Show HN: Scroll Wikipedia like TikTok (quack.sdan.io)

330 points by sdan ↗ HN
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.

47 comments

[ 9.0 ms ] story [ 69.2 ms ] thread
(comment deleted)
(comment deleted)
The animations + audio are great. I feel like these meaningfully differentiate from some other similar projects. There's a lot of potential here.
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.
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?
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

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?

Another sick Surya project, well done dude!

[Neall]

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.
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.

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

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?
Very cool! But text moves way too fast
Next step is allow viewing TikTok like wikipedia. Take a bunch of popular tiktok posts, use an LLM to describe what's happening via text/screenshots (with references to memes, etc), and link them to other relevant tiktoks.

Some meme sites might be somewhat similar to this.

Having a generated voice tell me about some historical massacre in a chipper tone with a generated infographic and set to TikTok music was. Especially dystopian.

As an experience I found it nauseating and am never doing it again, but as an art piece I give it high marks. Good job.

Hilarious. The one AI voice is a little too grating for me, but with a little variation I might actually scroll it for a while.
Good. However, on a smaller phone such as Iphone SE the viewport gets cropped all around and I don’t see around 20% of the content.
Note there's a rate limit on generated content for the time being, why you're unable to see any new content on the rest of the feeds. LLMs are expensive!