Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
26 posts
Human Values
Shard Theory
Guilt & Shame
Internal Alignment (Human)
Scrupulosity
84 posts
Sex & Gender
Fun Theory
Complexity of Value
Coherent Extrapolated Volition
148
Humans provide an untapped wealth of evidence about alignment
TurnTrout
5mo
92
141
The shard theory of human values
Quintin Pope
3mo
57
133
Shard Theory: An Overview
David Udell
4mo
34
92
Contra shard theory, in the context of the diamond maximizer problem
So8res
2mo
16
88
Human values & biases are inaccessible to the genome
TurnTrout
5mo
51
75
Shard Theory in Nine Theses: a Distillation and Critical Appraisal
LawrenceC
1d
9
52
Normativity
abramdemski
2y
11
45
Not for the Sake of Selfishness Alone
lukeprog
11y
20
44
Positive values seem more robust and lasting than prohibitions
TurnTrout
3d
9
42
What AI Safety Researchers Have Written About the Nature of Human Values
avturchin
3y
3
38
Thought experiment: coarse-grained VR utopia
cousin_it
5y
48
33
Human values differ as much as values can differ
PhilGoetz
12y
220
32
Team Shard Status Report
David Udell
4mo
8
26
Preference synthesis illustrated: Star Wars
Stuart_Armstrong
2y
8
108
Joy in the Merely Real
Eliezer Yudkowsky
14y
43
97
The Hidden Complexity of Wishes
Eliezer Yudkowsky
15y
136
91
Interpersonal Entanglement
Eliezer Yudkowsky
13y
167
86
The two-layer model of human values, and problems with synthesizing preferences
Kaj_Sotala
2y
16
86
The Gift We Give To Tomorrow
Eliezer Yudkowsky
14y
99
83
But exactly how complex and fragile?
KatjaGrace
3y
32
75
Complexity of Value ≠ Complexity of Outcome
Wei_Dai
12y
232
75
A Rationalist's Account of Objectification?
lukeprog
11y
327
71
Review of 'But exactly how complex and fragile?'
TurnTrout
1y
0
70
Sayeth the Girl
Alicorn
13y
503
69
Quantified Risks of Gay Male Sex
pianoforte611
8y
40
67
Value is Fragile
Eliezer Yudkowsky
13y
111
66
Challenges to Yudkowsky's Pronoun Reform Proposal
Zack_M_Davis
9mo
55
61
LW Women- Female privilege
daenerys
9y
236