PART 1 · MODULE 1Large Language Models
What are LLMs?
Understand how AI models predict and generate text
Loading module...
Understand how AI models predict and generate text
You know when Outlook suggests "Sounds good, thanks!" as a reply? That's a tiny language model. An LLM does the same thing, but trained on a massive amount of text — so it can write entire reports, summarize meetings, and draft proposals.
HOW AN LLM PREDICTS THE NEXT WORD
Click a prediction to fill in the blank — just like an LLM would.
The model reads billions of documents and learns patterns in language.
It builds an internal map of how words and concepts relate to each other.
Given a prompt, it predicts the most likely next words, one at a time.
LLMs don't "understand" language like humans do. They're incredibly sophisticated pattern matchers. But the patterns they find are so complex that the output often feels genuinely intelligent.