Packet To Sniff

How language models read text

Start here if you use language models but want to understand what happens to your text before the model sees it, and why limits and costs behave the way they do.

Beginner4 stepsFree, no account needed

Steps

  1. Step 1 · 4 min read

    What is a token in an LLM?

    Everything else is measured in tokens.

  2. Step 2 · 3 min read

    What is a context window in an LLM?

    The model's whole working memory, and how to budget it.

  3. Step 3 · 3 min read

    Why long context windows still miss things

    Why accepting text is not the same as using it.

  4. Step 4 · 3 min read

    What are embeddings? Meaning as numbers, explained

    How meaning becomes numbers you can search.