[ExI] AI motivation, was malevolent machines (Anders Sandberg)

[Keith Henson]

On Thu, Apr 10, 2014 at 6:18 PM,  Anders Sandberg <anders at aleph.se> wrote:

> Keith Henson <hkeithhenson at gmail.com> , 10/4/2014 11:36 PM:
>> I think a machine that was motivated to improve its status in the eyes
>> of both humans and other machines would be relatively safe.

> Any way of doing a formal analysis of it? We know human status gaming can be pretty destructive.?

That's a really good question.  I don't know.

>From what I see of destructive, zero sum, or negative sum status
games, they seem to stem from poor intelligence or poor understanding
of the object of the game.  Presumably an AI would be smart enough to
play the game well.

We should discuss this, either over Skype, or the next time I get to Oxford.

Keith

Oh, and to Spike, Tom Lehrer dates back into the early 50s.  I ran
into him in the pages of Mad Magazine around 1957.  In those days a
geek was a cheap circus sideshow act where a guy down in a pit,
dressed as a caveman, bit the heads off live chickens.