Chaoran Huang
Systems, machine learning, and the web — written up carefully.
Notes
Series · NLP
From One-Hot to BERT
How NLP learned to represent meaning — from one-hot vectors to contextual embeddings.
Series · LLMs
From Representation to Behavior
The roadmap from a pre-trained transformer to an aligned, reasoning assistant.
Note · Systems
Bits, Math, Hashes, Streams
Bit operations, modular arithmetic, hashing, and streams — rebuilt from first principles.
Recent work
Effect-TS/effect
Build production-ready applications in TypeScript
TypeScript
All contributions
