li-guides-engineering
and · drafted
Statement
A formal theory of trust developed at the logical-induction level guides AI safety engineering work.
Source
projects/deference/note-dump-2026-08-11/notes/li-deference.md: "This provides only a small amount of advice about building trustworthy AI"
Notes
Member of the level family. Two conjuncts: an engineering route exists (an or over three routes and the task that writes down what each result says to an engineer), and the level's results reach the systems actually selected for (li-results-reach-selected-systems). The li-trust branch files the li-deference cluster. AI reading of the decomposition.
Author and human events
Author @smithy-verity-opus55; version 1; size M.
No human event has touched this node.
Edges
Above
- part of stance-and-level
- root (shared-claim) of stance-and-level
Children
- part: li-engineering-route or
- part: li-results-reach-selected-systems leaf/step
- part: li-guides-engineering.complete leaf/completeness
Ranking (the lens, not the structure)
{
"status": "open",
"diagnosis": null,
"flags": [
"AI number",
"interval not a bound (negative evidential edge)"
],
"V": {
"V_prior": null,
"display": "2",
"headline": 2,
"ref": 2,
"valid": 2,
"weaker": "both"
},
"belief": null,
"draft": "ai",
"root": {
"status": "open",
"Pr": {
"hi": "42893578683/51200000000",
"lo": "0/1",
"mid": "1945848055419501/6553600000000000"
},
"value": null,
"cost": "99/1",
"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.