It’s Tokens All The Way Down: How RLMs are Different — Kevin Madura, AlixPartners
Source
AI Engineer
Author
AI Engineer
Date
Terms in this piece · Glossary
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
chain-of-thought — Having a model write out intermediate reasoning steps before its answer, which markedly improves performance on hard problems.
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
Why it matters
Recursive language models treat context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → as an object in a REPL rather than tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → to attend over, letting a model delegate subproblems to itself, moving one long-reasoning benchmarkA standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.Full definition →'s accuracy from 2.6% to 45.4%.
videoYour agents lack context: Here's how to fix "You're absolutely right!" — Brandon Waselnuk, Unblocked
videoMCP Apps: Give the Model Data, Give the User a UI — Dustin Mihalik, Indeed
videoThe Universal Remote Control for AI — Alex Hancock, Block
videoBuild-Time vs. Run-Time: Why Dev Tools Fail in Production — Averi Kitsch & Prerna Kakkar, Google
