Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
26 posts
Game Theory
Center on Long-Term Risk (CLR)
Risks of Astronomical Suffering (S-risks)
Mechanism Design
Suffering
Fairness
Blackmail / Extortion
Group Rationality
Terminology / Jargon (meta)
Reading Group
20 posts
Research Agendas
Goal Factoring
Mind Crime
204
Unifying Bargaining Notions (1/2)
Diffractor
4mo
38
155
«Boundaries», Part 1: a key missing concept from utility theory
Andrew_Critch
4mo
26
131
"Zero Sum" is a misnomer.
abramdemski
2y
35
120
Unifying Bargaining Notions (2/2)
Diffractor
4mo
11
102
What counts as defection?
TurnTrout
2y
21
101
The Commitment Races problem
Daniel Kokotajlo
3y
39
98
Threat-Resistant Bargaining Megapost: Introducing the ROSE Value
Diffractor
2mo
11
86
When Hindsight Isn't 20/20: Incentive Design With Imperfect Credit Allocation
johnswentworth
2y
24
79
Siren worlds and the perils of over-optimised search
Stuart_Armstrong
8y
417
60
Reducing collective rationality to individual optimization in common-payoff games using MCMC
jessicata
4y
12
54
«Boundaries», Part 3b: Alignment problems in terms of boundaries
Andrew_Critch
6d
2
50
Book report: Theory of Games and Economic Behavior (von Neumann & Morgenstern)
Nisan
2y
4
48
Nash equilibriums can be arbitrarily bad
Stuart_Armstrong
3y
24
44
My take on higher-order game theory
Nisan
1y
6
231
On how various plans miss the hard bits of the alignment challenge
So8res
5mo
81
155
Some conceptual alignment research projects
Richard_Ngo
3mo
14
127
Thoughts on Human Models
Ramana Kumar
3y
32
122
Our take on CHAI’s research agenda in under 1500 words
Alex Flint
2y
19
82
Research Agenda v0.9: Synthesising a human's preferences into a utility function
Stuart_Armstrong
3y
25
77
The Learning-Theoretic AI Alignment Research Agenda
Vanessa Kosoy
4y
39
69
Research agenda update
Steven Byrnes
1y
40
45
Immobile AI makes a move: anti-wireheading, ontology change, and model splintering
Stuart_Armstrong
1y
3
44
Technical AGI safety research outside AI
Richard_Ngo
3y
3
44
Research Agenda in reverse: what *would* a solution look like?
Stuart_Armstrong
3y
25
42
New safety research agenda: scalable agent alignment via reward modeling
Vika
4y
13
40
Ultra-simplified research agenda
Stuart_Armstrong
3y
4
38
Resources for AI Alignment Cartography
Gyrodiot
2y
8
36
Why I am not currently working on the AAMLS agenda
jessicata
5y
1