This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
Effective Altruism Forum
Alignment Theory Series
EA Forum
Login
Sign up
Alignment Theory Series
Get notified
Distillation pieces for those who want to start from somewhere but don't know where.
19
Deception as the optimal: mesa-optimizers and inner alignment
Eleni_A
Eleni_A
+ 0 more
·
2y
ago
· 6m read
0
0
7
Three scenarios of pseudo-alignment
Eleni_A
Eleni_A
+ 0 more
·
2y
ago
· 4m read
0
0
14
My summary of “Pragmatic AI Safety”
Eleni_A
Eleni_A
+ 0 more
·
2y
ago
· 5m read
0
0