authority-typed-corrigibility
and · drafted
Statement
Corrigibility is a property of preferences: the agent prefers every course of action it knows to be faithful to the allocation of authority over every course it knows to be unfaithful, accepts a risk of unfaithfulness only at a fixed exchange rate, and has the fidelity score as its canonical objective, so that fully updated deference is dissolved by the typing rather than repaired.
Source
wiki/Corrigibility.md, section 0 (the canonical research-state note, restated 2026-09-27 around the corrigibility kernel: "Corrigibility is not an epistemic response to uncertainty about a hidden utility: her authority is part of what makes one history better than another, so fully updated deference is dissolved by the typing, not repaired"); the rounds projects/deference/rounds/2026-09-26-corrigibility-kernel, projects/deference/rounds/2026-09-27-corrigibility-kernel-phase2 and projects/deference/rounds/2026-10-01-thin-legitimacy-and-effective-authority; the claims kernel. and authority. in projects/deference/CLAIMS.md.
Notes
The public deference line's corrigibility kernel, filed as it appears in the repository and as a plan: its literal probability carries the walls as an assumption, and its validity reading (the walls held true) is the kernel's own headline for fidelity-score maximizers.
Author and human events
Author @smithy-verity; version 1; size L.
No human event has touched this node.
Edges
Above
- part of public-corrigibility-line
- root (plan) of public-corrigibility-line
Children
- part: kernel-box1-fidelity-vs-fud and
- part: kernel-box2-mediation and
- part: kernel-walls-hold leaf/assumption
- part: authority-typed-corrigibility.complete leaf/completeness
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": null,
"draft": "ai",
"root": {
"status": "open",
"Pr": {
"hi": "5/8",
"lo": "0/1",
"mid": "43342324075323/2000000000000000"
},
"value": {
"hi": "1/1",
"lo": "-1/1",
"mid": "43342324075323/2000000000000000"
},
"cost": "330/1",
"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.