A thread you can test
Data Structures Inside the LLM
2 notes move from the word to a real choice at work — understand it first, then decide whether to use it.
Each note stands alone, or becomes the next step in this thread.
THE QUESTION THIS PAGE ANSWERS
ANSWER FIRSTWhat is Data Structures Inside the LLM, and which AI decisions does it change?
You saw tokenization in the LLM fundamentals part—now the underbelly: how a prefix tree recognizes “五花肉” (streaky pork) as one chunk. Walk a Trie and tokenize by hand This page keeps the related concepts, common mistakes, and practical notes in one reading thread.
First decide whether you are blocked by a definition, a choice, or verification; then choose the closest of the 2 notes below.
Start with “Vocabulary & Trie: How Tokenizers Cut Words,” then restate the conclusion using your own task.
Do not treat every method in a topic as interchangeable. The answer changes with the input, risk, and acceptance bar.
THIS QUESTION THREAD
Put the word back inside the choice it changes.
Vocabulary & Trie: How Tokenizers Cut Words
You saw tokenization in the LLM fundamentals part—now the underbelly: how a prefix tree recognizes “五花肉” (streaky pork) as one chunk. Walk a Trie and tokenize by hand
Vectors: RAG Retrieval Is Finding Nearest Neighbors
Embedding turns meaning into coordinates; similarity is distance. Drag the query point on a plane to watch nearest neighbors change, then see why HNSW finds answers instantly among hundreds of millions of vectors