What Is an LLM?
38%
Lesson 3 of 8

What Is an LLM?

An LLM predicts and generates language one token at a time using the context available in the conversation.

Active reading
Token

A small unit of text.

Context

The information currently available.

Prediction

Choosing likely next tokens.

An LLM is not a searchable encyclopedia

A language model generates sequences based on learned statistical structure. It can reproduce useful knowledge patterns, but it does not “open a fact record” before every sentence.

This explains why context matters so much: the instructions and evidence you provide can strongly shape the next tokens the model generates.

Example
Short context → broad answer. Clear context + constraints → a more targeted answer.
Quick check

Explain this lesson back in one sentence before continuing. If you cannot, reread the example and key takeaway.

Common mistake

Do not confuse confident language with guaranteed understanding.

Key takeaway

LLMs generate language from tokens and context. Better context improves control, but verification still matters.

Next lesson

Tokens and Context

Continue to the next lesson.

Continue →