Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
41 posts
Impact Regularization
Exercises / Problem-Sets
Fixed Point Theorems
84 posts
World Modeling
Anthropics
AIXI
Updateless Decision Theory
Sleeping Beauty Paradox
Cognitive Science
Extraterrestrial Life
Economics
Grabby Aliens
Infinity
61
Attainable Utility Preservation: Empirical Results
TurnTrout
2y
8
14
Using modal fixed points to formalize logical causality
cousin_it
5y
0
38
Attainable Utility Preservation: Concepts
TurnTrout
2y
20
33
Iteration Fixed Point Exercises
Scott Garrabrant
4y
12
60
Attainable Utility Theory: Why Things Matter
TurnTrout
3y
24
30
Overcoming Clinginess in Impact Measures
TurnTrout
4y
9
40
Diagonalization Fixed Point Exercises
Scott Garrabrant
4y
23
73
Worrying about the Vase: Whitelisting
TurnTrout
4y
26
17
[AN #68]: The attainable utility theory of impact
Rohin Shah
3y
0
32
When wishful thinking works
AlexMennen
4y
1
28
How Low Should Fruit Hang Before We Pick It?
TurnTrout
2y
9
12
Appendix: mathematics of indexical impact measures
Stuart_Armstrong
2y
0
64
Deducing Impact
TurnTrout
3y
26
28
Attainable Utility Preservation: Scaling to Superhuman
TurnTrout
2y
21
43
Open technical problem: A Quinean proof of Löb's theorem, for an easier cartoon guide
Andrew_Critch
26d
34
24
Traps of Formalization in Deconfusion
adamShimi
1y
7
56
«Boundaries», Part 3a: Defining boundaries as directed Markov blankets
Andrew_Critch
1mo
13
310
Without specific countermeasures, the easiest path to transformative AI likely leads to AI takeover
Ajeya Cotra
5mo
89
51
Humans do acausal coordination all the time
Adam Jermyn
1mo
36
69
Less Threat-Dependent Bargaining Solutions?? (3/2)
Diffractor
4mo
7
145
Testing The Natural Abstraction Hypothesis: Project Intro
johnswentworth
1y
34
777
Where I agree and disagree with Eliezer
paulfchristiano
6mo
205
14
Deliberation Everywhere: Simple Examples
Oliver Sourbut
5mo
0
8
An implementation of modal UDT
Benya_Fallenstein
7y
0
0
Corrigibility for AIXI via double indifference
Stuart_Armstrong
6y
0
11
Updatelessness and Son of X
Scott Garrabrant
6y
0
1
The Doomsday argument in anthropic decision theory
Stuart_Armstrong
5y
0
18
UDT as a Nash Equilibrium
cousin_it
4y
17