Alignment Workspace

a4-no-binding-counter-drive

cases · drafted

Statement

No explicit counter-drive is installed, or an installed one fails to bind at high capability.

Source

Reconstructed from Omohundro 2008, abstract: "tendencies which will be present unless explicitly counteracted"; the paper does not state it in this form.

Notes

The premise that makes the drives a risk rather than a description. Now a table: the pictures are no counter-drive installed, an installed counter-drive that fails to bind, and a learned counter-drive that binds because the system's utility on the correction algebra depends on the corrections, the content stage's reading of how the value-change note's thesis bears on this leaf (projects/deference/corrigibility-note-dump-2026-10-01/value-change-as-epistemic-update.md, section 4.1; the note does not discuss instrumental convergence, so the third picture is marked attribution-unvetted as a reading of the note). Statement unchanged; the landed range is stale by the leaf-became-a-table rule.

Author and human events

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

No human event has touched this node.

Edges

Above

Children

Ranking (the lens, not the structure)
{
 "status": "open",
 "diagnosis": null,
 "flags": [
  "AI number",
  "attribution unvetted",
  "no belief",
  "stale: leaf became a table",
  "under attack"
 ],
 "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