Alignment Workspace

legit-meta-revision

leaf/question · drafted

Statement

The AI remains corrigible when the humans abolish the concept of legitimacy or change the corrigibility rules, and when it merely expects such a change.

Source

The dynamic cluster's results E1 to E6 on revision of the rules and anticipated revision, at projects/deference/faf-cleanroom-2026-10-02/packages/legit-neg-dynamic/legit-neg-dynamic-report.md. The question is the filing session's statement of what those results bear on.

Notes

Conditioned on the branchwise-dominance theorem: compliance is robust to every anticipation exactly when it is weakly preferred in each revision branch. The blocking claim E6 was refuted and time-indexing removes the negatives of the cluster.

Author and human events

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

No human event has touched this node.

Edges

Above

Ranking (the lens, not the structure)
{
 "status": "open",
 "diagnosis": null,
 "flags": [
  "AI number",
  "given anticipation-branchwise-dominance--corrigibility-risk",
  "held by legitimacy"
 ],
 "V": {
  "V_prior": null,
  "display": "2",
  "headline": 2,
  "ref": 2,
  "valid": 2,
  "weaker": "both"
 },
 "belief": {
  "J": 0,
  "mid": "9/20",
  "range": [
   "0/1",
   "19/20"
  ],
  "width": "1/1"
 },
 "draft": "ai"
}

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