←back to thread

WikiTok

(wikitok.vercel.app)
1459 points Group_B | 2 comments | | HN request time: 0s | source
Show context
aizk ◴[] No.42936923[source]
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.

Here is the source code. https://github.com/IsaacGemal/wikitok

replies(18): >>42936962 #>>42936974 #>>42937696 #>>42937871 #>>42937989 #>>42938002 #>>42938007 #>>42938164 #>>42938260 #>>42938330 #>>42939286 #>>42939520 #>>42940031 #>>42940626 #>>42942340 #>>42944933 #>>42945717 #>>42947803 #
tomashubelbauer ◴[] No.42938330[source]
Shoutout to APIs that do not enforce CORS preventing requests be made from FE without a need for a BE. There's so many toy apps I started building that would have just worked if this was more common, but they have CORS restrictions requiring me to spin up a BE which for many one-off tools and personal tools just isn't worth doing and maintaining. Same with OAuth.
replies(9): >>42938463 #>>42938484 #>>42938836 #>>42939162 #>>42939366 #>>42939679 #>>42939693 #>>42939990 #>>42944599 #
jumploops ◴[] No.42939162[source]
Shameless plug for Magic Loops -- we run code in isolated MicroVMs and students love our lack of CORS enforcement, as the APIs they build can be easily integrated into their hackathon projects :)
replies(2): >>42940172 #>>42943100 #
1. aizk ◴[] No.42940172[source]
Tell me more?
replies(1): >>42942253 #
2. jumploops ◴[] No.42942253[source]
We built an LLM-based no-code "all-code" tool for non-developers to automate their daily tasks.

Counterintuitively, it's been picking up steam among student developers and professional devs due to how fast you can spin up API endpoints.

We're currently working to build on this momentum, and are now shifting focus to existing devs.

tl;dr - we use LLMs to create APIs that are run in Firecracker-based MicroVMs