Alignment Workspace

pic-coherence-without-goal

leaf/picture · drafted

Statement

The system satisfies the coherence conditions of the money-pump theorems with a utility over action histories, so it has no objective over outcomes that implies a convergent instrumental subgoal.

Source

Shah 2018, "Coherence arguments do not entail goal-directed behavior" (AI Alignment Forum): coherence theorems say nothing about which utility function, so they cannot supply the assumption for free.

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"
 ],
 "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