miatz™
Log inSit Chuun
AI Engineering · 100-level

How LLMs Actually Work

Sit Chuun — free All modules
AIE-1012 creditscorebadge: foundations-ino prerequisites
Start this course — free

Earn the foundations-i credential

What's inside

Sections & lessons

01

Tokens & vocabulary

  • Why the model never sees letters, only token IDsconcept45 min
02

Attention & meaning

  • How self-attention resolves what a word refers toconcept60 min
03

Reasoning traces

  • Chain-of-thought and the cost of an extra thinking stepconcept60 min
04

Lab + eval-gate: LLM fundamentals

  • Payload autopsy lab and Foundations I eval-gate (Foundations I badge)concept120 min
Start this course — free
Learn it from the inside

This module's playgrounds

AI Engineering

Next in this path

Where this specialization goes from here — in (level, code) order.

  • AIE-102

    Prompt Engineering

    2 creditscorebadge: prompter
    Start
  • AIE-103

    Context Engineering & Cost Basics

    2 creditscorebadge: context-thinker
    Start
  • AIE-110

    Open-Source & Sovereignty (India-first)

    1 creditselectivebadge: open-weights
    Start
  • AIE-120

    AI Consequences & War-Room

    1 creditscorebadge: responsible-builder
    Start
  • AIE-130

    Model Landscape & Jargon

    1 creditselectivebadge: model-literate
    Start
  • AIE-201

    AI-Assisted Coding

    3 creditscorebadge: builder
    Start
  • AIE-202

    RAG Foundations

    3 creditscorebadge: rag-i
    Start
  • AIE-203

    RAG Quality & Retrieval Evals

    2 creditselectivebadge: rag-ii
    Start
Vocabulary

Key concepts in this course

Token Subword Tokenization Chain-of-Thought Prompting Eval Gate

Compare related approaches

Code Grader vs LLM-as-Judge Temperature vs Top-P Sampling
Optional · watch & try

Go deeper, elsewhere

Hand-picked public explainers and open tools — always optional, never required, never graded.

How LLMs Work: A Visual GuideVisual walkthrough of the LLM pipeline from input text to output token How LLMs REALLY Work (Simple Explanation)Plain-language mental model for what an LLM is actually computing Attention in transformers, step-by-step | Deep Learning Chapter 6 (3Blue1Brown)Gold-standard visual explainer of the attention mechanism inside a transformer Transformer ExplainerLive in-browser GPT-2 running with every transformer stage visualized as you type LLM Visualization (bbycroft)3D walkthrough of a GPT-style model's full forward pass, weight matrix by weight matrix A visual introduction to tokenization in LLMs | Byte Pair Encoding AlgorithmShows how byte-pair encoding splits text into subword tokens step by step

This module ends in a gate you can fail.

That's what makes passing it mean something. Sit Chuun, get placed, and start earning.

Sit Chuun — free All modules