Go Back
You can't go any further
You can't go any further
meritocratic
regular
democratic
hot
top
alive
4 posts
The Pointers Problem
59 posts
Value Learning
93
The Pointers Problem: Human Values Are A Function Of Humans' Latent Variables
johnswentworth
2y
43
23
Stable Pointers to Value II: Environmental Goals
abramdemski
4y
2
20
Stable Pointers to Value: An Agent Embedded in Its Own Utility Function
abramdemski
5y
9
19
Stable Pointers to Value III: Recursive Quantilization
abramdemski
4y
4
97
The Urgent Meta-Ethics of Friendly Artificial Intelligence
lukeprog
11y
252
74
Where do selfish values come from?
Wei_Dai
11y
62
68
Clarifying "AI Alignment"
paulfchristiano
4y
82
64
Why we need a *theory* of human values
Stuart_Armstrong
4y
15
59
Preface to the sequence on value learning
Rohin Shah
4y
6
58
The E-Coli Test for AI Alignment
johnswentworth
4y
24
54
Conclusion to the sequence on value learning
Rohin Shah
3y
20
52
What is ambitious value learning?
Rohin Shah
4y
28
51
Humans can be assigned any values whatsoever…
Stuart_Armstrong
4y
26
51
Intuitions about goal-directed behavior
Rohin Shah
4y
15
50
The easy goal inference problem is still hard
paulfchristiano
4y
19
48
Different perspectives on concept extrapolation
Stuart_Armstrong
8mo
7
45
Two questions about CEV that worry me
cousin_it
12y
142
42
Since figuring out human values is hard, what about, say, monkey values?
shminux
2y
13