How would we align an AGI whose learning algorithms / cognition look like human brains?

From Stampy's Wiki

Canonical Answer

This is primarily Steven Brynes, a full time independent alignment researcher, working on answering the question: "How would we align an AGI whose learning algorithms / cognition look like human brains?"

Humans seem to robustly care about things, why is that? If we understood that, could we design AGIs to do the same thing? As far as I understand it, most of this work is biology based: trying to figure out how various parts of the brain works, but then also connecting this to alignment and seeing if we can solve the alignment problem with this understanding.

There are three other independent researchers working on related projects that Steven has proposed.

Stamps: None
Show your endorsement of this answer by giving it a stamp of approval!

Tags: None (add tags)

Non-Canonical Answers

This is primarily Steven Brynes, a full time independent alignment researcher, working on answering the question: "How would we align an AGI whose learning algorithms / cognition look like human brains?"

Humans seem to robustly care about things, why is that? If we understood that, could we design AGIs to do the same thing? As far as I understand it, most of this work is biology based: trying to figure out how various parts of the brain works, but then also connecting this to alignment and seeing if we can solve the alignment problem with this understanding.

There are three other independent researchers working on related projects that Steven has proposed.

Stamps: None
Show your endorsement of this answer by giving it a stamp of approval!

Tags: None (add tags)

Canonical Question Info
(edits welcome)
Asked by: RoseMcClelland
OriginWhere was this question originally asked
Wiki
Date: 2022/09/13


Discussion