AI ALIGNMENT FORUM
AF

1653
Wikitags

Coordination / Cooperation

Edited by Ruby, et al. last updated 5th Aug 2020

Coordination is the challenge of distinct actors being able to jointly choose their actions to achieve a favorable outcome. An example of easy coordination is coordinating to drive on the same side of the road. A hard example is coordinating everyone to move a superior yet different social media platform. Many failures of civilization are failures of coordination. A closely related concept is that of cooperation – multiple actors choosing their actions in ways that maximize collective value despite the temptation of greater short-term individual gain by acting to the detriment of the group/other actors. The Prisoner's Dilemma is the canonical cooperation/defection game, but the term is used in other games too, e.g. Stag Hunt.

Coordination and cooperation are fundamental concepts in Game Theory. LessWrong discussion has long been interested in overcoming the gnarly coordination and cooperation challenges that prevent many improvements to optimizing the world. There is also interest because failures to coordinate/cooperate are likely causes of existential risks such as AI Risk or nuclear war.

See also: Game Theory, Moloch

Another related term in this space is collective action problem. 

Related Sequences: Kickstarter for Coordinated Action

Subscribe
Discussion
2
Subscribe
Discussion
2
Posts tagged Coordination / Cooperation
68Consciousness as a conflationary alliance term for intrinsically valued internal experiences
Andrew_Critch
2y
5
76Unifying Bargaining Notions (1/2)
Diffractor
3y
8
93What Multipolar Failure Looks Like, and Robust Agent-Agnostic Processes (RAAPs)
Andrew_Critch
5y
49
56AI coordination needs clear wins
evhub
3y
5
16Some constructions for proof-based cooperation without Löb
James Payor
3y
1
38My Overview of the AI Alignment Landscape: A Bird's Eye View
Neel Nanda
4y
4
31Announcing the Alignment of Complex Systems Research Group
Jan_Kulveit, technicalities
3y
11
34What counts as defection?
TurnTrout
5y
9
30A Narrow Path: a plan to deal with AI extinction risk
Andrea_Miotti, davekasten, Tolga
1y
0
23My Overview of the AI Alignment Landscape: Threat Models
Neel Nanda
4y
3
9Sections 1 & 2: Introduction, Strategy and Governance
JesseClifton
6y
2
16AI Constitutions are a tool to reduce societal scale risk
Sammy Martin
1y
2
12Response to Dileep George: AGI safety warrants planning ahead
Steven Byrnes
1y
4
8Löbian emotional processing of emergent cooperation: an example
Andrew_Critch
3y
0
6Sections 3 & 4: Credibility, Peaceful Bargaining Mechanisms
JesseClifton
6y
0
Load More (15/32)
Add Posts