Go Back
Choose this branch
You can't go any further
meritocratic
regular
democratic
hot
top
alive
37 posts
Value Learning
Kolmogorov Complexity
5 posts
The Pointers Problem
60
Beyond Kolmogorov and Shannon
Alexander Gietelink Oldenziel
1mo
14
42
Different perspectives on concept extrapolation
Stuart_Armstrong
8mo
7
67
Parsing Chris Mingard on Neural Networks
Alex Flint
1y
27
26
How an alien theory of mind might be unlearnable
Stuart_Armstrong
11mo
35
46
Normativity
abramdemski
2y
11
14
Value extrapolation, concept extrapolation, model splintering
Stuart_Armstrong
9mo
1
17
Morally underdefined situations can be deadly
Stuart_Armstrong
1y
8
10
AIs should learn human preferences, not biases
Stuart_Armstrong
8mo
1
68
Preface to the sequence on value learning
Rohin Shah
4y
6
64
Clarifying "AI Alignment"
paulfchristiano
4y
82
41
Using vector fields to visualise preferences and make them consistent
MichaelA
2y
32
56
Humans can be assigned any values whatsoever…
Stuart_Armstrong
4y
26
52
Intuitions about goal-directed behavior
Rohin Shah
4y
15
49
Conclusion to the sequence on value learning
Rohin Shah
3y
20
60
Don't design agents which exploit adversarial inputs
TurnTrout
1mo
61
32
People care about each other even though they have imperfect motivational pointers?
TurnTrout
1mo
25
104
The Pointers Problem: Human Values Are A Function Of Humans' Latent Variables
johnswentworth
2y
43
18
Stable Pointers to Value II: Environmental Goals
abramdemski
4y
2
15
Stable Pointers to Value: An Agent Embedded in Its Own Utility Function
abramdemski
5y
9