Episode 2: Tokens & Context Windows
Notes de l’épisode
How do AI models measure text, and why do long chats start losing quality? In this episode, we unpack the mechanics of tokens and context windows—the foundational units behind AI memory, platform limits, and usage costs. We explore why Claude forgets everything between messages and must re-read the entire conversation history on every single turn. Discover why long conversations suffer from "context rot", how automatic compaction works when limits are reached, and how handoff notes can preserve your usage allowance.