Writing
Notes on the hard parts
Short, specific write-ups of problems I actually hit — and how I reasoned about them. Quality over cadence.
24 Jun 2026Coverage is the ceiling: what actually moved my retrieval numbersI tried the famous RAG retrieval upgrades — MMR, RAG-fusion, HyDE, multi-query, a per-source diversity cap. Most did nothing; one made things worse. What actually worked, and why only measurement could tell.7 min18 Apr 2026Making Arabic search actually find thingsWhy a naïve query misses most of its matches in Arabic text, and how diacritic-insensitive search + a client-side mirror fixes it without slowing down.6 min10 Feb 2026A translation pipeline that survives crashesTranslating tens of thousands of passages with an LLM means long, flaky, expensive runs. Here's the checkpointing and quality-gating that makes it safe.5 min
More as I go — I write these when there's a specific problem worth explaining, not on a schedule.