level-poly-time
frame · drafted
Question
Which whole-mind models of rationality at polynomial time or below would advance a formal theory of trust?
Owners: @abram (GitHub abramdemski) · not opened
Path: the-program › stance-and-level › level-poly-time
Roots (the frame's goals)
shared-claim
Bounded inductive rationality and the LI/BRIA synthesis target are computable agent criteria that quantify over efficiently computable hypotheses, so they sit at or near the poly-time boundary of the computability axis rather than at the logical-induction level proper.
Statement
A formal theory of trust developed as whole-mind models of rationality at polynomial time or below, where the model is itself an implementable AI design, guides AI safety engineering work.
Source
The computability axis of the-program, as its other levels state it (level-above-quantifiable, li-above-poly-time, level-super-turing): this is the level below logical induction. The placement is the filing session's reading; no public source states this line.
Notes
A line recorded and not opened (opened: false). It holds one shared claim, that the LI/BRIA synthesis target sits at or near the polynomial-time boundary (bria-near-the-line). It has no plan root, gets no spell-out unit, and is outside the plan decision.
Author and human events
Author @smithy-verity-opus55; version 1; size M.
No human event has touched this node.
Edges
Above
- part of stance-and-level
- root (plan) of stance-and-level
Children
- part: bria-near-the-line leaf/question
Ranking (the lens, not the structure)
{
"status": "open",
"diagnosis": null,
"flags": [
"not opened; see Notes"
],
"V": {
"V_prior": null,
"display": "2",
"headline": 2,
"ref": 2,
"valid": 2,
"weaker": "both"
},
"belief": null,
"draft": "ai",
"root": {
"status": "open",
"Pr": {
"hi": "0/1",
"lo": "0/1",
"mid": "0/1"
},
"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.