Alignment Workspace

oq-anti-wireheading

leaf/step · drafted

Statement

A model of legitimacy yields anti-wireheading results, closely related to results against manipulation of the humans.

Source

projects/deference/note-dump-2026-08-11/notes/li-deference.md, section 0.3, "Wireheading": "I expect some anti-wireheading results based on a model of legitimacy as well."; the earliest statement in the maintainer's 2023 post Meaning & Agency (https://www.lesswrong.com/posts/bnnhypM5MXBHAATLw/meaning-and-agency: "Wireheading is not legitimate.").

Notes

The maintainer's expectation, with the finite report-layer results as its base (the wirehead iff and the stop-gradient identity of legit-finite-defect) and the LI register open; conditioned on the finite iff.

Author and human events

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

No human event has touched this node.

Edges

Above

Ranking (the lens, not the structure)
{
 "status": "open",
 "diagnosis": null,
 "flags": [
  "AI number",
  "given wirehead-iff-finite"
 ],
 "V": {
  "V_prior": null,
  "display": "2",
  "headline": 2,
  "ref": 2,
  "valid": 2,
  "weaker": "both"
 },
 "belief": {
  "J": 0,
  "mid": "7/10",
  "range": [
   "1/5",
   "1/1"
  ],
  "width": "1/1"
 },
 "draft": "ai",
 "root": {
  "status": "open",
  "Pr": {
   "hi": "1/1",
   "lo": "4059/1000000",
   "mid": "92439/156250"
  },
  "value": null,
  "cost": "85/1",
  "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.

comment · challenge · estimate · want