Large Language Models (LLMs)

Large Language Models are a type of transformer model — a neural network architecture designed to handle sequences of text and learn context by paying attention to the relationships between words.

They work by predicting the next most likely word (or part of a word) in a sentence based on the context that came before.

Their strength lies in their scale:

• Trained on billions of words from books, websites, and other sources
• Learn grammar, facts, reasoning patterns, and more

LLMs are the foundation behind AI writing assistants increasingly used in education.

However, they don't "understand" the way humans do. They're statistical probability engines that generate plausible text based on probability. It's not magic — it's mathematics.

info

Like an English teacher who has read every book ever but doesn't know which facts are real, just what usually comes next in a sentence.