Skip to content

absolute beginner

LLM Basics

Look inside an LLM: tokens, context, transformers, next-token prediction, training, inference, fine-tuning, and the stages that shape model behavior.

Tutorials

Articles in LLM Basics

Follow these lessons in order, or jump directly to the topic you need.

High-tech laboratory equipment with computer system in lab setting.

absolute beginner

7 min read

What Is a Large Language Model?

A large language model is a pattern-prediction engine for language: it learns how words and ideas tend to follow one another, then uses that fluency to…

Close-up of a business planning cycle chart with a blue pencil on a wooden desk.

beginner

11 min read

How Do LLMs Work?

Large language models are not digital minds. They are probability engines that turn a conversation into a series of next-token guesses. The guesswork is…

Expansive desert landscape with golden sand dunes illuminated by sunrise, showcasing natural patterns and tranquility.

absolute beginner

15 min read

Key LLM Terms Explained

If you've tried to learn about large language models and felt like you hit a wall of unfamiliar jargon, you're not alone. LLM discussions can feel like…

A white humanoid toy robot standing on a reflective black surface in a studio setting with a blue and pink gradient background.

beginner

8 min read

A Brief History of LLMs

Large language models look like overnight magic, but they are the visible tip of decades of compounding engineering. If you want to use, trust, and build…

Minimalist image of industrial poles under a clear blue sky, highlighting clean energy.

beginner

11 min read

LLMs vs Other AI Models

Someone says "I built an app with NLP" when they really mean "I called the ChatGPT API." Someone else asks "which LLM should I use" when they're actually…

A mesmerizing view of the deep blue ocean with intricate white foam patterns captured from above.

beginner

10 min read

Real-World LLM Examples

You have probably already leaned on a large language model this week without naming it. That support chat that understood your question instead of forcing…

Dynamic image of a school of silver fish swimming against a deep blue aquatic backdrop.

beginner

7 min read

What Are LLM Tokens? A Beginner's Guide to Text Units

You paste a long document into a chatbot and hit an error about a "token limit." Or you open an API pricing page and see costs quoted per token, with no…

Back view of traveling couple in love wearing casual clothes walking with luggage and hugging while strolling along sidewalk together during vacation

beginner

10 min read

LLM Context Windows Explained: What Models Can See at Once

You tell a chatbot your name early in a conversation. Twenty messages later, it uses your name correctly. It feels like the model has been paying attention…

A vintage wooden desk with a gold octopus-like ornament, evoking antique charm.

beginner

7 min read

LLM Training vs Inference: What Changes When You Ask a Question

You correct a chatbot's mistake and expect it to remember next time. It won't. You ask the same question twice and get two different answers, which makes…

Dynamic underwater shot capturing a vibrant school of fish swimming in natural harmony.

intermediate

8 min read

Prompting vs RAG vs Fine-Tuning: Which Changes What?

You keep hearing three answers to the same question: "Just prompt it better." "Add RAG." "Fine-tune the model." They get offered like interchangeable…

Stunning sunrise over a serene mountain landscape showcasing nature's beauty.

beginner

11 min read

Transformer Architecture Explained: The Mechanism Behind Modern LLMs

You know an LLM predicts the next word. The real question is how it decides which word deserves to come next—and the answer lives in a design called the…

From below of monitor of modern computer with opened files on blue screen

beginner

9 min read

How LLM Tokenization Works: Why Words Become Different-Sized Pieces

You type a sentence into an AI chat window. The model reads it, thinks, and answers back. Somewhere in that exchange, your words get chopped into…

Aerial view of a traditional leather tannery in Fes, Morocco, showcasing colorful dye pits.

beginner

8 min read

What Are LLM Parameters? A Practical Mental Model for Model Size

You are comparing models and you see it everywhere: a name, a letter, and a number. Llama 3.1 8B. Mistral 7B. Qwen 72B. The reflex is almost automatic:…

Close-up of a blue screen error shown on a data center control terminal.

beginner

10 min read

Next-Token Prediction Explained: How LLMs Generate Text

When you watch a large language model type out a response, it feels like the system thought through the whole answer before writing a single word. It…

Visual abstraction of neural networks in AI technology, featuring data flow and algorithms.

intermediate

10 min read

What Is LLM Fine-Tuning? When Training Examples Change Model Behavior

You fine-tune a model on your own documents, ask it a factual question about them, and watch it hallucinate anyway. The training ran. The loss curve looked…

Expansive sand dune with sparse vegetation under a partly cloudy sky.

intermediate

11 min read

Pretraining vs Instruction Tuning vs Alignment: What Each Stage Changes

When someone says an LLM was "trained," they usually mean one thing. The people who build LLMs mean several. Each major stage of the modern training…

Appetizing grilled squid served with garnishes on a stylish plate with a spoon.

intermediate

10 min read

Attention and Token Representations: A Worked Mathematical Walkthrough

Most people can recite the attention formula. Far fewer can compute it. That gap is worth closing, because the formula is not a wall of symbols — it is a…

A woman in a blue bikini enjoying the sun and sea waves on a sandy beach.

intermediate

9 min read

From Next-Token Probabilities to Autoregressive Sequence Probability

A language model never scores a sentence. It scores one token at a time — and the sentence score is just those pieces multiplied together.

Close-up of hands working with electronics equipment and circuit board in a lab setting.

intermediate

9 min read

What the Language-Model Training Objective Optimizes

A model can write a confident, fluent paragraph that is completely false — and its training loss curve can look excellent the whole time. That combination…

Detailed image of a computer keyboard with blue LED backlighting, highlighting keys.

beginner

9 min read

Calculate an LLM Context Budget Step by Step

Your request worked yesterday. Today the answer stops mid-sentence, or the API returns an error, and you have no idea which of the four things you sent is…

Stunning sunset with a crescent moon, rich orange and red hues create a dramatic sky view.

beginner

12 min read

Practice Reviewing a Small Fine-Tuning Dataset

You generated forty examples. The file is open. Every row looks fine, and that is the problem — "looks fine" is not a review. A dataset is not a pile of…

Wide-angle view of a towering sand dune against a vibrant blue sky, showcasing the beauty of desert landscapes.

intermediate

11 min read

LLM Scaling Laws: Work Through a Simple Scaling Example

You have seen the chart. A straight line on a log-log plot, a caption promising that more compute buys predictable improvement, and a comment section…

Analyzing a bullish financial chart highlighting a significant upward trend in the market.

intermediate

9 min read

How a Training Loss Produces Gradients

You watch the loss number fall on a training chart. Something inside the model changed, but the chart never tells you what. The loss is a single number,…

Man diving into the ocean from a ledge with others swimming, showcasing thrilling summer fun.

intermediate

9 min read

Calculate a Gradient-Based Parameter Update

You can recite "gradient descent" and still freeze when someone hands you a loss, a gradient, and a learning rate. That freeze is not a math problem. It is…

Lush palm trees under a bright blue sky, evoking a tropical island vibe.

intermediate

9 min read

How Fine-Tuning Data Weights Change the Training Objective

You duplicate a handful of "good" examples to push the model toward a behavior. You retrain. The behavior barely moves — or it moves somewhere you did not…

A humanoid robot stands in a vibrant, modern hallway in Lagos, Nigeria.

absolute beginner

7 min read

LLMs vs Generative AI: How the Terms Fit Together

A headline calls an image tool "AI." A coworker calls ChatGPT "an LLM." A product page says "generative AI" for something that writes emails. Three labels,…