LESSWRONG
LW

Human Values

Edited by plex last updated 16th Sep 2021

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 , and could be extrapolated into a wide variety of forms.

1

1

Posts tagged Human Values

259The shard theory of human values

Quintin Pope, TurnTrout

3y

67

95Human values & biases are inaccessible to the genome

3y

54

63Multi-agent predictive minds and AI alignment

7y

18

52What AI Safety Researchers Have Written About the Nature of Human Values

7y

3

41Requirements for a Basin of Attraction to Alignment

1y

12

335. Moral Value for Sentient Animals? Alas, Not Yet

2y

41

2y

5

18Ends: An Introduction

10y

0

16Alignment has a Basin of Attraction: Beyond the Orthogonality Thesis

1y

15

126. The Mutable Values Problem in Value Learning and CEV

2y

0

5Utilitarianism and the replaceability of desires and attachments

1y

2

88[Valence series] 2. Valence & Normativity

2y

7

32How Would an Utopia-Maximizer Look Like?

2y

23

104. A Moral Case for Evolved-Sapience-Chauvinism

2y

0

167Shard Theory: An Overview

3y

34

Load More (15/178)

Add Posts