Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
5 posts
Shard Theory
Internal Alignment (Human)
22 posts
Complexity of Value
Value Drift
Ontology
Whole Brain Emulation
Motivations
LessWrong Review
Psychology
Futurism
General Alignment Properties
Superstimuli
155
The shard theory of human values
Quintin Pope
3mo
57
95
Contra shard theory, in the context of the diamond maximizer problem
So8res
2mo
16
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
26
Unpacking "Shard Theory" as Hunch, Question, Theory, and Insight
Jacy Reese Anthis
1mo
8
159
Humans provide an untapped wealth of evidence about alignment
TurnTrout
5mo
92
140
Shard Theory: An Overview
David Udell
4mo
34
99
Two Neglected Problems in Human-AI Safety
Wei_Dai
4y
24
88
The two-layer model of human values, and problems with synthesizing preferences
Kaj_Sotala
2y
16
86
But exactly how complex and fragile?
KatjaGrace
3y
32
78
Three AI Safety Related Ideas
Wei_Dai
4y
38
73
Review of 'But exactly how complex and fragile?'
TurnTrout
1y
0
71
Test Cases for Impact Regularisation Methods
DanielFilan
3y
5
67
Why we need a *theory* of human values
Stuart_Armstrong
4y
15
58
Alignment allows "nonrobust" decision-influences and doesn't require robust grading
TurnTrout
21d
27
51
General alignment properties
TurnTrout
4mo
2
47
Understanding and avoiding value drift
TurnTrout
3mo
9
42
Can there be an indescribable hellworld?
Stuart_Armstrong
3y
19
38
Broad Picture of Human Values
Thane Ruthenis
4mo
5