Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
125 posts
World Modeling
Impact Regularization
Anthropics
Exercises / Problem-Sets
Fixed Point Theorems
AIXI
Updateless Decision Theory
Sleeping Beauty Paradox
Cognitive Science
Extraterrestrial Life
Economics
Grabby Aliens
47 posts
Human Values
Shard Theory
Complexity of Value
Gradient Hacking
Heuristics & Biases
Evolution
Value Drift
Information Theory
Gradient Descent
Modularity
Ontology
Biology
573
Where I agree and disagree with Eliezer
paulfchristiano
6mo
205
48
Open technical problem: A Quinean proof of Löb's theorem, for an easier cartoon guide
Andrew_Critch
26d
34
75
«Boundaries», Part 3a: Defining boundaries as directed Markov blankets
Andrew_Critch
1mo
13
67
Humans do acausal coordination all the time
Adam Jermyn
1mo
36
239
Without specific countermeasures, the easiest path to transformative AI likely leads to AI takeover
Ajeya Cotra
5mo
89
84
Less Threat-Dependent Bargaining Solutions?? (3/2)
Diffractor
4mo
7
98
There is essentially one best-validated theory of cognition.
abramdemski
1y
34
77
Abstractions as Redundant Information
johnswentworth
10mo
7
159
Testing The Natural Abstraction Hypothesis: Project Intro
johnswentworth
1y
34
159
My research methodology
paulfchristiano
1y
36
100
Selection Theorems: A Program For Understanding Agents
johnswentworth
1y
23
145
Fixing The Good Regulator Theorem
johnswentworth
1y
25
36
Elementary Infra-Bayesianism
Jan
7mo
2
71
Chu are you?
Adele Lopez
1y
7
78
Shard Theory in Nine Theses: a Distillation and Critical Appraisal
LawrenceC
1d
9
46
Positive values seem more robust and lasting than prohibitions
TurnTrout
3d
9
58
Alignment allows "nonrobust" decision-influences and doesn't require robust grading
TurnTrout
21d
27
95
Contra shard theory, in the context of the diamond maximizer problem
So8res
2mo
16
155
The shard theory of human values
Quintin Pope
3mo
57
140
Shard Theory: An Overview
David Udell
4mo
34
159
Humans provide an untapped wealth of evidence about alignment
TurnTrout
5mo
92
26
Unpacking "Shard Theory" as Hunch, Question, Theory, and Insight
Jacy Reese Anthis
1mo
8
92
Human values & biases are inaccessible to the genome
TurnTrout
5mo
51
55
Gradient Hacker Design Principles From Biology
johnswentworth
3mo
13
35
How are you dealing with ontology identification?
Erik Jenner
2mo
10
47
Understanding and avoiding value drift
TurnTrout
3mo
9
117
A broad basin of attraction around human values?
Wei_Dai
8mo
16
51
General alignment properties
TurnTrout
4mo
2