Most devs don't understand how LLM tokens work
Most devs are using LLMs daily but don't have a clue about some of the fundamentals. Understanding tokens is crucial because you need to know how you're being billed, and why billing is different per provider. Join my newsletter on AI Hero: https://www.aihero.dev/s/y-newsletter Code: https://github.com/mattpocock/ai-sdk-... 00:00 Intro 00:33 Input & Output Tokens 01:11 Monitoring Token Usage 02:16 What are tokens? 02:50 Tiktoken 03:47 Full LLM Process 04:49 Building Token Vocabularies 05:25 Character-Level Tokenizer 06:37 Vocabulary Size 07:20 Subword-Level Tokenizer 08:33 Building Longer Subwords 08:58 Unusual Words 09:45 Summary
▶︎
Most devs don’t understand how context windows work
▶︎
Everyone is Wrong about Tokens
▶︎
5 Essential Claude Code Skills Every QA Engineer Needs
▶︎
Never Run claude /init
▶︎
Most devs don't understand what agents are
▶︎
Never Trust An LLM
▶︎
Your codebase is NOT ready for AI (here's how to fix it)
▶︎
Yann LeCun's $1B Bet Against LLMs
▶︎
Is RAG Still Needed? Choosing the Best Approach for LLMs
▶︎
How AI agents & Claude skills work (Clearly Explained)
▶︎
Microsoft AI CEO unveils 7 new AI models | Mustafa Suleyman at Microsoft Build 2026
▶︎
I was an AI skeptic. Then I tried plan mode
▶︎
Transformers, the tech behind LLMs | Deep Learning Chapter 5
▶︎
How LLMs Actually Generate Text (Every Dev Should Know This)
▶︎
The 7 phases of AI-driven development
▶︎
I Re-Created A Quant Trading Strategy With Claude Code (Insanely Cool)
▶︎
TOKENIZATION: How AI models turn text into numbers | Byte-Pair Encoding
▶︎
Tokens vs Embeddings – what are they + how are they different?
▶︎
How Anthropic Engineers ACTUALLY Prompt Claude Code
▶︎