Alignment Workspace

authority-typed-corrigibility.improvable

or · drafted

Statement

The kernel's model of a corrigible agent can be improved until it reflects real training and deployment interfaces well.

Source

Ruling 35 (every literal claim a plan builds on carries its improvement claim); wiki/Corrigibility.md, scope warning ("For systems that are not maximizers of the fidelity score, what carries over is the target ... not the guarantee"); PRIORITIES.md, Q3 and items 27, 101 and 102.

Notes

Improvement claim on the kernel plan (improves: authority-typed-corrigibility; reality: real training and deployment interfaces). Its routes are the kernel's own open pieces as the public priorities list states them, plus a residual.

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",
  "improvement claim on authority-typed-corrigibility (reality: real training and deployment interfaces)"
 ],
 "V": {
  "V_prior": null,
  "display": "2",
  "headline": 2,
  "ref": 2,
  "valid": 2,
  "weaker": "both"
 },
 "belief": null,
 "draft": "ai",
 "root": {
  "status": "open",
  "Pr": {
   "hi": "127991/128000",
   "lo": "0/1",
   "mid": "267814933385539/400000000000000"
  },
  "value": null,
  "cost": "inf",
  "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