Starting from the question of what sparse and dense really mean, this works through the embedding pipeline, subwords and vocabularies, input length, and their practical uses.

A game about finding one hundred hidden cats in a still illustration. They come in all shapes and sizes; each one lights up when found and answers with its own soothing meow.

My plain-language explanation of TF-IDF, from terms and tokenization through TF, IDF, query scoring, BM25, and using it to recommend related posts on this blog. Apparently, it is much easier to pay back the debt of skipping NLP lectures once there is a reason to learn it.

Does your Agent keep repeating the same mistake before it finally remembers? A look at gotcha.md: which memories must be fully available as soon as a new session begins, and which can wait to be retrieved later?

Reading notes on How We Use Skills: when you cannot put everything in front of an Agent at once, how do you keep it effective? Progressive Disclosure and Task Decomposition.

memU ADR 0007 overturns the earlier LLM mode: thoughts from a consumer-product developer and emotional-companion perspective.

Starting from a video about blending with the dust, this reflects on Han Li's Dao heart, character writing in A Record of a Mortal's Journey to Immortality, and letting go of the self.

A breakdown of memU focused on its main paths and ADR architecture documents, currently following through ADR 0008.