AI ALIGNMENT FORUM
Books of LessWrong
AF

Alignment & Agency

Apr 09, 2022 by Raymond Arnold

61An Orthodox Case Against Utility Functions

5y

45

53The Pointers Problem: Human Values Are A Function Of Humans' Latent Variables

5y

34

63Alignment By Default

5y

72

72An overview of 11 proposals for building safe advanced AI

5y

32

93The ground of optimization

5y

50

34Search versus design

5y

30

59Inner Alignment: Explain like I'm 12 Edition

5y

12

44Inaccessible information

Paul Christiano

5y

9

39AGI safety from first principles: Introduction

5y

15

40Is Success the Enemy of Freedom? (Full)

5y

0