🤖

Series · Part 1 of 21

Foundation
AI Demystified
Abhishek Saha
Abhishek Saha
· 🤖 AI / ML

What Happens When You Ask AI Something?

You type a message. Half a second later, AI replies. Here's every single step that happens in between — from your first letter to the model's last word.

What Happens When You Ask AI Something?

You type: “What’s the capital of France?”

Half a second later: “Paris.”

Simple. But between your keypress and that answer, something remarkable happened — a chain of mathematical transformations so precise that the model understood not just your words, but their meaning, context, and intent.

This is that chain, step by step.

PIPELINE EXPLORER

Click each stage to see what the model is actually doing with your text.

✂️
1. Tokenization
Text → Numbers

The input text is split into tokens — small chunks of characters. Each token gets a unique ID number. LLMs don't read words, they read numbers.

"The cat sat"
"The"
ID: 464
" cat"
ID: 3797
" sat"
ID: 3332
TOKENS → TOKEN IDs
✂️ Text → Numbers
🌌 Numbers → Vectors
👁️ Which words matter?
🔁 Deep processing
🎯 Probabilities → Word

Every response from ChatGPT, Claude, or Gemini goes through these exact five stages. The model never “reads” your text — it converts everything to numbers, applies matrix math through 96+ layers, and converts back to text. That purely mathematical process somehow produces understanding.

Next up: Part 2 goes inside the Transformer architecture — the attention mechanism, why it replaced everything before it, and what 96 layers actually do.

AI Demystified · 16 of 21 published

  1. 0 Grounding 5 Mental Models You Need Before Diving Into AI
  2. 1 Foundation What Happens When You Ask AI Something?
  3. 2 Foundation Transformers — The Architecture That Changed Everything
  4. 3 Foundation How AI Learns, Thinks, and Decides
  5. 4 Foundation How AI Reads Your Words
  6. 5 Foundation Why AI Forgets
  7. 6 Foundation Why AI Lies (And Doesn't Know It)
  8. 7 Foundation What AI Cannot Do
  9. 8 Foundation How AI Reasons (And Why It Sometimes Breaks)
  10. 9 Practice Prompt Engineering — How to Talk to AI
  11. 10 Practice Embeddings & Vector Databases — The Memory Layer of AI
  12. 11 Practice RAG Explained — How AI Knows What You Didn't Train It On
  13. 12 Practice Fine-tuning vs. Prompting — When to Use Which
  14. 13 Practice Do You Really Need GPT-4?
  15. 14 Practice Latency, Tokens, and Cost — The Physics of AI Products
  16. 15 Practice How Do You Know AI Is Actually Working?
  17. 16 Hands-On Coding Setup — Your AI Development Environment soon
  18. 17 Hands-On MCP Tool Calling — How AI Uses Tools soon
  19. 18 Hands-On AI Agents — Beyond Chatbots soon
  20. 19 Hands-On Build Your First Real AI App soon
  21. 20 Hands-On Token Optimization — Spend Less, Get More soon

Related posts

⚙️
How DNS Works — The Internet's Phone Book ⚙️ Tech
Part 1 · How the Internet Works

How DNS Works — The Internet's Phone Book

You type google.com. Your browser stares at it blankly — it has no idea where that is. Here's how the internet turns a name into an address, and why it's faster than you'd expect.

read more →
⚙️
How HTTP Works — The Language of the Web ⚙️ Tech
Part 4 · How the Internet Works

How HTTP Works — The Language of the Web

The TLS tunnel is open. Now your browser and server need to speak the same language. Here's what GET, POST, 404, and 200 actually mean — and what really travels across the wire.

read more →
⚙️
How HTTP/2 Works — The Speed Upgrade ⚙️ Tech
Part 5 · How the Internet Works

How HTTP/2 Works — The Speed Upgrade

HTTP/1.1 can only send one request at a time. A modern page needs 50+ files. HTTP/2 loads everything at once over a single connection — here's how multiplexing actually works.

read more →
newsletter

Get new posts in your inbox

No spam. No digest. Just a note when I publish something new.

Discussion