Notes
Notes to understand things better, in plain language.
Things I want to understand more deeply, written down simply so I can come back and reread them. They are not meant to be complete or to cover everything; they are a place to reflect and to connect ideas to each other.
Browse by series
0401Search and retrievalHow systems find and rank what is relevant: from classic ranking models to neural retrievers and evaluation, through retrieval-augmented generation (RAG) to search agents.2 published 02Inside LLMsWhat happens between the prompt and the answer: practical notes on reading a model’s internal representations, and what they can and cannot tell us.Work in progress 03Statistics for MLThe statistics that make an experimental result believable: comparing models, quantifying uncertainty, and reporting what we actually found.Work in progress 04Personal reflectionsOccasional, less technical writing about research and doing a PhD.Work in progress