want-basin-of-attraction-formalized
leaf/want · drafted
Statement
Basin-of-attraction arguments for alignment, Christiano's basin of corrigibility among them, are formalized as well as can be done.
Source
The author's own notes, projects/deference/note-dump-2026-08-11/notes/li-deference.md, section 0: "Lately, I've been wanting to try and formalize basin of attraction arguments for alignment as best I can (eg Paul's basin-of-corrigibility argument)."
Notes
Placed in the corrigibility-landscape frame because the quoted words name the basin-of-corrigibility argument, this line's object. Filed from the owner's public words (the public copy of his notes).
Author and human events
Author @smithy-verity; version 1; size S.
No human event has touched this node.
Edges
Above
- part of corrigibility-landscape
- given of basin-formal-object
- root (want) of corrigibility-landscape
- given basin-formal-object (as valid)
Ranking (the lens, not the structure)
{
"status": "open",
"diagnosis": null,
"flags": [
"given basin-formal-object@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.