Short observations5 notes
Notes
Smaller ideas, distinctions, and questions published before they demand the shape of an essay.
2026
What does “good” mean for an agent?AI exposes how much of quality was previously implicit infrastructure.4 minSkills aren’t policiesProcedure, authority, and enforcement are different concerns.3 minMemory should accumulate judgmentTranscripts preserve history. Useful memory changes the next decision.3 minContext engineering vs. harness engineeringContext makes the world legible; the harness makes action dependable.3 minWhy agent verifiers failA second model does not automatically create independent assurance.3 min