AI ALIGNMENT FORUMAlignment & Agency
AF

Alignment & Agency

Apr 09, 2022 by Raymond Arnold
51An Orthodox Case Against Utility Functions
Abram Demski
3y
33
50The Pointers Problem: Human Values Are A Function Of Humans' Latent Variables
johnswentworth
2y
32
61Alignment By Default
johnswentworth
3y
72
67An overview of 11 proposals for building safe advanced AI
Evan Hubinger
3y
25
86The ground of optimization
Alex Flint
3y
43
32Search versus design
Alex Flint
3y
30
57Inner Alignment: Explain like I'm 12 Edition
Rafael Harth
3y
12
45Inaccessible information
Paul Christiano
3y
9
39AGI safety from first principles: Introduction
Richard Ngo
2y
15
40Is Success the Enemy of Freedom? (Full)
alkjash
2y
0