2026-08-28·by Sijie Wang#cybernetics#theory

good-regulator-in-the-harness

Parent: theory · Reference: good-regulator-theorem

Three ways "control = modeling" lands on the harness:

  1. The positive reason for the observability ceiling (convergence-needs-an-observable-target): control requires a model; the unobservable part of the system (hidden variable / mood) can't be modeled → can't be regulated → you converge only to the observable marginal. "Must model" ⟺ "can't converge on what you can't model."
  2. The LLM is the model: an LLM-agent regulating a task is, by this theorem, necessarily a model of the task domain — its common sense / world-knowledge is the model it regulates with (tacit-spec-as-spec-compression). Regulation quality = model fidelity.
  3. Upstream of "control = destroy variety / converge" (control-methods, recursion-convergence-contraction): variety-matching (Ashby) → matching requires a model (Good Regulator).
about this entry

One of sijie's wiki entries. The AI on this site is grounded in the same corpus and answers in sijie's voice, with citations back to entries like this one — answering costs sijie money, so it waits behind a code: enter an access code →