rules-certified-or-learned
leaf/question · drafted
Statement
Corrigibility rules certified at commitment, rather than learned from legitimate-branch feedback, escape the selection bias and the retroactive-judging knife-edge.
Source
The results A2 and A3 (projects/deference/faf-cleanroom-2026-10-02/packages/legit-neg-static/legit-neg-static-report.md, targets 10 to 13), C10 (projects/deference/faf-cleanroom-2026-10-02/packages/legit-neg-pricing/legit-neg-pricing-report.md), E3 and E6 (projects/deference/faf-cleanroom-2026-10-02/packages/legit-neg-dynamic/legit-neg-dynamic-report.md, targets 9 and 12: the rules layer).
Notes
Open. Its truth lowers the mistaken-anticipation risk story, which conditions on it. The agent-side work is a model of rule learning measuring the bias.
Author and human events
Author @smithy-verity; version 2; size M.
No human event has touched this node.
Edges
Above
- part of legitimacy-rule-characterization
- part of legitimacy-weighted-deference
- root (shared-claim) of legitimacy-weighted-deference
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": "21/40",
"range": [
"1/40",
"1/1"
],
"width": "1/1"
},
"draft": "ai",
"root": {
"status": "open",
"Pr": {
"hi": "1/1",
"lo": "1/40",
"mid": "21/40"
},
"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.