ps-trained-systems-seek-power.complete
leaf/completeness · drafted
Statement
No step beyond the toy theorem and the three listed relaxations is needed to carry the power-seeking conclusion to the policies the training procedures produce.
Source
Turner et al. 2021, closing paragraph, and the two sequels as read for the bridges.
Author and human events
Author @smithy-verity; version 1; size S.
No human event has touched this node.
Edges
Above
- part of ps-trained-systems-seek-power
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": {
"J": 0,
"mid": "9/20",
"range": [
"0/1",
"19/20"
],
"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.