geometric-udt-deference-theorem
leaf/step · drafted
Statement
An agent is content to defer to a Geometric UDT construction over a broad prior of value hypotheses, provided the hypotheses report their beliefs honestly, under stated further assumptions.
Source
Stated from its content: the deference question for the construction of the maintainer's post Geometric UDT (https://www.lesswrong.com/posts/Gmaq7vMj9NWLyQkEx/geometric-udt), with the honesty of the hypotheses as the assumption the inner-optimizer story removes; the finite identity geometric_udt_identity in projects/deference/faf-cleanroom-2026-10-02/packages/udt-endorse-policy/udt-endorse-policy-report.md. The trust lab's agenda (projects/deference/note-dump-2026-08-11/deference-trust-lab/AGENDA.md) states the related Geometric UDT conjecture on how updateful an agent should be about human values.
Notes
Not proved. Given the inner-optimizer risk story as negative evidence: where dishonest hypotheses occur, the honesty assumption the theorem needs is strong.
Author and human events
Author @smithy-verity; version 1; size L.
No human event has touched this node.
Edges
Above
- part of geometric-rationality-value-uncertainty
- given of dishonest-inner-optimizers
- given dishonest-inner-optimizers
Ranking (the lens, not the structure)
{
"status": "open",
"diagnosis": null,
"flags": [
"AI number",
"given dishonest-inner-optimizers"
],
"V": {
"V_prior": null,
"display": "2",
"headline": 2,
"ref": 2,
"valid": 2,
"weaker": "both"
},
"belief": {
"J": 0,
"mid": "19/40",
"range": [
"0/1",
"39/40"
],
"width": "1/1"
},
"draft": "ai"
}Say something about it
Each verb opens a prefilled issue; a round files what lands as the ledger event it is.