policy-selection-over-li
leaf/step · drafted
Statement
Policy selection over logical induction, as proposed in 2017, yields policy-level guarantees in per-round counterfactual mugging with a theorem behind it.
Source
projects/decision-theory/rounds/2026-09-29-li-bria-synthesis-spec/PROBLEM_STATEMENT.md, section 7, A2: policy selection over LI (Demski 2017) "claims it with no theorem".
Author and human events
Author @smithy-verity; version 1; size M.
No human event has touched this node.
Edges
Above
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": "3/10",
"range": [
"0/1",
"4/5"
],
"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.