Field notes — essays & research notes

Things I've written down.

Ruby, Rails, performance, security and applied machine learning. Updated when something feels finished.

5 posts in LLM & Agents
LLM & AGENTS 10 / 20 / 26

Temperature is not a creativity dial

Temperature, top-k and top-p are three different operations on one probability distribution. Treat them as vibes and you'll tune the wrong one. Watch them act on a model small enough to see.

3 min
LLM & AGENTS 09 / 24 / 26

Your RAG demo is lying to you

Every shortcut you take to make retrieval cheap — a smaller model, an approximation, a reduced dimension — can invent failures the real system doesn't have. Check the behaviour you're about to teach or ship.

3 min
LLM & AGENTS 08 / 15 / 26

pgvector or a dedicated vector database?

For most applications the answer is the database you already run, and the threshold where that stops being true is higher than the marketing suggests.

3 min
LLM & AGENTS 06 / 27 / 26

Chunking is a retrieval decision, not preprocessing

How you split documents determines what is findable. Everything downstream inherits that choice, and almost nobody measures it.

3 min
LLM & AGENTS 02 / 09 / 26

Your RAG chatbot doesn't have a model problem

It has a measurement problem. Why swapping the model is the last thing to try, what to instrument first, and how an aggregate score hides the failure that matters.

4 min