5 articles tagged “Search relevance”.
Qdrant got 5 hyperbolic dimensions to beat 200 Euclidean ones on hierarchical data, and then HNSW returned 0.020 recall on it. The representation win is real and the index can't cash it - because an ANN graph isn't neutral plumbing, it has an opinion about what close means.
Dot product, cosine, Euclidean, Manhattan and Hamming - what each one actually measures, why most of them collapse into the same ranking once your vectors are normalised, and the handful of mistakes that bite in practice.
A small, self-contained experiment on why single-vector retrieval breaks on compound, high-intent queries - and how late interaction keeps two facets intact where a dense embedding averages them away.
The previous post in this series argued the engineering inside an AI answer is recognisable IR. This one looks at the visible end of the pipeline: the citation slot. When the surface is a paragraph with three sources cited, the question "did we get cited?" becomes the new "did we rank #1?".
xAI open-sourced the For You feed algorithm today. Three observations through a search-and-IR lens: two-tower’s quiet dominance, the retrieve/rank split surviving the bitter lesson, and recsys converging with search.
