This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
Catastrophic Regressional Goodhart
AF
Login
Catastrophic Regressional Goodhart
62
When is Goodhart catastrophic?
Drake Thomas
,
Thomas Kwa
2y
14
12
Catastrophic Regressional Goodhart: Appendix
Thomas Kwa
,
Drake Thomas
2y
1
27
Catastrophic Goodhart in RL with KL penalty
Thomas Kwa
,
Adrià Garriga-Alonso
9mo
0
5
Goodhart in RL with KL: Appendix
Thomas Kwa
9mo
0