Hi! I'm the dev here! I built this on a whim at after seeing someone ask for it on twitter. It was 12:30 at night but I couldn't pass down the opportunity to build it.
The code is very simple, there's no backend at all actually, I believe because wikipedia's api is very permissive and you can just make the requests in the frontend. So you just simply request random articles, get some snippets, and the image attached!
I used Claude and cursor do 90% of the heavy lifting, so I am positive there's plenty of room for optimizations. But right now as it stands, it's quite fun to play with, even without anything very sophisticated.
Wonder what it would take to add a simple algorithm to this. Part of what makes short media apps (dangerously) addictive is that they eventually learn what you like and feed you more of that. An app like this with such an algo could help with the stickiness (and presumably get us away from the other apps at least for a little bit). "Oh this person likes science stuff, let's feed them more, oh they specifically like stuff related to quantum mechanics, let's place a summary paragraph from a related page topic in there."
Awesome. I have a project with a similar tik-tok-esque philosophy for serving all sorts of noncommercial content from the web. The interface is one button and a random page is embedded in an iframe. I use random wikipedia pages as a fallback in case my algorithm returns a dead page.
I like the idea, but one thing about Wikipedia is that with technical or granular topics it approaches things in a focused way. A specific molecular biology term's page isn't there to explain exactly how it fits into a larger biology topic. It makes random pages difficult to glean information from.
Even wikipedia articles I understand, more on computer topics, fall into the category of "the only people who understand this page are people who ... already understand it / don't need to read this".
Granted sometimes the social media context is kinda opaque, but usually "man fall down it funny" is pretty universal.
This, plus an AI generated voice reading a TikTok-creator style catchy summary, plus TikTok's actual algorithm for surfacing content would actually make a decent app I believe.
EDIT: Also the name should be WikTok instead of WikiTok.
aizk ·12 days ago
The code is very simple, there's no backend at all actually, I believe because wikipedia's api is very permissive and you can just make the requests in the frontend. So you just simply request random articles, get some snippets, and the image attached!
I used Claude and cursor do 90% of the heavy lifting, so I am positive there's plenty of room for optimizations. But right now as it stands, it's quite fun to play with, even without anything very sophisticated.
Here is the source code. https://github.com/IsaacGemal/wikitok
Show replies
xhrpost ·12 days ago
Show replies
ya1sec ·12 days ago
I call it moonjump: https://moonjump.app/
Show replies
duxup ·12 days ago
Even wikipedia articles I understand, more on computer topics, fall into the category of "the only people who understand this page are people who ... already understand it / don't need to read this".
Granted sometimes the social media context is kinda opaque, but usually "man fall down it funny" is pretty universal.
Show replies
doctoboggan ·12 days ago
EDIT: Also the name should be WikTok instead of WikiTok.
Show replies