$ ls ./blog/series

Series, read in order

Each series is one subject told from start to finish. This page remembers what you have read, so you can pick up where you left off.

./series/cach-hoat-dong-cua-llm/in progress

How LLMs Work

A series that goes from the Transformer architecture up to the system layers built on top of it. Each part stands on its own, but reading them in order shows why every concept shows up exactly where it does.

0 / 14 published parts14 parts · ~479 min
nextpart 1 — Transformer from A to Z: Understanding the Foundation of LLMs
./series/decision-model/in progress

Decision Models: When AI Decides Instead of Writes

A series on decision models, a class of models that take a program's state plus questions with a pre-declared answer space and return typed decisions with probabilities instead of generating text. TypeSafe AI's JEV is the running example: from the concept to the mechanics, the ecosystem and a concrete application, always separating what the vendor has published from the blog's own analysis.

0 / 3 published parts4 parts · ~58 min
nextpart 1 — Decision Models: A New Branch Beside Generative LLMs