Generative AI Fundamentals · Lesson 2
How LLMs Work Under the Hood
We cover tokens, embeddings, and next-token prediction — no math required, but deep enough to understand model behavior.
Practical exercise
What to do after this lesson
In any LLM interface, ask the same question 3 times in a row without changes. Compare the responses — you'll see variability. If temperature is adjustable (e.g., OpenAI Playground), try temperature=0 and temperature=1 on the same prompt.
Ready-to-use prompt
Template for this lesson
Copy and adapt to your context. Text in angle brackets should be replaced.
Continue the following text in three different ways — formal, conversational, and creative. Show all three versions: <paste your text opening here>
Common mistakes
What people get wrong
- Thinking the model has "memory" between tokens like a human — it only sees the current context window.
- Confusing temperature with "intelligence" — higher temperature doesn't make the model smarter, just more varied.
- Assuming 1 token = 1 word — this leads to incorrect estimates of limits and cost.
Pro tips
What works but no one documents
- For tasks with a single correct answer (code, SQL, JSON), use temperature=0 or close to it.
- For brainstorming, variations, stories — raise temperature to 0.8–1.0.
- Use tokenizer.openai.com to count tokens in a text — essential when working with large documents.
When to use
This is a theory lesson — understanding the mechanism helps you write better prompts and interpret model behavior correctly.
When not to use
You don't need to hold the full mechanics in your head for every prompt — just keep the key implications in mind: tokens, context, temperature.
Official sources
Квиз — 2 вопроса
1.What is a token in the context of LLMs?
2.What happens when you set temperature=0?
Отвечено: 0 из 2