# How Models Read Your Prompt — Prompt Engineering

Source: https://www.geekswithgeeks.com/en/prompt-engineering/f-read

> Understand tokens, context and why wording changes results.

## Tokens in, probabilities out

The model splits your prompt into **tokens**, reads all of them at once within its **context window**, and then generates its reply one token at a time, each chosen from a probability distribution shaped by everything before it. Consequences: (1) it only knows what is in the prompt plus its training, so you must supply missing facts; (2) tiny wording changes can shift probabilities and change answers; (3) text near the beginning and end is often used more reliably than details buried in a very long middle; (4) replies are not guaranteed identical across runs unless sampling is fixed.

## Say what you left unsaid

If a human would need to ask a clarifying question, the model needs the answer in the prompt. Include audience, constraints and definitions.

**Quiz:** Why must you include facts the model may not know?

- [x] It only has the prompt plus its training, not your private data
- [ ] Models forget their training
- [ ] Facts shorten the reply
- [ ] It is a rule of HTTP

*Answer:* It only has the prompt plus its training, not your private data. Missing facts lead to guesses, so supply them in the prompt.