boatbuilder
Re:Measuring LLM citations with server logs might not work as assumed
on Thursday August 28, 2025 @01:08PM (#45054543)
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.
Re:Show HN: I've build a stupidly simple invoicing for freelancers and...
on Wednesday May 01, 2024 @12:19PM (#40225372)
Have been using this for a while. Yep, stupidly simple and super super useful! Thank you
Re:Show HN: I made a tool to clean and convert any webpage to Markdown
on Tuesday April 16, 2024 @12:08AM (#40048257)
The recent project from jina AI was a clone of this idea?
Re:Show HN: Chat-focused RAG with automated memory management
on Saturday February 17, 2024 @07:35AM (#39408883)
So is this like dspy, but has a very specific user flow I.e chat
Re:Show HN: Get notified when your desired Twitter handle is available
on Tuesday January 30, 2024 @11:44PM (#39200032)
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