Alignment Workspace

pic-detect-selects-undetectable

leaf/picture · drafted

Statement

A legitimacy detector learned from retractions discounts only the manipulations the overseers catch, so learning selects for manipulations never caught and detection is not made accurate.

Source

projects/deference/corrigibility-note-dump-2026-10-01/corrigibility-bli-thread-and-early-questions-audit.md, row 2.14.

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": null,
 "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