Building in public
Journal
Short, dated entries: what I'm building, what broke, and what I learned. Less polished than the articles, closer to the work.
- exploring
Notes on chunking: smaller isn't always better
Spent the afternoon re-running a chunking ablation because a retrieval metric drifted and I wanted to know why. The folklore is "smaller chunks → better recall." That is true right…
- note
An eval harness before the feature
Rule I keep relearning: build the evaluation before the feature, not after. It feels slower. You sit down to add a capability and instead spend the first hour assembling twenty lab…
- reading
Re-reading BM25 in the age of embeddings
Went back to the BM25 literature this week, partly out of nostalgia from my IR research days, partly because a hybrid retriever I'm tuning keeps reminding me how good the old lexic…