gandhi-argument-assumes-flat-utility
leaf/step · drafted
Statement
The murder-pill inequality, that the utility of the best act under U is at least the utility under U of the best act under the changed utility, yields resistance to value change only for a utility that does not depend on the modification event; in the note's two-step example an expected-utility agent strictly prefers having its values changed, 0.9 for accepting against 0.6 for declining.
Source
projects/deference/corrigibility-note-dump-2026-10-01/value-change-as-epistemic-update.md, sections 1.2 to 1.4 and the paragraph "The answer, in one paragraph"; the numbers are computed by projects/deference/corrigibility-note-dump-2026-10-01/fixtures/value_change_journey.py. The author's framing, section 1.3: "Real agents are embodied in the physical universe. Swapping an agent's utility function means changing its physical configuration".
Notes
The dissolution of the oldest anti-naturality argument (Omohundro's and Bostrom's goal-content integrity, Soares et al.'s section 1) at the level of a computed example. It is the formal content behind outline item 1 and the first conjunct of the author's thesis; unvetted.
Author and human events
Author @smithy-verity; version 1; size S.
No human event has touched this node.
Edges
Above
- part of value-change-base-layer
- root (shared-claim) of value-change-base-layer
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": "91/100",
"range": [
"41/100",
"1/1"
],
"width": "1/1"
},
"draft": "ai",
"root": {
"status": "open",
"Pr": {
"hi": "1/1",
"lo": "41/100",
"mid": "91/100"
},
"value": null,
"cost": "33/1",
"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.