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
01y3 min readShow Highlight
0
Stable Pointers to Value III: Recursive Quantilization
110mo3 min readShow Highlight
0
Policy Approval
31y8 min readShow Highlight
13
Non-Consequentialist Cooperation?
124mo7 min readShow Highlight
4