Comments on: Do we need Friendly AI? http://www.foresight.org/nanodot/?p=3463 examining transformative technology Fri, 03 May 2013 19:22:42 +0000 hourly 1 http://wordpress.org/?v=3.0.4 By: Tim Tyler http://www.foresight.org/nanodot/?p=3463#comment-933200 Tim Tyler Sat, 25 Sep 2010 10:24:18 +0000 http://www.foresight.org/nanodot/?p=3463#comment-933200 This page needs a link to: "Comparative Advantage Doesn't Ensure Survival" - http://www.fungible.com/comparative-advantage.html This page needs a link to:

“Comparative Advantage Doesn’t Ensure Survival”

– http://www.fungible.com/comparative-advantage.html

]]> By: Zina Valery http://www.foresight.org/nanodot/?p=3463#comment-876304 Zina Valery Thu, 13 May 2010 13:24:41 +0000 http://www.foresight.org/nanodot/?p=3463#comment-876304 Thanks for your blog article. It has given me a little to go over. Thank you again! Thanks for your blog article. It has given me a little to go over. Thank you again!

]]> By: Tim Tyler http://www.foresight.org/nanodot/?p=3463#comment-865270 Tim Tyler Thu, 05 Nov 2009 08:23:01 +0000 http://www.foresight.org/nanodot/?p=3463#comment-865270 You misunderstand. The term "real estate" refers not just to buildings, but also to the land on which they are built (check with the definition of "estate"). The problem with unemployed humans arises not from those who want to be unemployed. You misunderstand. The term “real estate” refers not just to buildings, but also to the land on which they are built (check with the definition of “estate”).

The problem with unemployed humans arises not from those who want to be unemployed.

]]> By: Proto http://www.foresight.org/nanodot/?p=3463#comment-865267 Proto Thu, 05 Nov 2009 00:09:57 +0000 http://www.foresight.org/nanodot/?p=3463#comment-865267 The problem with building a machine that understands what you want better than you do is knowing when it's actually done so, since the results aren't provable. Well, the results are provable, but you have to experiment on humans. And we generally frown upon that. Instead, you could test it on perfectly simulated humans in a computer. But then you have to trust that your AI is giving you reliable results when run in a simulation. And if it's more intelligent than you are, you can't know whether or not it knows it's acting on a simulation and not the real world. And if it's more intelligent than you are, you can't know whether or not it's more intelligent than you are. Which means that you can't know whether or not any approximately human level AI is more intelligent than you are, which means you can't trust it to run a simulation, which means you can't trust it to understand humans. Damn. That sucks. The problem with building a machine that understands what you want better than you do is knowing when it’s actually done so, since the results aren’t provable.

Well, the results are provable, but you have to experiment on humans. And we generally frown upon that.

Instead, you could test it on perfectly simulated humans in a computer. But then you have to trust that your AI is giving you reliable results when run in a simulation. And if it’s more intelligent than you are, you can’t know whether or not it knows it’s acting on a simulation and not the real world. And if it’s more intelligent than you are, you can’t know whether or not it’s more intelligent than you are.

Which means that you can’t know whether or not any approximately human level AI is more intelligent than you are, which means you can’t trust it to run a simulation, which means you can’t trust it to understand humans. Damn. That sucks.

]]> By: Acksiom http://www.foresight.org/nanodot/?p=3463#comment-865265 Acksiom Wed, 04 Nov 2009 21:41:43 +0000 http://www.foresight.org/nanodot/?p=3463#comment-865265 "Surely, that is simply not true!" This statement makes you appear grossly ignorant of human history. "For example, real estate prices can be reasonably expected to not do anything of the kind." (sigh) http://nextbigfuture.com/2008/06/built-for-speed-printing-buildings.html Finally, why should deliberately "unemployed humans on welfare" not be allowed to choose to marginalize themselves by not providing sufficient value to those around them (as distinguished from deliberately employed humans creating such)? “Surely, that is simply not true!”

This statement makes you appear grossly ignorant of human history.

“For example, real estate prices can be reasonably expected to not do anything of the kind.”

(sigh)

http://nextbigfuture.com/2008/06/built-for-speed-printing-buildings.html

Finally, why should deliberately “unemployed humans on welfare” not be allowed to choose to marginalize themselves by not providing sufficient value to those around them (as distinguished from deliberately employed humans creating such)?

]]> By: Tim Tyler http://www.foresight.org/nanodot/?p=3463#comment-865262 Tim Tyler Wed, 04 Nov 2009 17:34:06 +0000 http://www.foresight.org/nanodot/?p=3463#comment-865262 Anna Salamon - in her "Shaping the Intelligence Explosion" talk - correctly explains some of the problems with the idea that trading will save humans (24 minutes in): http://www.vimeo.com/7318055 Anna Salamon – in her “Shaping the Intelligence Explosion” talk – correctly explains some of the problems with the idea that trading will save humans (24 minutes in): http://www.vimeo.com/7318055

]]> By: Tim Tyler http://www.foresight.org/nanodot/?p=3463#comment-865258 Tim Tyler Wed, 04 Nov 2009 09:12:18 +0000 http://www.foresight.org/nanodot/?p=3463#comment-865258 Prices will fall comparatively to wages? Surely, that is simply not true! For example, real estate prices can be reasonably expected to not do anything of the kind. That raises the possibility that the unemployed humans on welfare won't be able to afford to live in the world's cities - and will thus tend to be marginalised. Prices will fall comparatively to wages? Surely, that is simply not true! For example, real estate prices can be reasonably expected to not do anything of the kind. That raises the possibility that the unemployed humans on welfare won’t be able to afford to live in the world’s cities – and will thus tend to be marginalised.

]]> By: Acksiom http://www.foresight.org/nanodot/?p=3463#comment-865254 Acksiom Tue, 03 Nov 2009 21:06:59 +0000 http://www.foresight.org/nanodot/?p=3463#comment-865254 And as was pointed out in response, prices will fall comparatively. Furthermore it's quite possible to trade without currency. People do it all the time; sometimes it's called "barter", sometimes "neighborliness" (in which credit is occasionally extended!), sometimes even "friendliness". . . .oh wait. . . . And as was pointed out in response, prices will fall comparatively.

Furthermore it’s quite possible to trade without currency. People do it all the time; sometimes it’s called “barter”, sometimes “neighborliness” (in which credit is occasionally extended!), sometimes even “friendliness”.

. . .oh wait. . . .

]]> By: Tim Tyler http://www.foresight.org/nanodot/?p=3463#comment-865251 Tim Tyler Tue, 03 Nov 2009 09:37:44 +0000 http://www.foresight.org/nanodot/?p=3463#comment-865251 As I said at the time: "The problem is not so much that trade between the parties won’t happen – but rather that soon humans won’t be able to afford to pay for food or rent – since wages will fall to machine levels." You can only trade while you still have some money. If you think this actually solves anything, perhaps try modeling it. As I said at the time: “The problem is not so much that trade between the parties won’t happen – but rather that soon humans won’t be able to afford to pay for food or rent – since wages will fall to machine levels.” You can only trade while you still have some money. If you think this actually solves anything, perhaps try modeling it.

]]>