Operating manual

Tag: Agent Architecture

A focused reading path for Agent Architecture: related field notes, evidence trails, and operating questions from the archive.

AI Agents/
18 Aug, 2026

a-world-model-is-an-executable-hypothesis.md

A World Model Is an Executable Hypothesis

A test-time world model should earn authority through replay, bounded action, and immediate revocation when reality produces a counterexample.
open artifact →