Module 4 of 6 · LLMs
Section 1 of 7

What Is a Large Language Model?

A Large Language Model is a Transformer trained on enormous amounts of text to do one deceptively simple thing: predict the next word (technically, the next 'token') given everything before it.

That single objective, applied at massive scale — billions of parameters, trained on trillions of words of text — turns out to be enough to make the model implicitly learn grammar, facts, reasoning patterns, and even coding ability, purely as a side effect of getting very good at prediction.

Knowledge Check

5 questions — answer all, then submit

1. What is the primary training objective of a large language model?

2. What does RLHF add to a pretrained LLM?

3. Setting temperature to 0 makes a model produce output that is:

4. What is a text embedding?

5. Why are output tokens priced higher than input tokens by most providers?