What is an LLM?

A large language model (LLM) is a neural network trained on very large amounts of text to predict the next token in a sequence. That single objective, scaled up, produces models that can summarise, translate, write code and answer questions.

Tokens, not words

Models read and write tokens, which are chunks of text that are often a whole word or part of one. "Unbelievable" might be split into three tokens. Pricing, speed and context limits are all measured in tokens.

Context window

The context window is how many tokens the model can consider in one request, including your prompt and its reply. Anything outside that window is invisible to the model for that request.

What they are good at

Strong	Weak
Drafting and rewriting text	Precise arithmetic
Summarising long documents	Knowing recent events without a source
Explaining and writing code	Reliably avoiding invented facts

Key takeaway

Treat an LLM as a fast, well-read assistant that needs clear instructions and a second pair of eyes, not as an oracle.