I’m Chris — a software developer based in London, currently CTO at Searchable. This is my personal blog, where I typically write about programming, search systems and technology.
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.
8-part seriesJun 2026
A series on how consumer search habits are shifting toward AI answers, and what that shift means for the businesses, publishers, and engineers who depend on being found.
Ben Trent and Thomas Veasey shipped another DiskBBQ optimisation today: quantising queries against coarser parent centroids instead of per-document ones. 5x off the quantisation stack with no meaningful recall loss. The insight underneath is that the query path and the document path don’t have to be treated symmetrically.
A new paper out this week shows the per-token hidden states of off-the-shelf single-vector embedders already carry the information needed for ColBERT-style MaxSim - and you can wire it in at inference time, without retraining. The late-interaction deployment barrier I most underestimated just dropped.
Elasticsearch 9.4 adds query_vector_builder.lookup - a tiny API addition that collapses a two-request vector search into one and runs better than 3x faster. A small change with a big impact, and a look at where that ratio actually comes from.
