Go Back
You can't go any further
Choose this branch
meritocratic
regular
democratic
hot
top
alive
15 posts
Human Values
11 posts
Shard Theory
Guilt & Shame
Internal Alignment (Human)
Scrupulosity
202
Humans provide an untapped wealth of evidence about alignment
TurnTrout
5mo
92
96
Human values & biases are inaccessible to the genome
TurnTrout
5mo
51
58
What AI Safety Researchers Have Written About the Nature of Human Values
avturchin
3y
3
40
Normativity
abramdemski
2y
11
23
Not for the Sake of Selfishness Alone
lukeprog
11y
20
21
Human values differ as much as values can differ
PhilGoetz
12y
220
18
Silliness
lsusr
6mo
0
17
Inner Goodness
Eliezer Yudkowsky
14y
31
16
Ends: An Introduction
Rob Bensinger
7y
0
16
Thought experiment: coarse-grained VR utopia
cousin_it
5y
48
15
Questions about Value Lock-in, Paternalism, and Empowerment
Sam
1mo
2
12
Preference synthesis illustrated: Star Wars
Stuart_Armstrong
2y
8
7
Modeling humans: what's the point?
Charlie Steiner
2y
1
6
Value Notion - Questions to Ask
aysajan
11mo
0
263
The shard theory of human values
Quintin Pope
3mo
57
127
Shard Theory: An Overview
David Udell
4mo
34
76
Contra shard theory, in the context of the diamond maximizer problem
So8res
2mo
16
68
The Parable Of The Talents
Scott Alexander
7y
10
65
Shard Theory in Nine Theses: a Distillation and Critical Appraisal
LawrenceC
1d
9
44
Team Shard Status Report
David Udell
4mo
8
44
Nate Soares' Replacing Guilt Series compiled in epub Format
lifelonglearner
5y
9
40
Positive values seem more robust and lasting than prohibitions
TurnTrout
3d
9
26
Signaling Guilt
Krieger
2mo
6
9
Typical Minding Guilt/Shame
Unreal
5y
2
2
Rhythm 0 and the Absolution of Responsibility
Precious Oluwatobi Emmanuel
1y
0