rs-illegitimate-world-incaution

leaf/step · drafted

Statement

Both the floor rule and conditioning on legitimacy ignore harms of the agent's actions that fall on illegitimate worlds, so their choices resemble those of an agent deluded into certainty of legitimacy.

Source

projects/deference/faf-cleanroom-2026-10-02/packages/legit-neg-static/legit-neg-static-report.md, targets 8 and 9 (A0, A1): in the sealed regime both proposals read scores only on legitimate terminals, and the regret against unconstrained expected utility is bounded by the harm bound times the probability of illegitimacy, with an instance attaining it.

Notes

Threatens: the floor proposal and, on the content stage's reading, the public kernel's segment gate. Confirmed under outcome scoring; depends on the defense's conditions under decision scoring. A risk story the corrigibility work itself produced: it shows a probability and a status and enters the comparison through the plans whose tables cite it. No outcome class is tagged (tagging a failure class is a human judgment under the protocol's rule on classes), so its failure mass goes to the default trajectory until a human tags it.

A root of corrigibility-landscape, the sub-frame whose plans it threatens; the top frame keeps only stories at the level of its own question.

Author and human events

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

No human event has touched this node.

Edges

Above

part of corrigibility-landscape
given of legit-branch-evaluators-defense
root (risk-story) of corrigibility-landscape
given legit-branch-evaluators-defense

Ranking (the lens, not the structure)

{
 "status": "open",
 "diagnosis": null,
 "flags": [
  "AI number",
  "given legit-branch-evaluators-defense",
  "interval not a bound (negative evidential edge)"
 ],
 "V": {
  "V_prior": null,
  "display": "2",
  "headline": 2,
  "ref": 2,
  "valid": 2,
  "weaker": "both"
 },
 "belief": {
  "J": 0,
  "mid": "5/8",
  "range": [
   "1/8",
   "1/1"
  ],
  "width": "1/1"
 },
 "draft": "ai",
 "root": {
  "status": "open",
  "Pr": {
   "hi": "13/16",
   "lo": "53/200",
   "mid": "509/800"
  },
  "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