This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
Catastrophic Regressional Goodhart
LW
Login
Catastrophic Regressional Goodhart
167
When is Goodhart catastrophic?
Ω
Drake Thomas
,
Thomas Kwa
1y
Ω
23
22
Catastrophic Regressional Goodhart: Appendix
Ω
Thomas Kwa
,
Drake Thomas
1y
Ω
1
10
Catastrophic Goodhart in RL with KL penalty
Thomas Kwa
,
Adrià Garriga-alonso
1h
0