Go Back
You can't go any further
Choose this branch
meritocratic
regular
democratic
hot
top
alive
0 posts
LessWrong Review
16 posts
Complexity of Value
Value Drift
Whole Brain Emulation
Motivations
Futurism
Superstimuli
52
Alignment allows "nonrobust" decision-influences and doesn't require robust grading
TurnTrout
21d
27
33
Understanding and avoiding value drift
TurnTrout
3mo
9
120
Shard Theory: An Overview
David Udell
4mo
34
50
The two-layer model of human values, and problems with synthesizing preferences
Kaj_Sotala
2y
16
2
Chatbots or set answers, not WBEs
Stuart_Armstrong
7y
0
15
Would I think for ten thousand years?
Stuart_Armstrong
3y
13
71
Two Neglected Problems in Human-AI Safety
Wei_Dai
4y
24
9
Towards deconfusing values
Gordon Seidoh Worley
2y
4
34
Broad Picture of Human Values
Thane Ruthenis
4mo
5
12
Working towards AI alignment is better
Johannes C. Mayer
11d
2
37
Review of 'But exactly how complex and fragile?'
TurnTrout
1y
0
28
Can there be an indescribable hellworld?
Stuart_Armstrong
3y
19
58
Three AI Safety Related Ideas
Wei_Dai
4y
38
60
But exactly how complex and fragile?
KatjaGrace
3y
32