Tag
#context-window
Every story tagged context-window, newest first.

How LLM Context Windows Actually Work (and Why Bigger Isn't Always Better)
A context window is a language model's working memory: shared between your prompt and its reply, wiped every request. Here's the machinery underneath (attention and the KV cache), why the biggest 2026 models reach toward a million tokens, and why a bigger number isn't automatically better.
Ahmad J · Aug 9, 2026 · 4 min read

Tokens, Explained: How Language Models Read Your Text and How You're Billed
Tokens are the unit of currency in every LLM interaction. Understand how text becomes tokens, why the count never matches your word count, and which levers actually control cost at scale.
Ahmad J · Aug 7, 2026 · 8 min read

What a context window actually is
A context window is not memory. It is the fixed amount of text a model can look at in a single pass, and everything outside it simply does not exist to the model.
Ahmad J · May 11, 2026 · 4 min read