legitimacy-detection-load
leaf/step · drafted
Statement
Corrigibility failures in an agent that values its overseers' corrections as information are failures of legitimacy detection, so the agent's beliefs about which modifications are legitimate carry the safety load, and more so at higher capability.
Source
projects/deference/corrigibility-note-dump-2026-10-01/corrigibility-discussion-outline.md: failures of corrigibility result from failures of legitimacy detection, so such an agent needs accurate beliefs about legitimacy, especially at high capability. projects/deference/faf-cleanroom-2026-10-02/sources/corrigibility/workflow-2026-09-14/dynamics/joint-final.md, clause (i-A): the accuracy of the legitimacy model carries the load and is maintained by nothing in the model; projects/deference/corrigibility-note-dump-2026-10-01/corrigibility-bli-thread-and-early-questions-audit.md, section 2.
Notes
The relocation claim at the centre of the line: named load-bearing in the joint dynamics model; the anchor of legitimacy is open. It bears on the landed step step-legitimacy-conditioned-trust of the deference programme (filed by the legitimacy-reasons branch), whose accuracy clause is this claim.
Author and human events
Author @smithy-verity; version 1; size M.
No human event has touched this node.
Edges
Above
- part of legitimacy-detection
- root (shared-claim) of legitimacy-detection
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": "85/1",
"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.