LESSWRONGTags
LW

Human Values

EditHistory
Discussion (0)
Help improve this page (2 flags)
EditHistory
Discussion (0)
Help improve this page (2 flags)
Human Values
Random Tag
Contributors
3plex

Human Values are the things we care about, and would want an aligned superintelligence to look after and support. It is suspected that true human values are highly complex, and could be extrapolated into a wide variety of forms.

Posts tagged Human Values
16
241The shard theory of human valuesΩ
Quintin Pope, TurnTrout
9mo
Ω
63
14
88Human values & biases are inaccessible to the genomeΩ
TurnTrout
1y
Ω
51
5
50What AI Safety Researchers Have Written About the Nature of Human Values
avturchin
4y
3
5
12Ends: An Introduction
Rob Bensinger
8y
0
3
152Shard Theory: An OverviewΩ
David Udell
10mo
Ω
34
3
23Review: Foragers, Farmers, and Fossil Fuels
LRudL
2y
7
3
21How evolution succeeds and fails at value alignment
Ocracoke
10mo
2
3
10Brain-over-body biases, and the embodied value problem in AI alignmentΩ
geoffreymiller
9mo
Ω
6
3
1Intent alignment should not be the goal for AGI x-risk reduction
John Nay
8mo
10
2
228My Model Of EA Burnout
LoganStrohl
5mo
48
2
189Humans provide an untapped wealth of evidence about alignmentΩ
TurnTrout, Quintin Pope
10mo
Ω
93
2
106A broad basin of attraction around human values?Ω
Wei Dai
1y
Ω
17
2
63The Computational Anatomy of Human ValuesΩ
beren
2mo
Ω
30
2
57Alignment allows "nonrobust" decision-influences and doesn't require robust gradingΩ
TurnTrout
7mo
Ω
41
2
52Book Review: A Pattern Language by Christopher Alexander
lincolnquirk
2y
8
Load More (15/94)
Add Posts