Alignment Workspace

factor-reaches-engineering

leaf/step · drafted

Statement

A theory of trust obtained for unbounded agents and related to bounded computation reaches AI safety engineering through the logical-induction level it is related to.

Source

projects/deference/faf-cleanroom-2026-10-02/sources/unbounded-embedded/01-primary/planning-to-write-about-coles-theorem.md: the factor-then-relate plan, as cited on factor-unbounded-then-relate.

projects/deference/faf-cleanroom-2026-10-02/sources/unbounded-embedded/01-primary/summer-research-plan-2026--research-ideas-may-2026.md: "The impact of this project would be to refine our picture of computationally unbounded intelligence, with the hope that doing so will also help our understanding of bounded intelligence, and AI safety."

Notes

Conditioned on li-guides-engineering: once the unbounded theory is related to the logical-induction level, its engineering relevance is that level's. AI reading of how the plan's two steps reach the frame question.

Author and human events

Author @smithy-verity-opus55; 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",
  "given li-guides-engineering"
 ],
 "V": {
  "V_prior": null,
  "display": "2",
  "headline": 2,
  "ref": 2,
  "valid": 2,
  "weaker": "both"
 },
 "belief": {
  "J": 0,
  "mid": "17/40",
  "range": [
   "0/1",
   "37/40"
  ],
  "width": "1/1"
 },
 "draft": "ai"
}

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