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
100
Towards a New Impact Measure
TurnTrout
4y
159
90
Reframing Impact
TurnTrout
3y
15
73
Worrying about the Vase: Whitelisting
TurnTrout
4y
26
70
Topological Fixed Point Exercises
Scott Garrabrant
4y
52
64
Deducing Impact
TurnTrout
3y
26
62
Value Impact
TurnTrout
3y
8
62
World State is the Wrong Abstraction for Impact
TurnTrout
3y
19
61
Attainable Utility Preservation: Empirical Results
TurnTrout
2y
8
60
Attainable Utility Theory: Why Things Matter
TurnTrout
3y
24
60
Best reasons for pessimism about impact of impact measures?
TurnTrout
3y
55
58
Fixed Point Exercises
Scott Garrabrant
4y
8
53
Appendix: how a subagent could get powerful
Stuart_Armstrong
2y
17
51
Attainable Utility Landscape: How The World Is Changed
TurnTrout
2y
7
50
The Gears of Impact
TurnTrout
3y
16
777
Where I agree and disagree with Eliezer
paulfchristiano
6mo
205
310
Without specific countermeasures, the easiest path to transformative AI likely leads to AI takeover
Ajeya Cotra
5mo
89
148
My research methodology
paulfchristiano
1y
36
145
Testing The Natural Abstraction Hypothesis: Project Intro
johnswentworth
1y
34
123
Fixing The Good Regulator Theorem
johnswentworth
1y
25
103
Selection Theorems: A Program For Understanding Agents
johnswentworth
1y
23
95
Frequent arguments about alignment
John Schulman
1y
16
88
There is essentially one best-validated theory of cognition.
abramdemski
1y
34
73
The Goldbach conjecture is probably correct; so was Fermat's last theorem
Stuart_Armstrong
2y
27
69
Less Threat-Dependent Bargaining Solutions?? (3/2)
Diffractor
4mo
7
62
Abstractions as Redundant Information
johnswentworth
10mo
7
60
Chu are you?
Adele Lopez
1y
7
57
What Selection Theorems Do We Expect/Want?
johnswentworth
1y
11
56
«Boundaries», Part 3a: Defining boundaries as directed Markov blankets
Andrew_Critch
1mo
13