Alignment Workspace

value-change-is-belief-change

leaf/step · drafted

Statement

A change of an agent's utility function can be written as a change of belief about a value variable on an expanded algebra, and the agent that results acts identically on the original propositions; the direction from the expanded algebra back to the original is marginalization and the converse is a choice of decomposition that is not unique.

Source

projects/deference/corrigibility-note-dump-2026-10-01/value-change-as-epistemic-update.md, section 2.1 (the transform, with Theorem 2.4) and the fixture projects/deference/corrigibility-note-dump-2026-10-01/fixtures/value_change_journey.py, run by the note dump's tests; the author's own statement of the idea in projects/deference/corrigibility-note-dump-2026-10-01/position-statement.md, section 2.2: "I am non-realist about the distinction: this is just a transformation in how we represent the agent."

Notes

The base layer of the corrigibility line: every later claim about corrections as information rests on this transform. The derivation is the filing session's (an AI's) at the author's request, with the fixture's numbers as witnesses; it is unvetted against the fixture, and no Lean statement for it is cited here. The Lean task is the plan root value-change-kernel-checked.

Author and human events

Author @smithy-verity; version 1; size M.

No human event has touched this node.

Edges

Above

Ranking (the lens, not the structure)
{
 "status": "open",
 "diagnosis": null,
 "flags": [
  "AI number"
 ],
 "V": {
  "V_prior": null,
  "display": "2",
  "headline": 2,
  "ref": 2,
  "valid": 2,
  "weaker": "both"
 },
 "belief": {
  "J": 0,
  "mid": "7/8",
  "range": [
   "3/8",
   "1/1"
  ],
  "width": "1/1"
 },
 "draft": "ai",
 "root": {
  "status": "open",
  "Pr": {
   "hi": "1/1",
   "lo": "3/8",
   "mid": "7/8"
  },
  "value": null,
  "cost": "85/1",
  "margin": "no established leaves"
 }
}

Say something about it

Each verb opens a prefilled issue; a round files what lands as the ledger event it is.

comment · challenge · estimate · want