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
49
Research Agenda v0.9: Synthesising a human's preferences into a utility function
Ω
Stuart_Armstrong
7d
Ω
10
11
Preference conditional on circumstances and past preference satisfaction
Ω
Stuart_Armstrong
7d
Ω
1
29
For the past, in some ways only, we are moral degenerates
Ω
Stuart_Armstrong
17d
Ω
14
17
To first order, moral realism and moral anti-realism are the same thing
Ω
Stuart_Armstrong
21d
Ω
5
6
Conditional meta-preferences
Ω
Stuart_Armstrong
21d
Ω
0
20
Uncertainty versus fuzziness versus extrapolation desiderata
Ω
Stuart_Armstrong
25d
Ω
8
71
And the AI would have got away with it too, if...
Ω
Stuart_Armstrong
1mo
Ω
4
31
By default, avoid ambiguous distant situations
Ω
Stuart_Armstrong
1mo
Ω
15
21
Oracles, sequence predictors, and self-confirming predictions
Ω
Stuart_Armstrong
2mo
Ω
0
43
Self-confirming predictions can be arbitrarily bad
Ω
Stuart_Armstrong
2mo
Ω
11
Stuart_Armstrong's Comments