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
54
Humans can be assigned any values whatsoever…
Stuart_Armstrong
4y
26
10
AIs should learn human preferences, not biases
Stuart_Armstrong
8mo
1
37
Human-AI Interaction
Rohin Shah
3y
10
54
What is ambitious value learning?
Rohin Shah
4y
28
21
Morally underdefined situations can be deadly
Stuart_Armstrong
1y
8
31
Thoughts on implementing corrigible robust alignment
Steven Byrnes
3y
2
28
Learning human preferences: black-box, white-box, and structured white-box access
Stuart_Armstrong
2y
9
16
Values, Valence, and Alignment
Gordon Seidoh Worley
3y
4
9
What's the dream for giving natural language commands to AI?
Charlie Steiner
3y
8
53
Intuitions about goal-directed behavior
Rohin Shah
4y
15
45
Future directions for ambitious value learning
Rohin Shah
4y
9
22
The AI is the model
Charlie Steiner
3y
1
39
Other versions of "No free lunch in value learning"
Stuart_Armstrong
2y
0
14
Future directions for narrow value learning
Rohin Shah
3y
4
40
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
66
Parsing Chris Mingard on Neural Networks
Alex Flint
1y
27