This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
CAST: Corrigibility As Singular Target
LW
Login
CAST: Corrigibility As Singular Target
86
0. CAST: Corrigibility as Singular Target
Ω
Max Harms
1mo
Ω
10
45
1. The CAST Strategy
Ω
Max Harms
1mo
Ω
18
53
2. Corrigibility Intuition
Ω
Max Harms
1mo
Ω
8
0
3a. Towards Formal Corrigibility
Ω
Max Harms
25d
Ω
0
12
3b. Formal (Faux) Corrigibility
Ω
Max Harms
25d
Ω
10
34
4. Existing Writing on Corrigibility
Ω
Max Harms
24d
Ω
8
14
5. Open Corrigibility Questions
Ω
Max Harms
24d
Ω
0