A large language model is the thing behind ChatGPT and Claude. It can write, summarise, translate, code, and reason about almost anything — yet at its core it does something almost laughably simple: it predicts the next word. This course explains how something so simple becomes something so capable, and where it still gets things wrong.
- Understand how "predict the next word" leads to writing, translating, and reasoning
- Follow the three training stages that turn raw text into a helpful assistant
- Know the key dials — context window, temperature — and what they do
- Understand why LLMs hallucinate, so you can use them wisely
Predicting the next word — the whole game
Give an LLM the words "The capital of France is" and it predicts the most likely next word: "Paris." Give it "Once upon a" and it predicts "time." That is the entire core skill — guess what comes next.
Now here is the leap. To predict the next word well across all of human writing, the model is forced to learn an astonishing amount: grammar, facts, reasoning steps, the style of a legal letter versus a poem, even how a half-finished joke usually ends. You cannot reliably finish "To make a good argument, you should first…" without having absorbed how arguments work. The simple task secretly demands deep knowledge.
Before predicting, the model chops text into pieces called tokens — usually whole words or word-parts. Everything an LLM does is really "predict the next token," one token at a time, feeding its own output back in to keep going.
- An LLM's one skill is predicting the next token (word or word-part)
- Doing this well across all writing forces it to learn grammar, facts, and reasoning
- It generates text one token at a time, feeding its output back in
How an LLM is made: three stages
A raw next-word predictor is knowledgeable but unruly — it will happily continue offensive text or ramble. Turning it into a helpful assistant takes three stages:
Pre-training — read almost everything
The model reads a vast amount of text (books, websites, code) and learns to predict the next token. This is where it absorbs language and world knowledge. It is hugely expensive and done once. The result is powerful but raw.
Fine-tuning — learn to follow instructions
The model is then trained on examples of good answers to instructions — questions paired with helpful, well-structured responses. This teaches it to behave like an assistant rather than just autocompleting text.
Human feedback (RLHF) — learn to be helpful and safe
Finally, humans rate the model's answers, and it is nudged toward the responses people prefer — more helpful, honest, and harmless. This is the reinforcement learning you met in the ML course, applied to politeness and usefulness.
- Pre-training: read everything, learn language and knowledge (expensive, once)
- Fine-tuning: learn to follow instructions like an assistant
- RLHF: human ratings shape it toward helpful, honest, harmless answers
- How can "predict the next word" lead to a model that can reason through a problem?
- What does each of the three training stages contribute — in one phrase each?
The dials: context window and temperature
Two settings shape how an LLM behaves, and knowing them makes you far more effective.
The context window is how much text the model can "hold in mind" at once — your prompt plus its answer, measured in tokens. Think of it as the model's short-term memory or its desk space. Everything outside the window is invisible to it. If a conversation gets very long, the earliest parts may fall off the desk. This is why feeding the model the right information matters — a whole course later in this track (Context Engineering) is about exactly that.
Temperature controls creativity versus reliability. Low temperature makes the model pick the most likely next word every time — focused, predictable, repeatable (good for facts and code). High temperature lets it take chances — more varied and creative, but riskier (good for brainstorming, bad for a tax calculation).
- The context window is the model's working memory — only what fits is "seen"
- Long conversations can push early content out of the window
- Temperature trades reliability (low) for creativity (high)
Why LLMs hallucinate — and what to do
LLMs sometimes state false things with total confidence. This is called hallucination, and understanding why it happens is the key to using these tools safely.
Remember: the model predicts plausible next words, not true ones. It has no separate "fact-checker" inside. If a fluent, confident-sounding sentence is the most likely continuation, it produces it — whether or not it is correct. It is built to sound right, and usually that overlaps with being right, but not always.
The practical fix is to give the model the facts instead of relying on its memory — connect it to real documents and tools so it answers from sources, not from vibes. That is precisely the next course, RAG & Tool Use.
- LLMs predict plausible text, not verified truth — there is no built-in fact-checker
- They are reliable for language and reasoning, unreliable for specific facts
- The fix is to supply real facts and tools (the next course), not trust memory
- Why does an LLM sometimes sound confident while being wrong?
- For a factual question, would you use low or high temperature — and would you trust the model's memory or give it sources?