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
50
Different perspectives on concept extrapolation
Stuart_Armstrong
8mo
7
30
How an alien theory of mind might be unlearnable
Stuart_Armstrong
11mo
35
20
Value extrapolation, concept extrapolation, model splintering
Stuart_Armstrong
9mo
1
54
Normativity
abramdemski
2y
11
21
Morally underdefined situations can be deadly
Stuart_Armstrong
1y
8
10
AIs should learn human preferences, not biases
Stuart_Armstrong
8mo
1
71
Clarifying "AI Alignment"
paulfchristiano
4y
82
62
Preface to the sequence on value learning
Rohin Shah
4y
6
39
Other versions of "No free lunch in value learning"
Stuart_Armstrong
2y
0
56
Conclusion to the sequence on value learning
Rohin Shah
3y
20
37
Using vector fields to visualise preferences and make them consistent
MichaelA
2y
32
28
Learning human preferences: black-box, white-box, and structured white-box access
Stuart_Armstrong
2y
9
53
Intuitions about goal-directed behavior
Rohin Shah
4y
15
54
Humans can be assigned any values whatsoever…
Stuart_Armstrong
4y
26
40
Beyond Kolmogorov and Shannon
Alexander Gietelink Oldenziel
1mo
14
66
Parsing Chris Mingard on Neural Networks
Alex Flint
1y
27
1
Humans can be assigned any values whatsoever...
Stuart_Armstrong
5y
0
0
Kolmogorov complexity makes reward learning worse
Stuart_Armstrong
5y
0