Alternate Alignment Ideas

May 15, 2019

by abramdemski

These are 'brainstorming' posts, around the theme of what it means for a system to be helpful to a human.

0
Stable Pointers to Value II: Environmental Goals
271y3 min readShow Highlight
2
Stable Pointers to Value III: Recursive Quantilization
1710mo3 min readΩ 1Show Highlight
4
Policy Approval
471y8 min readΩ 3Show Highlight
25
Non-Consequentialist Cooperation?
404mo7 min readΩ 12Show Highlight
15