Go Back
You can't go any further
Choose this branch
meritocratic
regular
democratic
hot
top
alive
2 posts
Whole Brain Emulation
12 posts
Complexity of Value
Motivations
Futurism
Superstimuli
68
Three AI Safety Related Ideas
Wei_Dai
4y
38
2
Chatbots or set answers, not WBEs
Stuart_Armstrong
7y
0
130
Shard Theory: An Overview
David Udell
4mo
34
85
Two Neglected Problems in Human-AI Safety
Wei_Dai
4y
24
73
But exactly how complex and fragile?
KatjaGrace
3y
32
69
The two-layer model of human values, and problems with synthesizing preferences
Kaj_Sotala
2y
16
65
Why we need a *theory* of human values
Stuart_Armstrong
4y
15
55
Review of 'But exactly how complex and fragile?'
TurnTrout
1y
0
55
Alignment allows "nonrobust" decision-influences and doesn't require robust grading
TurnTrout
21d
27
36
Broad Picture of Human Values
Thane Ruthenis
4mo
5
35
Can there be an indescribable hellworld?
Stuart_Armstrong
3y
19
25
Reversible changes: consider a bucket of water
Stuart_Armstrong
3y
18
12
Towards deconfusing values
Gordon Seidoh Worley
2y
4
7
Working towards AI alignment is better
Johannes C. Mayer
11d
2