AI ALIGNMENT FORUMBooks of LessWrong
AF

Alignment & Agency

Apr 09, 2022 by Raymond Arnold

62An Orthodox Case Against Utility Functions

5y

45

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

4y

34

63Alignment By Default

4y

72

68An overview of 11 proposals for building safe advanced AI

4y

31

93The ground of optimization

4y

50

34Search versus design

4y

30

58Inner Alignment: Explain like I'm 12 Edition

4y

12

44Inaccessible information

Paul Christiano

4y

9

39AGI safety from first principles: Introduction

4y

15

39Is Success the Enemy of Freedom? (Full)

4y

0