Alignment Workspace

corrigibility-less-anti-natural

leaf/step · drafted

Statement

Each published argument that corrigibility is anti-natural rests on at least one assumption that fails for an agent whose utility on the algebra containing the overseers' corrections depends on those corrections.

Source

The author's thesis as published in projects/deference/corrigibility-note-dump-2026-10-01/corrigibility-discussion-outline.md, section "the author's thesis": the arguments for anti-naturality have hidden or under-scrutinized assumptions. The utility-depends-on-corrections form is the value-change note's reframing, projects/deference/corrigibility-note-dump-2026-10-01/value-change-as-epistemic-update.md, section 4.1.

Notes

The thesis of the corrigibility line. It conditions on the conjunction of the arguments as stated: where that conjunction fails, the thesis is close to established; where some argument holds as stated, the thesis fails at that argument.

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",
  "given anti-naturality-arguments-as-stated",
  "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": "13/40",
  "range": [
   "0/1",
   "33/40"
  ],
  "width": "1/1"
 },
 "draft": "ai",
 "root": {
  "status": "open",
  "Pr": {
   "hi": "610261063117/655360000000",
   "lo": "1/40",
   "mid": "176157917401232841/335544320000000000"
  },
  "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