Posts
All the articles I've posted.
-
Hybrid Search: BM25 and Embeddings Are Better Together
Pure vector search quietly fails on the exact terms, codes, and acronyms users actually type. Combining BM25 with dense retrieval, fusing the two, and paying the latency bill it costs.
-
vLLM, Quantization, and Serving LLMs on a Budget
Self-hosting an open model when GPUs are scarce and finance is reading the bill. Continuous batching, KV-cache, what quantization actually costs you, and when to just call a hosted API instead.
-
Stop Fine-Tuning. Start Retrieving. (Usually.)
A decision framework for RAG versus fine-tuning that is not "it depends." Three questions settle most of it, and the cases where fine-tuning actually wins are narrower than the budget requests suggest.
-
Evals Are the New Unit Tests (And You're Not Writing Them)
Shipping an LLM feature with no evals is shipping with no tests, and almost everyone is doing it. A small, hand-written harness you run on every change, plus the honest limits of grading with another model.