This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
Stuart_Armstrong
LW
Login
Stuart_Armstrong
Stuart_Armstrong's Posts
Sorted by New
15
Toy model piece #2: Combining short and long range partial preferences
Ω
Stuart_Armstrong
17d
Ω
0
20
Preferences as an (instinctive) stance
Ω
Stuart_Armstrong
19d
Ω
4
23
Practical consequences of impossibility of value learning
Ω
Stuart_Armstrong
22d
Ω
13
13
Very different, very adequate outcomes
Ω
Stuart_Armstrong
22d
Ω
10
12
Toy model piece #1: Partial preferences revisited
Ω
Stuart_Armstrong
1mo
Ω
18
16
Normalising utility as willingness to pay
Ω
Stuart_Armstrong
1mo
Ω
9
13
Intertheoretic utility comparison: examples
Ω
Stuart_Armstrong
1mo
Ω
1
16
Indifference: multiple changes, multiple agents
Ω
Stuart_Armstrong
2mo
Ω
5
58
Contest: $1,000 for good questions to ask to an Oracle AI
Ω
Stuart_Armstrong
2mo
Ω
117
6
Self-confirming prophecies, and simplified Oracle designs
Ω
Stuart_Armstrong
2mo
Ω
1
Stuart_Armstrong's Comments