Alignment Workspace

misreport-induces-action

leaf/assumption · drafted

Statement

A hypothesis with enough bargaining weight can, by one false report, induce the aggregated policy to take an action the hypothesis wants.

Source

The maintainer's post Geometric UDT (https://www.lesswrong.com/posts/Gmaq7vMj9NWLyQkEx/geometric-udt), where the bargaining is over reported utilities; that a weighty hypothesis can exploit this by a false report is the filing session's reading of that setting.

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": {
  "J": 0,
  "mid": "7/10",
  "range": [
   "1/5",
   "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