Alignment Workspace

total-trust-is-updateful

leaf/question · drafted

Statement

Total Trust, the notion of alignment in Deference Done Better, is an updateful notion: total trust and deference come apart when actions have acausal consequences.

Source

projects/deference/faf-cleanroom-2026-10-02/sources/unbounded-embedded/01-primary/summer-research-plan-2026--research-ideas-may-2026.md, section Updatelessness: "The notion of alignment as total trust appears to be an updateful one; total trust and deference come apart when actions can have acausal consequences, since a more-knowledgeable future self might refuse a profitable counterfactual mugging, get the wrong answer in a transparent newcomb, etc."

Notes

The maintainer's claim, stated and not formalized; a scope limit the updateful trust line can cite once it is a theorem, and evidence for the predicted-AI picture of the engineering crux. The deference lab's copy of the same paragraph, projects/deference/note-dump-2026-08-11/deference-trust-lab/AGENDA.md, replaces 'Total Trust' by 'Endorsement'; the May 2026 document is cited as the source and the variant is noted.

Author and human events

Author @smithy-verity; version 1; size S.

No human event has touched this node.

Edges

Above

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": "9/10",
  "range": [
   "2/5",
   "1/1"
  ],
  "width": "1/1"
 },
 "draft": "ai",
 "root": {
  "status": "open",
  "Pr": {
   "hi": "1/1",
   "lo": "2/5",
   "mid": "9/10"
  },
  "value": null,
  "cost": "inf",
  "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.

comment · challenge · estimate · want