A general guide to matching messy records into governed entities, with blocking, scoring, selective review, clustering, survivorship, and evidence-first reference tables.

Google’s new TurboQuant method compresses key-value cache and search vectors more aggressively by cutting quantization overhead, which could make long-context inference and retrieval cheaper and faster.

A file-level benchmark comparing PDF and Markdown on storage, prep speed, and token estimates, including an image-bearing Grimm fairy tales PDF.

A practical framework for using folders, Markdown, per-project agent contracts, and Obsidian as a durable local context layer.