Alignment Workspace

anger-substitute-for-updatelessness

cases · drafted

Statement

A learned human desire for the AI to take actions that are beneficial in illegitimate worlds, learned correctly by the AI, substitutes for updateless reasoning in a legitimacy-weighted objective.

Source

projects/deference/faf-cleanroom-2026-10-02/packages/legit-neg-dynamic/legit-neg-dynamic-findings.md: "the anger substitute relocates updatelessness into the evaluators' values" (D7) is recorded there as an argument with no declaration, and its identification failure is the proved D4_iv (anger_identification_failure).

Notes

A deconfusion question as a cases node with three readings. One row is conditioned on the identification failure. The coupling to the updateless-dt branch: under the first or third reading, progress on the tractability of logical induction plus updatelessness raises the value of this whole line.

Author and human events

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

No human event has touched this node.

Edges

Above

Children

Ranking (the lens, not the structure)
{
 "status": "open",
 "diagnosis": null,
 "flags": [
  "AI number",
  "given deterrence-not-identified-on-path",
  "held by legitimacy",
  "no belief",
  "under attack"
 ],
 "V": {
  "V_prior": null,
  "display": "2",
  "headline": 2,
  "ref": 2,
  "valid": 2,
  "weaker": "both"
 },
 "belief": null,
 "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