This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
Stuart_Armstrong
AF
Login
Stuart Armstrong
Stuart Armstrong's Posts
Sorted by New
6
Toy model piece #2: Combining short and long range partial preferences
Stuart Armstrong
14d
0
9
Preferences as an (instinctive) stance
Stuart Armstrong
16d
0
9
Practical consequences of impossibility of value learning
Stuart Armstrong
19d
0
5
Very different, very adequate outcomes
Stuart Armstrong
19d
3
5
Toy model piece #1: Partial preferences revisited
Stuart Armstrong
23d
6
5
Normalising utility as willingness to pay
Stuart Armstrong
1mo
0
6
Intertheoretic utility comparison: examples
Stuart Armstrong
1mo
1
7
Indifference: multiple changes, multiple agents
Stuart Armstrong
1mo
5
13
Contest: $1,000 for good questions to ask to an Oracle AI
Stuart Armstrong
2mo
39
3
Self-confirming prophecies, and simplified Oracle designs
Stuart Armstrong
2mo
0
Stuart Armstrong's Comments