want-legitimacy-corrigibility-theorems
leaf/want · drafted
Statement
The legitimacy-based notion of corrigibility, under which an agent is corrigible where it sees human shutdown and modification decisions as legitimate, is formalized, with theorems proved about what it can and cannot accomplish.
Source
The author, projects/deference/faf-cleanroom-2026-10-02/sources/unbounded-embedded/01-primary/summer-research-plan-2026--research-ideas-may-2026.md, section "Modeling Legitimacy & Corrigibility": "I believe a good model of legitimacy could also shed light on corrigibility: AI can be corrigible in cases where it sees human shutdown/modification decisions as legitimate. Formalizing this notion of corrigibility and proving some theorems about what it can and cannot accomplish seems high-priority."
Notes
Placed in the legitimacy-detection frame because the quoted words name legitimacy as the basis of corrigibility, this frame's object. Filed from the owner's public words. The author's own phrase 'seems high-priority' is not a priority word in this system until he gives one.
The same want as want-corrigibility-theorems-via-legitimacy (under legitimacy-reasons-programme), filed from the same section by a second session; its Source is appended there, and the owner's one priority word on either settles both. Kept as a root because its events are history.
Author and human events
Author @smithy-verity; version 1; size S.
No human event has touched this node.
Edges
Above
- part of legitimacy-detection
- given of legitimacy-conditioned-reflection
- root (want) of legitimacy-detection
- given legitimacy-conditioned-reflection (as valid)
Ranking (the lens, not the structure)
{
"status": "open",
"diagnosis": null,
"flags": [
"given legitimacy-conditioned-reflection@valid",
"given: conditionals not judged",
"no belief",
"owner has not confirmed"
],
"V": {
"V_prior": null,
"display": "2",
"headline": 2,
"ref": 2,
"valid": 2,
"weaker": "both"
},
"belief": null,
"draft": "ai",
"root": {
"status": "open",
"Pr": {
"hi": "1/2",
"lo": "1/2",
"mid": "1/2"
},
"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.