I assumed you could measure LLM citations by watching server logs. Our experiment showed otherwise: ChatGPT and Perplexity often cite pages without fetching them, instead serving from a global cache.

We ran this on Vercel/Next.js middleware (before the edge cache) to rule out local caching—browser requests log normally, but many citations never appear.

This doesn’t mean measurement is impossible, but the “citation = visit” assumption doesn’t always hold. Curious if others have observed similar patterns.

Have been using this for a while. Yep, stupidly simple and super super useful! Thank you

Thank you! Thanks for your support and glad to see you onboard!

The recent project from jina AI was a clone of this idea?

https://jina.ai/reader/

So is this like dspy, but has a very specific user flow I.e chat

I think DSPy is more a framework to build LLM programs; this is more of chat functionality as a service.

Nice. Not sure how many people would need a service like this to make it financially viable for you to maintain though. Also noticed a bug: not getting verify email

True! Hm, well you didn't receive it till now? Will check it out.