Tokenization
Cutting text into the tokens a model can process — and a quiet source of odd model behaviour.
A tokenizer maps text to integers using a fixed vocabulary learned from data. It explains several famous quirks: models miscount letters because they never see letters, and non-English text often costs more tokens for the same meaning because vocabularies skew English.
In practice: The same sentence in Greek can cost two to three times the tokens it costs in English.
Where this comes up
- AI for Marketers Course: Transform Your Marketing Strategy with AI
- Best Apps to Learn AI in 2026: 8 AI Learning Apps Tested on iPhone and Android
- Claude Sonnet 5: Release Date, Pricing, API & Benchmarks
- How Does ChatGPT Work? A Deep Dive into AI Language Models
- How to Start an AI Training Career in 2026: Skills, Roles & Growth Opportunities