LLM Internals
Why Your LLM Prompt Costs More Tokens Than Expected
See how whitespace, punctuation, numbers, code and multilingual text shift token counts, with before/after examples and cheaper prompt formatting tips.
Read the guide
Guides
Deep dives between the course and the docs: each guide explains one decision you will actually have to make, with the trade-offs spelled out.
LLM Internals
Fine-Tuning Memory Math: Why Full Training Needs 16 Bytes per Parameter
Why full fine-tuning needs about 16 bytes per parameter: weights, gradients and Adam states. Compare it to LoRA and QLoRA with a worked 7B example.
Read the guide
LLM Internals
KV Cache Size Formula: Why Long Context Eats Your VRAM
Use the KV cache size formula to see why long context eats VRAM. Worked numbers for Llama 3 8B and 70B, plus ways to shrink the cache and serve more users.
Read the guide
LLM Internals
Why Non-English Text Costs More Tokens: Turkish, Chinese, Arabic
Turkish, Chinese and Arabic often use more tokens than English for the same meaning. Learn why, how to measure the gap, and how it changes your API bill.
Read the guide
LLM Internals
How to Count Tokens in a Multi-Turn Chat Conversation
Learn how to count tokens across a full multi-turn chat, including per-message overhead and role tags, with a worked 3-message example and a budgeting checklist.
Read the guide
LLM Internals
Best Open-Source LLMs in 2026: A Practical Guide
Explore the best open-source LLMs in 2026, compare architectures, licensing, and inference costs, and learn how each fits the ML lifecycle.
Read the guide
LLM Internals
Context Engineering vs Prompt Engineering Explained
Learn how context engineering differs from prompt engineering, why it matters for LLM apps, and how to structure context across the model lifecycle.
Read the guide
LLM Internals
Counting Chat Tokens with Multiple Messages
Learn how chat formatting, speaker labels, and per-message overhead add tokens beyond raw text, with a worked manual counting method and estimation checklist.
Read the guide
LLM Internals
AI Hallucinations: Why LLMs Make Things Up and How to Reduce It
Understand why LLMs hallucinate, from tokenization to alignment, and learn practical techniques to reduce made-up answers in your AI applications.
Read the guide
LLM Internals
Prompt Injection Explained: Attacks and Defenses for LLM Apps
Learn how prompt injection attacks compromise LLM applications, from direct jailbreaks to indirect data poisoning, and the defenses that actually work.
Read the guide
LLM Internals
What Is MCP (Model Context Protocol)? Practical Guide
Learn what MCP (Model Context Protocol) is, how it connects LLMs to tools and data, and why it standardizes context for AI applications.
Read the guide
LLM Internals
Best AI Assistants for Work and Daily Life
Compare the best AI assistants for work and daily life, from chat helpers to coding copilots, and learn how the ML lifecycle powers them.
Read the guide