The Context Window: an LLM's Short-Term Memory, Explained (opens in new tab)

A chatbot feels like it remembers you. It doesn't — it's stateless. Everything it "knows" is just text resent each call, up to a fixed limit: the context window. When the box fills, the oldest messages fall off the edge and are genuinely gone. 🪟 Watch tokens fall off: The model is stateless reply = model(allMessagesSoFar); // the app resends the whole history every turn "Memory" is just text you keep pasting back in. The window is a hard token limit Prompt + conversation + pasted docs + the r...