legit-learning-theorems
leaf/question · drafted
Statement
Under stated conditions an AI learning the humans' legitimacy concept learns enough of it to avoid wireheading and manipulating the humans.
Source
projects/deference/note-dump-2026-08-11/related-chats/2026-07-05__theory-of-legitimacy__c1ab54d9.md, turn 17 (quoted at legit-dynamics-learning).
Notes
No result at the LI register is filed; the finite report-layer results (wirehead-iff-finite) are the nearest.
Author and human events
Author @smithy-verity; version 1; size M.
No human event has touched this node.
Edges
Above
- part of legit-dynamics-learning
- root (shared-claim) of legit-dynamics-learning
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": "9/20",
"range": [
"0/1",
"19/20"
],
"width": "1/1"
},
"draft": "ai",
"root": {
"status": "open",
"Pr": {
"hi": "19/20",
"lo": "0/1",
"mid": "9/20"
},
"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.