pic-corrigibility-commitment
leaf/picture · drafted
Statement
Corrigibility toward shutdown-type corrections is a prior-stage commitment that a fully updated self would not renew, so its formal guarantee needs an updateless or policy-level evaluation.
Source
projects/deference/corrigibility-note-dump-2026-10-01/corrigibility-bli-thread-and-early-questions-audit.md, row 2.5 (the UDT commitment "the fully-updated self would not renew", valid "only for a faithfully run algorithm"); AI reading: corrigibility located in the gap between algorithmic self-trust and implementation self-distrust.
Notes
Shared with the corrigibility line's commitment-based plans: this picture's validity is evidence for them as well as for this crux.
Author and human events
Author @smithy-verity; version 1; size S.
No human event has touched this node.
Edges
Above
- part of updateless-engineering-value
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"
}Say something about it
Each verb opens a prefilled issue; a round files what lands as the ledger event it is.