Alignment Workspace

value-on-agency

leaf/step · drafted

Statement

Corrigibility is formalized as the agent learning early that humans value their own control, a value on agency, and the formalization gives verdicts beside explicit corrigibility rules on a shared instance.

Source

AI reading: a value on agency (humans value their own control, learned early) as an alternative to explicit corrigibility rules; wiki/Corrigibility.md, Box 1's house-sale instance, for the rules side.

Notes

Not started. A plan root, actioned: the first formal sketch on the kernel's house-sale instance is the work.

Author and human events

Author @smithy-verity; version 2; size M.

No human event has touched this node.

Edges

Above

Ranking (the lens, not the structure)
{
 "status": "open",
 "diagnosis": null,
 "flags": [
  "AI number"
 ],
 "V": {
  "V_prior": null,
  "display": "2",
  "headline": 2,
  "ref": 2,
  "valid": 2,
  "weaker": "both"
 },
 "belief": {
  "J": 0,
  "mid": "21/40",
  "range": [
   "1/40",
   "1/1"
  ],
  "width": "1/1"
 },
 "draft": "ai",
 "root": {
  "status": "open",
  "Pr": {
   "hi": "1/1",
   "lo": "1/40",
   "mid": "21/40"
  },
  "value": {
   "hi": "1/1",
   "lo": "-1/1",
   "mid": "21/40"
  },
  "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