legitimacy-blocks-wireheading
leaf/step · drafted
Statement
Legitimacy blocks wireheading and allows a form of corrigibility.
Source
projects/deference/note-dump-2026-08-11/related-chats/2026-07-05__theory-of-legitimacy__f57f5f2d.md, turn 7, the maintainer: "Embedded Agents can adhere to Reflection, but then they'll wirehead, manipulate, accept manipulation, accept arbitrary self-fulfilling prophecies, do drugs, become hedonic utilitarians"; legitimacy, in turn 5, is the correction to Reflection that blocks this. The corrigibility half is the filing session's reading.
Notes
A one-line claim, filed because it states the legitimacy-corrigibility link and because the June toy proves its wireheading half in a finite frame.
Author and human events
Author @smithy-verity; version 1; size S.
No human event has touched this node.
Edges
Above
- given of wirehead-decline-toy
- part of legitimacy-detection
- root (shared-claim) of legitimacy-detection
- given wirehead-decline-toy
Ranking (the lens, not the structure)
{
"status": "open",
"diagnosis": null,
"flags": [
"AI number",
"given wirehead-decline-toy"
],
"V": {
"V_prior": null,
"display": "2",
"headline": 2,
"ref": 2,
"valid": 2,
"weaker": "both"
},
"belief": {
"J": 0,
"mid": "59/100",
"range": [
"9/100",
"1/1"
],
"width": "1/1"
},
"draft": "ai",
"root": {
"status": "open",
"Pr": {
"hi": "1/1",
"lo": "3551/40000",
"mid": "7089/10000"
},
"value": null,
"cost": "33/1",
"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.