Go Back
You can't go any further
You can't go any further
meritocratic
regular
democratic
hot
top
alive
33 posts
Value Learning
4 posts
Kolmogorov Complexity
68
Preface to the sequence on value learning
Rohin Shah
4y
6
64
Clarifying "AI Alignment"
paulfchristiano
4y
82
56
Humans can be assigned any values whatsoever…
Stuart_Armstrong
4y
26
52
Intuitions about goal-directed behavior
Rohin Shah
4y
15
50
Policy Alignment
abramdemski
4y
25
50
The easy goal inference problem is still hard
paulfchristiano
4y
19
49
What is ambitious value learning?
Rohin Shah
4y
28
49
Conclusion to the sequence on value learning
Rohin Shah
3y
20
46
Future directions for ambitious value learning
Rohin Shah
4y
9
46
Normativity
abramdemski
2y
11
42
Different perspectives on concept extrapolation
Stuart_Armstrong
8mo
7
41
Using vector fields to visualise preferences and make them consistent
MichaelA
2y
32
34
Human-AI Interaction
Rohin Shah
3y
10
30
Following human norms
Rohin Shah
3y
10
67
Parsing Chris Mingard on Neural Networks
Alex Flint
1y
27
60
Beyond Kolmogorov and Shannon
Alexander Gietelink Oldenziel
1mo
14
1
Humans can be assigned any values whatsoever...
Stuart_Armstrong
5y
0
0
Kolmogorov complexity makes reward learning worse
Stuart_Armstrong
5y
0