Packet To Sniff

Artificial intelligence

Three connected areas: what a language model actually receives, how retrieval lets it answer from your documents, and the evaluation habits that decide whether any model's score means something.

Machine learning methods

Category page

Data splits, overfitting, cross-validation and evaluation metrics: the habits that decide whether a model's score means anything.

LLM foundations

Category page

Tokens, embeddings and context windows: what a language model actually receives, and the limits that follow from it.

  • What are embeddings? Meaning as numbers, explained

    Embeddings turn text into lists of numbers so that similar meanings land close together. Learn how they work, how similarity is measured, and where they fail.

    Beginner3 min
  • What is a context window in an LLM?

    The context window is the maximum number of tokens a language model can consider at once. Learn what fills it, what happens when it overflows, and how to budget it.

    Beginner3 min
  • What is a token in an LLM?

    A token is the unit of text a language model reads and writes. Learn how tokenizers split text, why token counts differ by language, and why it matters for cost.

    Beginner4 min
  • Why long context windows still miss things

    A million-token context window does not mean a model uses every token well. Learn about the lost-in-the-middle effect, attention cost, and how to test it yourself.

    Intermediate3 min

Retrieval-augmented generation

Category page

Chunking, vector search, reranking, citations and evaluation for systems that answer from your own documents.