This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
AlexMennen
LW
Login
AlexMennen
AlexMennen's Posts
Sorted by New
22
When wishful thinking works
Ω
AlexMennen
1y
Ω
1
24
Safely and usefully spectating on AIs optimizing over toy worlds
Ω
AlexMennen
1y
Ω
16
17
Computational efficiency reasons not to model VNM-rational preference relations with utility functions
AlexMennen
1y
5
39
A comment on the IDA-AlphaGoZero metaphor; capabilities versus alignment
Ω
AlexMennen
1y
Ω
1
0
[Link]
Logical uncertainty and mathematical uncertainty
Ω
AlexMennen
1y
Ω
0
39
Logical uncertainty and Mathematical uncertainty
AlexMennen
1y
6
37
More on the Linear Utility Hypothesis and the Leverage Prior
AlexMennen
2y
4
0
Value learning subproblem: learning goals of simple agents
Ω
AlexMennen
2y
Ω
0
73
Against the Linear Utility Hypothesis and the Leverage Penalty
AlexMennen
2y
47
2
Being legible to other agents by committing to using weaker reasoning systems
Ω
AlexMennen
2y
Ω
0
AlexMennen's Comments