Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
42 posts
Value Learning
The Pointers Problem
Kolmogorov Complexity
14 posts
Metaethics
Meta-Philosophy
Philosophy
Perceptual Control Theory
67
Don't design agents which exploit adversarial inputs
TurnTrout
1mo
61
80
Beyond Kolmogorov and Shannon
Alexander Gietelink Oldenziel
1mo
14
25
People care about each other even though they have imperfect motivational pointers?
TurnTrout
1mo
25
34
Different perspectives on concept extrapolation
Stuart_Armstrong
8mo
7
109
The Pointers Problem: Human Values Are A Function Of Humans' Latent Variables
johnswentworth
2y
43
68
Parsing Chris Mingard on Neural Networks
Alex Flint
1y
27
22
How an alien theory of mind might be unlearnable
Stuart_Armstrong
11mo
35
38
Normativity
abramdemski
2y
11
10
AIs should learn human preferences, not biases
Stuart_Armstrong
8mo
1
74
Preface to the sequence on value learning
Rohin Shah
4y
6
45
Using vector fields to visualise preferences and make them consistent
MichaelA
2y
32
13
Morally underdefined situations can be deadly
Stuart_Armstrong
1y
8
58
Humans can be assigned any values whatsoever…
Stuart_Armstrong
4y
26
57
Clarifying "AI Alignment"
paulfchristiano
4y
82
45
What Should AI Owe To Us? Accountable and Aligned AI Systems via Contractualist AI Alignment
xuan
3mo
15
32
AI Alignment, Philosophical Pluralism, and the Relevance of Non-Western Philosophy
xuan
1y
21
48
Some Thoughts on Metaphilosophy
Wei_Dai
3y
27
20
Recursive Quantilizers II
abramdemski
2y
15
29
Gricean communication and meta-preferences
Charlie Steiner
2y
0
24
Deconfusing Human Values Research Agenda v1
Gordon Seidoh Worley
2y
12
25
Deliberation as a method to find the "actual preferences" of humans
riceissa
3y
5
25
A theory of human values
Stuart_Armstrong
3y
13
17
The Value Definition Problem
Sammy Martin
3y
6
14
Meta-preferences two ways: generator vs. patch
Charlie Steiner
2y
0
16
Impossible moral problems and moral authority
Charlie Steiner
3y
8
11
Can we make peace with moral indeterminacy?
Charlie Steiner
3y
8
16
RFC: Philosophical Conservatism in AI Alignment Research
Gordon Seidoh Worley
4y
13
15
My take on agent foundations: formalizing metaphilosophical competence
zhukeepa
4y
6