Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
47 posts
Abstraction
Finite Factored Sets
Causality
Open Problems
Intuition
Consciousness
Free Will
Incentives
Adding Up to Normality
47 posts
Rationality
Filtered Evidence
Consequentialism
Techniques
Deontology
148
Finite Factored Sets in Pictures
Magdalena Wache
9d
29
137
Finite Factored Sets
Scott Garrabrant
1y
94
130
Saving Time
Scott Garrabrant
1y
19
83
Testing The Natural Abstraction Hypothesis: Project Update
johnswentworth
1y
17
82
Public Static: What is Abstraction?
johnswentworth
2y
18
81
[Intro to brain-like-AGI safety] 15. Conclusion: Open problems, how to help, AMA
Steven Byrnes
7mo
11
76
Writing Causal Models Like We Write Programs
johnswentworth
2y
8
59
Pointing to a Flower
johnswentworth
2y
18
50
Open Problems in AI X-Risk [PAIS #5]
Dan H
6mo
3
47
Computational Model: Causal Diagrams with Symmetry
johnswentworth
3y
29
46
A second example of conditional orthogonality in finite factored sets
DanielFilan
1y
0
43
(A -> B) -> A in Causal DAGs
johnswentworth
2y
11
43
Modeling AGI Safety Frameworks with Causal Influence Diagrams
Ramana Kumar
3y
6
42
Motivating Abstraction-First Decision Theory
johnswentworth
2y
16
169
What's Up With Confusingly Pervasive Consequentialism?
Raemon
11mo
88
115
Principles for Alignment/Agency Projects
johnswentworth
5mo
20
113
Problem relaxation as a tactic
TurnTrout
2y
8
85
Thinking About Filtered Evidence Is (Very!) Hard
abramdemski
2y
29
76
Learning Normativity: A Research Agenda
abramdemski
2y
18
70
Search-in-Territory vs Search-in-Map
johnswentworth
1y
13
70
Builder/Breaker for Deconfusion
abramdemski
2mo
9
65
Distributed Decisions
johnswentworth
6mo
4
64
Better priors as a safety problem
paulfchristiano
2y
7
54
Mathematical Mindset
komponisto
4y
5
52
All the posts I will never write
Alexander Gietelink Oldenziel
4mo
8
43
Probability theory and logical induction as lenses
Alex Flint
1y
7
43
A simple example of conditional orthogonality in finite factored sets
DanielFilan
1y
3
41
Do Sufficiently Advanced Agents Use Logic?
abramdemski
3y
11