
             | fka wrote:
             | Yep, that's why it's "on-demand". With LLMs, you won't need
             | to fill the form, it's an optional interaction makes your
             | UX process better. Please read the post and then comment :)
             | You're possibly commenting on the title.
        
               | aatd86 wrote:
               | No I read the post. I had actually read it before I think
               | even. But I am not convinced by the on demand part.
               | 
               | Isn't on demand what chat llms already do nowadays btw?
               | 
               | point being that generating visual UI components is easy.
               | chatgpt does it. server driven UI does it.
               | 
               | But multimodal interaction is something else that goes
               | further.
        
               | fka wrote:
               | Well, AI might ask you to choose a color. Now, is it
               | better to show a color picker UI or just ask for the
               | name?
               | 
               | You might say naming the color is enough, but in reality,
               | a color picker is the more natural way to interact.
               | 
               | As humans, we don't communicate only through words. Other
               | forms of interaction matter too.
        
               | aatd86 wrote:
               | Yes but the AI is not creating these components from zero
               | is it (on demand part)?
               | 
               | It will probably have access to a list of components with
               | their specifications, especially the type of data that
               | the components allow to mutably (or not) represent.
               | 
               | Or respond to a query from a database by presenting a
               | graph automatically.
               | 
               | But the hard part is to turn natural language into a sql
               | query in my opinion. It's not really the choice of data
               | representation which is heavily informed by the data
               | itself (type and value) and doesn't require much
               | inference.
        
               | fka wrote:
               | I still do think you haven't read the post :D
        
       | ActionHank wrote:
       | I really believe this is the future.
       | 
       | Conversations are error prone and noisy.
       | 
       | UI distills down the mode of interaction into something defined
       | and well understood by both parties.
       | 
       | Humans have been able to speak to each other for a long time, but
       | we fill out forms for anything formal.
        
         | fka wrote:
         | Exactly! LLMs can generate UIs according to user needs. E.g. it
         | can generate simplified or translated ones, on-demand. No need
         | for preset forms or long ones. Just the required ones.
        
         | visarga wrote:
         | > Conversations are error prone and noisy.
         | 
         | I thought you'd say not being able to reload the form at a
         | later time from the same URL is bad. This would be a "quantum
         | UI" slightly different every time you load it.
        
           | ActionHank wrote:
           | I think that there will be ways to achieve this.
           | 
           | If you look at many of the current innovations around working
           | with llms and agents, they are largely around constraining
           | and tracking context in a structured way. There will likely
           | be emergent patterns for these sorts of things over time, I
           | am implementing my own approach for now with hopefully good
           | abstractions to allow future portability.
        
         | aziaziazi wrote:
         | > this is the future
         | 
         | For sure! UIs are also most of the past and present way to
         | interact with a computer, off or online. Even Hacker News -
         | which is mostly text - has some UI for to vote, navigate,
         | flag...
         | 
         | Imagine the mess of a text-field-only interface where you had
         | to type "upvote the upper ActionHank message" or "open the
         | third article' comments on the front page, the one that talks
         | about On-demand UI generation..." then press enter.
         | 
         | Don't get me wrong: LLMs are great and it's fascinating to see
         | experimentations with them. Kudos to the author.
        
       | banga wrote:
       | Semantic clarity of written prose is hard, but this approach
       | seems like making it easier for the machines rather than the
       | other way around.
        
       | jFriedensreich wrote:
       | I was working on exactly this in gpt 3 days and still believe ad
       | hoc generation of super specifc and contextual relevant UIs will
       | solve a lot of problems and friction that purely textual or
       | speech based conversational interfaces pose especially if the UI
       | elements like sliders provide some form of live feedback of their
       | effect and are possible to scroll back to or pin and make changes
       | anytime.
        
         | WillAdams wrote:
         | This always felt like something which the LCARS interface
         | addressed, at least conceptually (though I've never seen an
         | implementation which was more than just a skin).
         | 
         | I'd love to see folks finding the same sort of energy and
         | innovation which was driving early projects such as Momenta and
         | PenPoint and so forth.
        
           | bhj wrote:
           | Yes, there's a video where Michael Okuda (with Adam Savage, I
           | think?) recalls the TNG cast being worried about where to
           | tap, and his response was essentially "you can't press a
           | wrong button".
        
           | jFriedensreich wrote:
           | thanks for bringing this up, totally forgot the connection
           | even though i looked at it before and also remember the adam
           | savage interview
        
       | wddlz wrote:
       | Related to this: Here is some recently published research we did
       | at Microsoft Research on generating UX for prompt refinements
       | based on the user prompt and other context (case study:
       | https://www.iandrosos.me/promptly.html, paper link also in
       | intro).
       | 
       | We found it lowered barriers to providing context to AI, improved
       | user perception of control over AI, and provided users guidance
       | for steering AI interactions.
        
       | sheo wrote:
       | I think that the example in the article is not a good usecase for
       | this technology. It would be better, cheaper and less error prone
       | to have prebuilt forms that LLM can call like tools, at least for
       | things like changing shipping address
       | 
       | Shipping forms usually need verification of addresses, sometimes
       | they even include a map
       | 
       | Especially if on the other end data that would be inputted in
       | this form, would be stored in the traditional DB
       | 
       | Much better usecase would be use it in something, that is dynamic
       | by nature. For example, advanced prompt generator for image
       | generation models (sliders for size of objects in a scene;
       | dropdown menus with variants of backgrounds or style, instead of
       | usual lists)
        
         | cjcenizal wrote:
         | You make a good point! There are many common input
         | configurations that will come up again and again, as forms and
         | other types on input (like maps as you mentioned). How can we
         | solve for that?
         | 
         | Maybe a solution would look like the server expression a more
         | general intent -- "shipping address", and leaving it to the
         | client to determine the best UI component for capturing that
         | information. Then the server will need to do its own validation
         | of the user's input, perhaps asking for confirmation that it
         | understood correctly.
        
       | jmull wrote:
       | This seems much worse than the typical pre-AI mechanism of
       | navigating to and clicking on a "Change Delivery Address" button.
       | 
       | I don't know why you wouldn't develop whatever forms you wanted
       | to support upfront and make them available to the agent (and
       | hopefully provide old-fashioned search). You can still use AI to
       | develop and maintain the forms. Since the output can be used as
       | many times as you want, you can probably use more
       | expensive/capable models to develop the forms rather than
       | cheaper/faster but less capable models that you're probably
       | limited to for customer service.
        
       ___________________________________________________________________
       (page generated 2025-05-16 23:01 UTC)