LLMs: Zero to Hero

Lessons

1. 1.

   Lesson 1: How LLMs Work: A Practitioner's Mental Model

   Build just enough intuition about tokens, context windows, and next-token prediction to reason confidently about why LLMs behave the way they do — without the math.

   llm-how-they-work-for-practitioners
   Open →
2. 2.

   Lesson 2: Prompt Engineering: The Core Moves

   Master the prompting patterns that actually change output quality — role prompting, few-shot examples, chain-of-thought, and output format control — with concrete before/after examples.

   llm-prompting-fundamentals
   Open →
3. 3.

   Lesson 3: Temperature, Top-p, and the Knobs That Matter

   Demystify the sampling parameters (temperature, top-p, top-k, max tokens, stop sequences) with interactive intuition for when to turn each one up or down for your use case.

   llm-parameters-and-sampling
   Open →
4. 4.

   Lesson 4: Evaluating and Iterating on LLM Outputs

   Develop a systematic approach to diagnosing bad outputs — distinguishing prompt failures from model limitations — and learn the iteration loop that moves from a rough first response to a reliable one.

   llm-evaluating-and-iterating
   Open →
5. 5.

   Lesson 5: Calling LLMs from Code: The API Basics

   Make your first API call, understand the messages array and system prompt, handle streaming responses, and know the three failure modes every programmer hits on day one.

   llm-api-for-programmers
   Open →