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
Platonic rewards, reward features, and rewards as information
Ω
Stuart_Armstrong
8d
Ω
2
28
All I know is Goodhart
Ω
Stuart_Armstrong
1mo
Ω
23
12
Full toy model for preference learning
Ω
Stuart_Armstrong
1mo
Ω
1
11
Toy model #6: Rationality and partial preferences
Ω
Stuart_Armstrong
2mo
Ω
0
9
Stuart_Armstrong's Shortform
Ω
Stuart_Armstrong
2mo
Ω
1
12
Toy model piece #5: combining partial preferences
Ω
Stuart_Armstrong
2mo
Ω
0
9
Toy model piece #4: partial preferences, re-re-visited
Ω
Stuart_Armstrong
2mo
Ω
0
19
Is my result wrong? Maths vs intuition vs evolution in learning human preferences
Ω
Stuart_Armstrong
2mo
Ω
11
11
Simple and composite partial preferences
Ω
Stuart_Armstrong
2mo
Ω
0
15
Best utility normalisation method to date?
Ω
Stuart_Armstrong
3mo
Ω
7
Stuart_Armstrong's Comments