Robust Delegation

by abramdemski, Scott Garrabrant 1y4th Nov 20181 min read10 comments


Ω 25

Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.

(A longer text-based version of this post is also available on MIRI's blog here, and the bibliography for the whole sequence can be found here)

The next post in this sequence, 'Embedded Agency', will come out on Tuesday, November 6th.

Tomorrow's AI Alignment Forum sequences post will be 'Humans can be assigned any values whatsoever…' by Stuart Armstrong, in the Value Learning sequence.