Skip to main content
AI EducademyAIEducademy
🌳

AI Foundations

🌱
AI Seeds

AI literacy for the real world

🌿
AI Sprouts

The foundations behind intelligent systems

🌳
AI Branches

Build with today’s AI capabilities

🏕️
AI Canopy

Engineer reliable GenAI systems

🌲
AI Forest

Ship AI products responsibly

🔨

AI Mastery

✏️
AI Sketch

Engineering foundations for AI builders

🪨
AI Chisel

Patterns for solving harder problems

⚒️
AI Craft

Design systems that scale AI

💎
AI Polish

Communicate and lead in the AI era

🏆
AI Masterpiece

Your production AI capstone

🚀

Career Ready

🚀
Interview Launchpad

Navigate the AI engineering job market

🌟
Behavioral Mastery

Tell the story of how you create impact

💻
Technical Interviews

Solve, design, and communicate under pressure

🤖
AI & ML Interviews

Prepare for modern ML and GenAI interviews

🏆
Offer & Beyond

Make a confident, informed next move

View All Programs→

Lab

7 experiments loaded
🧠Neural Network Playground🤖AI or Human?💬Prompt Lab🎨Image Generator😊Sentiment Analyzer💡Chatbot Builder⚖️Ethics Simulator
🎯Mock InterviewEnter the Lab→
JourneyBlog
🎯
About

Making AI education accessible to everyone, everywhere

❓
FAQ

Common questions answered

🧰
AI Tools

Curated tools we use and recommend

✉️
Contact

Get in touch with us

⭐
Open Source

Built in public on GitHub

Pricing
Get Started
AI EducademyAIEducademy

© 2026 AI Educademy. All rights reserved.

Learn

  • Academies
  • Lessons
  • Lab
  • AI Starter Kit
  • Pricing

Community

  • GitHub
  • Contribute
  • Code of Conduct
  • About
  • FAQ

Support

  • Buy Me a Coffee ☕
  • Terms of Service
  • Privacy Policy
  • Contact
  • Sitemap
AI & Engineering Academics›🌿 AI Sprouts›Lessons›Tokenisation - How AI Reads Text
🔤
AI Sprouts • Intermediate⏱️ 14 min read

Tokenisation - How AI Reads Text

Public lesson preview

Learn how language models break text into tokens using BPE and other algorithms, and why tokenisation shapes everything from cost to capability.

Programme
AI Sprouts
Level
Intermediate
Reading time
14 min read

Learning objectives

By the end of this lesson, you will understand:

  • ✓Why Can't AI Just Read Characters?
  • ✓Word-Level Tokenisation
  • ✓The Sweet Spot - Subword Tokenisation
  • ✓Byte Pair Encoding (BPE) - Step by Step
  • ✓Other Tokenisation Methods

Lesson outline

  1. Why Can't AI Just Read Characters?
  2. Word-Level Tokenisation
  3. The Sweet Spot - Subword Tokenisation
  4. Byte Pair Encoding (BPE) - Step by Step
  5. Other Tokenisation Methods
  6. WordPiece
  7. SentencePiece
  8. How GPT-Style Models Tokenise Text
  9. The Vocabulary Size Trade-Off
  10. Multilingual Challenges
  11. Token Counting and Cost Implications
  12. Key Takeaways
  13. 📚 Further Reading

Introductory preview

Neural networks work with numbers. They cannot read the word "hello" the way you do. Before any language model can process text, it must be broken into small numerical pieces called tokens . This seemingly simple step has profound consequences for how AI understands - and misunderstands - language.

Continue Tokenisation - How AI Reads Text with Pro

Tokenisation - How AI Reads Text is part of AI Sprouts

Tokenisation - How AI Reads Text is part of AI Sprouts. Upgrade to unlock the full lesson, quizzes, progress tracking, and every academy.

All programs & tracks
Progress sync
Certificates
Try Pro free for 7 daysSign in first

Free for 7 days. Cancel anytime, no questions asked.