Large Language Models
How ChatGPT, Claude, and modern AI systems work
What LLMs Are
Understand the foundations of large language models
What is an LLM?
From simple language models to GPT-4 — understand what makes a language model 'large' and why it matters.
Tokenization: Text to Numbers
See how text gets split into tokens and converted to numbers — the first step in any LLM pipeline.
Pre-training: Learning from the Internet
Watch a model learn language patterns from billions of tokens — next-token prediction at massive scale.
Scale & Generation
How LLMs generate text and why bigger models perform better
Scaling Laws: Bigger is Better?
Discover the mathematical relationship between model size, data, compute, and performance.
Text Generation: Next Token Prediction
Follow the autoregressive loop that turns probability distributions into coherent text.
Sampling: Temperature, Top-k, Top-p
Control creativity vs coherence by adjusting how the model picks the next token.
Alignment & Control
Making LLMs helpful, harmless, and honest
Fine-tuning: Teaching New Tricks
Adapt a pre-trained model to specific tasks with supervised fine-tuning and parameter-efficient methods.
RLHF: Learning from Human Feedback
See how human preferences train a reward model that guides the LLM toward helpful, safe responses.
Practical Usage
Get the most out of LLMs in practice
Prompt Engineering
Master zero-shot, few-shot, and chain-of-thought prompting to get better results from any LLM.
Context Windows & Memory
Understand the attention bottleneck, KV cache, and how RAG extends an LLM's knowledge.
Continue Your Journey
After understanding LLMs, learn how to augment them with external knowledge