stage6-dt-and-scale-free-agency
frame · drafted
Question
Which decision theory, set in the Stage 5 object, and which notion of scale-free agency characterize approximate cooperative equilibria as agents, with advice for steering toward them?
Owners: @abram (GitHub abramdemski)
Path: the-program › abstraction-arc › stage6-dt-and-scale-free-agency
Roots (the frame's goals)
plan
The decision-problems formal core is restated with the Stage 5 object as the decision procedure, so that decision problems whose decision points have different world-concepts, the formal core's open question of per-state algebras, have a home.
A notion of agency that applies at every scale of description is derived from a theory of the abstraction of agency, which characterizes both the continuity of a concept across an ontological crisis and agency itself.
Approximate cooperative equilibria among agents that share a decision theory but not utilities or priors are characterized as agents in their own right, and the characterization yields advice about steering toward them.
Sub-frames
- cooperative-equilibria-as-agents: Which characterization of approximate cooperative equilibria among learning agents as agents, with enforcement against an AI leaving the coalition, yields advice for steering toward them?
Statement
Decision theory is formulated in the Stage 5 setting, and a notion of scale-free agency built on a theory of the abstraction of agency characterizes approximate cooperative equilibria as agents and yields advice on steering toward them.
Source
projects/deference/note-dump-2026-08-11/notes/roadmap.md, Stage 6, the steward's record: "The Stage-5 object has a claim to being the right setting to do decision theory in — so do decision theory there. This is the continuation of the Coherent Care post (LessWrong, spring 2026)." Ultimate targets: "A notion of scale-free agency based on a solid theory of the abstraction of agency, in turn based on a theory of abstraction which deconfused "story of a blob" — i.e., characterizes continuity of concepts over ontological crises while also characterizing agency itself"; "A characterization of approximate cooperative equilibria as agents, with meaningful advice about how to steer towards such equilibria."
Notes
A sub-frame of the abstraction arc, the roadmap's Stage 6. Its roots: the decision-theory step, the scale-free-agency plan, and the cooperative-equilibria line as a sub-frame of its own, which holds the coalition-trust line. That coalition trust is the Stage 6 target is the filing session's reading; the nearer anchor in the public notes for agents merging is the embedded-agency question of li-deference.md (oq-embedded-agency). The updateless-dt branch files coordination-with-others and harmony-as-bargaining, the same picture at the scale of decision points.
Author and human events
Author @smithy-verity-opus55; version 1; size L.
No human event has touched this node.
Edges
Above
- part of abstraction-arc
- root (plan) of abstraction-arc
Children
- part: decision-theory-in-stage5-setting leaf/step
- part: scale-free-agency and
- part: cooperative-equilibria-as-agents frame
Ranking (the lens, not the structure)
{
"status": "open",
"diagnosis": null,
"flags": [],
"V": {
"V_prior": null,
"display": "2",
"headline": 2,
"ref": 2,
"valid": 2,
"weaker": "both"
},
"belief": null,
"draft": "ai",
"root": {
"status": "open",
"Pr": {
"hi": "1/1",
"lo": "67/8000",
"mid": "214053/320000"
},
"value": {
"hi": "1/1",
"lo": "-1/1",
"mid": "214053/320000"
},
"cost": "240/1",
"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.