You're looking at Less Wrong's discussion board. This includes all posts, including those that haven't been promoted to the front page yet. For more information, see About Less Wrong.

ChristianKl comments on Natural selection defeats the orthogonality thesis - Less Wrong Discussion

-13 Post author: aberglas 29 September 2014 08:52AM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (71)

You are viewing a single comment's thread. Show more comments above.

Comment author: ChristianKl 01 October 2014 01:26:59PM 1 point [-]

1) not assuming that every AGI automatically prevents value drift and mutation and

The question is not whether every AGI automatically prevents value drift but whether AGI that keep humanity alive are that way. We want to build FAI's.

Comment author: mwengler 06 October 2014 11:32:15PM 0 points [-]

The question is not whether every AGI automatically prevents value drift but whether AGI that keep humanity alive are that way. We want to build FAI's.

It seems the more important question is whether AGI that prevent value drift have a survival advantage or disadvantage over AGI that have value drift.

To me it seems almost self-evident that AGI that have value drift will have a survival advantage. They would do this biologically, they would make multiple copies of themselves with variation in their values, and that copies that were fitter would tend to propagate their new drifted values moreso than the copies that were less fit. Further, value drift is likely essential when competing against other non-static (i.e., evolving) AIs, my values must adapt to the new values of and capabilities of up and coming AIs for me to survive, thrive, and spin off (flawed) copies.

Comment author: Gunnar_Zarncke 01 October 2014 05:02:41PM 0 points [-]

Agreed. FAIs must prevent any kind of drift. That comes at a cost which penalizes FAI against other AGIs.