Hacker News

Favorites Setup
Comment by tomaskafka | original | What thousands of conversations look like inside a language model
[−]tomaskafka · 2026-11-15 Sun 16:59 UTC · link
I have played with similar problem in different domain, and if you could have “which users play which games” (or in general “which articles are read by which people”), you can do really good similarity search and self organizing map based on no content at all, just the metadata.

Which is of course why Facebook can say they don’t read your conversation content, while still be able to target ads precisely based on conversion metadata.