[HN Gopher] Show HN: Scroll Wikipedia like TikTok
       ___________________________________________________________________
        
       Show HN: Scroll Wikipedia like TikTok
        
       Hey - I've been playing with LLMs since GPT-2 and recently
       experimented with fully generative UIs where the HTML/Canvas are
       generated just-in-time.  Every post on the feed( on
       slop/duck/storytime) you see is streamed and generated just-in-time
       with HTML and into a Canvas with Gemini 3 Flash.  Comments and DMs
       are bidirectionally linked with a Cloudflare Workers Durable Object
       which is why they feel so fast. Every generated post is saved into
       a DO SQLite which is then served into the "Following" feed so it
       can be served quicker.  This was inspired by Wikitok, a VSCode
       Extension I made around brainrot, and another fully generative UI
       site I made.
        
       Author : sdan
       Score  : 116 points
       Date   : 2026-01-09 18:15 UTC (4 hours ago)
        
 (HTM) web link (quack.sdan.io)
 (TXT) w3m dump (quack.sdan.io)
        
       | xnx wrote:
       | Sounds like WikTok (2023,
       | https://news.ycombinator.com/item?id=42936723) or WikiTok (early
       | 2025, https://news.ycombinator.com/item?id=42936723).
        
         | SirFatty wrote:
         | "This was inspired by Wikitok, a VSCode Extension I made around
         | brainrot, and another fully generative UI site I made."
        
           | xnx wrote:
           | I saw that but got the submitter and commenter names mixed
           | up, so I didn't realize it was the same person.
        
           | aizk wrote:
           | :)
        
           | mellosouls wrote:
           | I also thought immediately of WikiTok and was confused by
           | this exchange and the grammar in the quote here; I thought
           | they were claiming to have made a VSCode extension called
           | Wikitok. I understand now!
        
       | personjerry wrote:
       | The animations + audio are great. I feel like these meaningfully
       | differentiate from some other similar projects. There's a lot of
       | potential here.
        
       | furyofantares wrote:
       | Reading it with sound off is really hard because of the way the
       | words come up one at a time, rather than the whole sentence at
       | once.
        
       | recallingmemory wrote:
       | Neat idea, and love the Undertale menu mp3: https://brainrot-
       | vscode-ext.sdan.io/quack/music/undertale-me...
        
       | ram_rattle wrote:
       | Looks super cool
        
       | emsign wrote:
       | Nice tech demo but in practice utterly annoying and without
       | purpose. I mean don't you think enshitifying Wiki knowledge kind
       | of beats the purpose of acquiring knowledge?
        
         | odie5533 wrote:
         | It's a proof of concept to pave the way. I could see benefit in
         | having series which deep dive into material. This felt too
         | shallow to me.
        
       | Edmond wrote:
       | Work related versions of this, expense report:
       | 
       | https://youtu.be/h0Bg-lqNlkU
       | 
       | In general Just-In-Time app generation is a bad idea. The right
       | approach is to create human-in-loop tools that a bot would
       | recognize and invoke as needed, of course the human-in-loop tool
       | would itself be AI generated.
       | 
       | Example of human-in-loop tool in use:
       | 
       | https://youtu.be/srG5Ze7mS7s
        
       | lukebechtel wrote:
       | Honestly, pretty cool.
        
       | kerisi wrote:
       | you can use LTX to generate the videos, this video took 15s on a
       | 4090
       | 
       | https://vimeo.com/1152992073?share=copy&fl=sv&fe=ci
        
         | sdan wrote:
         | nice did you make this just for the comment? haha
        
       | vedmakk wrote:
       | This is really cool. I'm interested in the GenUI part. Is the web
       | app itself static and the stories are generated on-demand?
       | 
       | Do you give gemini some UI components/templates to build with or
       | is it just prompting to get consistent results across multiple
       | stories?
        
         | pests wrote:
         | Google AI Studio has a Gallery[0] with some similar apps. It's
         | an editor so you can view the code, they are usually react apps
         | with gemini integration via genai package. Like this one
         | here[1] is similar. It generates interesting stories to share
         | about a route you are driving / walking / biking along. This is
         | one of the pre-made examples I believe, I didn't make it or
         | anything. Just to show some how some of this might work.
         | 
         | [0]
         | https://aistudio.google.com/apps?source=showcase&showcaseTag...
         | 
         | [1]
         | https://aistudio.google.com/apps/bundled/echo_paths?showPrev...
        
         | sdan wrote:
         | Yes I have base css/js that I inject on top of whatever codegen
         | gemini 3 comes back with -- It runs via ai-sdk so the specific
         | function is streamObject which is prompted to generate inner
         | HTML elements
        
       | nseth wrote:
       | Another sick Surya project, well done dude!
       | 
       | [Neall]
        
         | sdan wrote:
         | thanks
        
       | aizk wrote:
       | Hi there, creator of Wikitok here! Very happy to hear that my
       | random little project inspired you :) The attention to detail in
       | the UI is good - I'm so over every default AI generated UI being
       | rounded corners, centered divs, blue and purple gradients, etc.
       | Nice work.
        
         | sdan wrote:
         | Thanks! Half of the work here was getting gemini to generate
         | reasonable canvas animations within the window. I'm still
         | experimenting which "style" I should keep/add
        
       | cons0le wrote:
       | This is amazing! I think this could actually catch on!
       | 
       | Plz give an easy way to follow some tags so it's not showing me
       | football stuff. If it was just topics I was interested in, I
       | could scroll this for hours.
        
         | sdan wrote:
         | Huge- good to hear will see if I can add a way to type in what
         | you want or to go dig further into just certain hashtags.
        
       | bstsb wrote:
       | wow, my attention span is terrible - the first time i tried
       | watching a generated video, i instinctively held the right side
       | of the screen to speed it up to 2x...
       | 
       | is there scope for allowing users to search for / ask about
       | specific topics? although then you do have to think about
       | security issues with prompt injection
        
       | cornonthecobra wrote:
       | The caption highlight timing is very inaccurate. It looks like it
       | just steps through each word on a fixed timer, rather than using
       | timing information from the TTS engine?
        
         | sdan wrote:
         | Yes just fixed timer, and using browser TTS nothing fancy here
         | on purpose - when I did some research on tiktok videos
         | generally simpler/worse quality seemed to be better XD
        
       | vishnuharidas wrote:
       | Coincidentally, I was vibe-coding a doom-scroller for Hacker News
       | Top Stories today: https://vishnuharidas.github.io/hn-reels/
        
       ___________________________________________________________________
       (page generated 2026-01-09 23:01 UTC)