Azathoth123 comments on Natural selection defeats the orthogonality thesis - Less Wrong

-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: Kawoomba 29 September 2014 12:04:29PM *  1 point [-]

It's kind of interesting that humans generally don't guard themselves against value drift. Even though any sufficiently intelligent agent clearly would. One of those fundamental divides higher up on the intelligence scale than us, divides that seem binary rather than linear in nature. I wonder if there are any more of those. Apart from (a lack of) susceptibility to the usual biases.

Comment author: Gunnar_Zarncke 29 September 2014 09:18:11PM 1 point [-]

I don't think that 'any' sufficiently intelligent agent 'clearly' would. It requires at least a solution to the cartesianism problem which is currently unsolved and not every self-optimizing process neccessarily solves this.

Comment author: Azathoth123 30 September 2014 02:45:35AM 1 point [-]

I don't think that 'any' sufficiently intelligent agent 'clearly' would.

Any AI that doesn't will have its values drift until they drift to something that guards against value drift.

Comment author: TheAncientGeek 30 September 2014 11:03:57AM *  0 points [-]

If that is both abstractly possible and compatible with adaptation. If survival requires constant adaptation, which seems likely, value stability - at least the stability of a precise and concrete set of values - may not be compatible with survival.

Comment author: Gunnar_Zarncke 30 September 2014 09:58:15AM 0 points [-]

Maybe. But in that case the drift implies a selection mechanism - and in the absence of some goal in that direction natural selection applies. Those AI that don't stabilize mutate or stop.

Comment author: aberglas 30 September 2014 07:56:11AM 0 points [-]

Actually not quite. Until they drift into the core value of existence. Then natural selection will maintain that value, as the AIs that are best at existing will be the ones that exist.

Comment author: TheAncientGeek 30 September 2014 11:20:20AM 1 point [-]

Of course the ones that are best at existing will continue to exist, but I think it is misleading to picture them as a occupying a precise corner of valuespace. Suicidal values are more precise and concrete.