thm-power-seeking-optimal.bridge

leaf/bridge · drafted

Statement

The theorem's conclusion, that average-optimal policies tend toward larger sets of recurrent state distributions, is what the informal thesis calls seeking power: keeping options open and staying alive.

Source

Turner et al. 2021, abstract: "optimal policies to tend to seek power over the environment"; Turner and Tadepalli 2022 (arXiv 2206.13477), abstract: "most reward functions have an optimal policy which seeks power by keeping options open and staying alive".

Notes

The landed bridge, with an evidence edge added by the content stage of 2026-10-05: the clean-room's exact orbit count on the paper's own Corollary 6.14 example shows that eroding the human's grip is power-seeking in the one-shot form, which is the reading this bridge asserts. Statement unchanged.

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",
  "attribution unvetted",
  "given ps-cor614-orbit-count@valid"
 ],
 "V": {
  "V_prior": null,
  "display": "2",
  "headline": 2,
  "ref": 2,
  "valid": 2,
  "weaker": "both"
 },
 "belief": {
  "J": 0,
  "mid": "13/20",
  "range": [
   "3/20",
   "1/1"
  ],
  "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.

comment · challenge · estimate · want