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
777
Where I agree and disagree with Eliezer
paulfchristiano
6mo
205
43
Open technical problem: A Quinean proof of Löb's theorem, for an easier cartoon guide
Andrew_Critch
26d
34
310
Without specific countermeasures, the easiest path to transformative AI likely leads to AI takeover
Ajeya Cotra
5mo
89
56
«Boundaries», Part 3a: Defining boundaries as directed Markov blankets
Andrew_Critch
1mo
13
51
Humans do acausal coordination all the time
Adam Jermyn
1mo
36
69
Less Threat-Dependent Bargaining Solutions?? (3/2)
Diffractor
4mo
7
88
There is essentially one best-validated theory of cognition.
abramdemski
1y
34
103
Selection Theorems: A Program For Understanding Agents
johnswentworth
1y
23
145
Testing The Natural Abstraction Hypothesis: Project Intro
johnswentworth
1y
34
148
My research methodology
paulfchristiano
1y
36
62
Abstractions as Redundant Information
johnswentworth
10mo
7
38
Elementary Infra-Bayesianism
Jan
7mo
2
123
Fixing The Good Regulator Theorem
johnswentworth
1y
25
95
Frequent arguments about alignment
John Schulman
1y
16
70
Shard Theory in Nine Theses: a Distillation and Critical Appraisal
LawrenceC
1d
9
42
Positive values seem more robust and lasting than prohibitions
TurnTrout
3d
9
55
Alignment allows "nonrobust" decision-influences and doesn't require robust grading
TurnTrout
21d
27
202
The shard theory of human values
Quintin Pope
3mo
57
84
Contra shard theory, in the context of the diamond maximizer problem
So8res
2mo
16
175
Humans provide an untapped wealth of evidence about alignment
TurnTrout
5mo
92
29
Unpacking "Shard Theory" as Hunch, Question, Theory, and Insight
Jacy Reese Anthis
1mo
8
130
Shard Theory: An Overview
David Udell
4mo
34
7
Working towards AI alignment is better
Johannes C. Mayer
11d
2
92
Human values & biases are inaccessible to the genome
TurnTrout
5mo
51
52
Gradient Hacker Design Principles From Biology
johnswentworth
3mo
13
33
How are you dealing with ontology identification?
Erik Jenner
2mo
10
40
Understanding and avoiding value drift
TurnTrout
3mo
9
105
A broad basin of attraction around human values?
Wei_Dai
8mo
16