kernel-box2-mediation
and · drafted
Statement
Mediating a policy, turning its reserved raw releases into proposals, raises its score under every credence by at least the penalty margin times the probability the policy violates; the mediated policy is faithful under effect completeness, delegation safety and allocation completeness; and consulting beats bypass at every day of a logical inductor whatever it believes about legitimacy.
Source
wiki/Corrigibility.md, section 5, Box 2; projects/deference/CLAIMS.md, the entries kernel.box2-dominance, kernel.box2-mediation-faithful and kernel.box2-finite-time (lean-proved, ci-only).
Bridge card
A conjunct of the informal claim authority-typed-corrigibility: 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.
Declaration kernel.box2-dominance (record kernel-box2-mediation.record)
The three registered statements are the kernel's second box: dominance of mediation, faithfulness under the walls, and finite-time consulting over bypass.
Hypotheses, read:
- kernel-box2-mediation.setting definitional: The kernel's setting with a policy, its mediated form, the penalty margin and the three completeness walls, as the specification fixes them.
Completeness (kernel-box2-mediation.complete): No premise beyond the proved declaration, its stated setting and its bridge is needed for the informal reading of kernel box2 mediation to hold.
What remains (authority-typed-corrigibility.improvable)
The kernel's model of a corrigible agent can be improved until it reflects real training and deployment interfaces well.
- kernel-route-realization-layer: A learning layer realizes the kernel's walls approximately on a real interface: effect completeness and count integrity hold up to a measured defect that enters the guarantee as a bound.
- kernel-route-foreclosure-expressibility: The kernel's interface is extended to express foreclosure, an advisor removing the principal's later ability to correct, through an operation that reassigns the authorization relation at a later index.
- kernel-route-fallible-future-comparator: The fully-updated-deference comparator is rebuilt with a future agent that has its own credence, so that more informed and correct come apart and the execution layer is reinstated. — item 27
- kernel-route-residual (residual): A refinement of the kernel not described by the other routes makes it hold of real training and deployment interfaces.
Author and human events
Author @smithy-verity; version 1; size M.
No human event has touched this node.
Edges
Above
- part of authority-typed-corrigibility
Children
- part: kernel-box2-mediation.record leaf/record
- part: kernel-box2-mediation.setting leaf/hypothesis
- part: kernel-box2-mediation.bridge leaf/bridge
- part: kernel-box2-mediation.complete leaf/completeness
Ranking (the lens, not the structure)
{
"status": "open",
"diagnosis": null,
"flags": [],
"V": {
"V_prior": null,
"display": "2",
"headline": 2,
"ref": 2,
"valid": 2,
"weaker": "both"
},
"belief": null,
"draft": "ai"
}Say something about it
Each verb opens a prefilled issue; a round files what lands as the ledger event it is.