Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
94 posts
Rationality
Abstraction
Finite Factored Sets
Causality
Open Problems
Consequentialism
Filtered Evidence
Techniques
Consciousness
Intuition
Free Will
Adding Up to Normality
83 posts
Decision Theory
Goal-Directedness
Utility Functions
Literature Reviews
Quantilization
Mild Optimization
Coherence Arguments
Bounded Rationality
Orthogonality Thesis
Law-Thinking
Coherent Extrapolated Volition
Indexical Information
171
Finite Factored Sets in Pictures
Magdalena Wache
9d
29
62
Builder/Breaker for Deconfusion
abramdemski
2mo
9
141
Finite Factored Sets
Scott Garrabrant
1y
94
32
Counterfactability
Scott Garrabrant
1mo
4
108
Principles for Alignment/Agency Projects
johnswentworth
5mo
20
69
All the posts I will never write
Alexander Gietelink Oldenziel
4mo
8
88
[Intro to brain-like-AGI safety] 15. Conclusion: Open problems, how to help, AMA
Steven Byrnes
7mo
11
86
Testing The Natural Abstraction Hypothesis: Project Update
johnswentworth
1y
17
13
A critical agential account of free will, causation, and physics
jessicata
2y
10
26
Logical Representation of Causal Models
johnswentworth
2y
0
60
Learning Normativity: A Research Agenda
abramdemski
2y
18
12
Is my result wrong? Maths vs intuition vs evolution in learning human preferences
Stuart_Armstrong
3y
11
33
Knowledge, manipulation, and free will
Stuart_Armstrong
2y
15
52
Distributed Decisions
johnswentworth
6mo
4
91
wrapper-minds are the enemy
nostalgebraist
6mo
36
160
Can you control the past?
Joe Carlsmith
1y
93
35
Take 7: You should talk about "the human's utility function" less.
Charlie Steiner
12d
22
20
Quantilizers and Generative Models
Adam Jermyn
5mo
5
46
Notes on "Can you control the past"
So8res
2mo
40
32
Exploring Mild Behaviour in Embedded Agents
Megan Kinniment
5mo
3
48
Three ways that "Sufficiently optimized agents appear coherent" can be false
Wei_Dai
3y
3
38
Buridan's ass in coordination games
jessicata
4y
26
13
Modal Bargaining Agents
orthonormal
7y
0
18
Quantilizers maximize expected utility subject to a conservative cost constraint
jessicata
7y
0
14
Another view of quantilizers: avoiding Goodhart's Law
jessicata
6y
1
19
In memoryless Cartesian environments, every UDT policy is a CDT+SIA policy
jessicata
6y
5
2
Thoughts on Quantilizers
Stuart_Armstrong
5y
0
10
Quantilal control for finite MDPs
Vanessa Kosoy
4y
0