Vibe Check — Devlog 🍓
well…
there was a pretty big plot twist.
the original plan was to ship Vibe Check as a Chrome extension.
everything was already built around that idea.
popup UI.
chrome APIs.
extension architecture.
the whole thing.
then i found out Google wants a $5 one-time fee just to publish an extension.
and honestly…
i was NOT about to pay $5 just so my little prompt tool could exist on the Chrome Web Store 😭
so…
i scrapped the entire extension idea.
which meant i had to redesign…
basically everything.
the whole app was originally designed around a tiny popup window.
now it had to become a full webpage.
different layout.
different navigation.
different spacing.
different interactions.
pretty much every screen got rewritten from scratch.
the funny part is that none of the actual features changed.
they just had to be rebuilt in a way that actually made sense on a full website.
while rebuilding everything i also decided to add a feature i honestly wish more AI tools had.
Token Saver :3
after Vibe Check analyzes and improves your prompt…
it can now convert the final prompt into Chinese.
before anyone asks…
no, this isn’t some weird translation gimmick 😭
the reason is actually pretty simple.
Chinese is far more information-dense than English, so the same instructions usually require significantly fewer input tokens.
that means:
- lower API costs
- fewer prompt tokens
- more room inside the context window
without changing what the prompt is actually asking.
the AI still understands exactly the same instructions.
if you want the response in English, you can literally just add:
“Respond in English, even though my prompt is written in Chinese.”
and it’ll work exactly the same.
so now Vibe Check doesn’t just make prompts better…
it also tries to make them cheaper to run.
which i thought was a pretty neat addition :3
meow
Comments 11
tis lowk a vibecoded wrapper bro im crine
@subhansh idk about stardance, but its just a llm wrapper mostly vibecoded, your endpoints are completely exposed, i found out you have 10 second as your ratelimit i give you that, but you dont have any form of token logging, i have a suspicion youre running a local llm instead of using an api to do this, so props to u for that, but anyone smart enough would just use your endpoints to troll tf out of u, good job on that prompt job tho i couldnt bypass it even after multiple tries, your endpoints and your apis i took full advantage of tho, if you have any form of local logging youll know what im tallking about
i apologize humbly if my assumption was wrong and u were using a cloud ai api to do this.
I just told u all that because i thought if you WERE thinking of making this project a big thing. And as you mentioned your keys are stored in .env, I wanna inform you i dont need to acess your env to exploit your apis, i already have acess to your exposed endpoint i wouldnt waste my time finding the api. Youre absolutely right about the complexity part, Maybe its just me projecting as im tried of seeing people larping about their llm wrapper projects and it just kinda pisses me off.
This is why i stopped doing webdev to be honest, way too many AI spammers out there
it gives its own prompt like a 60/100 even if you pass it through like 10 times 😭
Sign in to join the conversation.