On 19/01/2015 14:47, Matt Mahoney via AGI wrote:
On Sat, Jan 17, 2015 at 6:37 PM, Tim Tyler via AGI <[email protected]> wrote:
de Gray is arguing against the scenario where a recursively self
improving AI in a box goes FOOM!
It seems like a straw man scenario. Has anyone seriously proposed it?
There are some old proposals, for example Corwin's experiments on
containing AI in 2002.
http://www.sl4.org/archive/0207/4935.html
Yudkowsky's Coherent Extrapolated Volition in 2004.
https://intelligence.org/files/CEV.pdf
Aren't those just imagined attempts to contain superintelligences?
I don't really see the idea that the machine gets smarter and smarter
inside the box just by thinking about things.
Of course there are senses in which machines can learn things in an
intellectual vaccuum. They can search large spaces, cache any solutions
they find and then use them more rapidly later. K-complexity arguments
don't prohibit such things - because K-complexity is not time sensitive -
whereas in practice, being able to do tasks quickly is an important
component of intelligence - and most intelligence tests have time limits.
Machines can only learn rapidly the things we already know. There are
some important questions that even very powerful computers cannot
answer quickly. Among the most important are how we can live longer.
Ray Kurzweil takes 100 pills a day, hoping to live to see the
singularity in 2045 and be immortal. But there is a problem. There is
not a single pill of any kind that is known to increase life
expectancy. It would take decades to find out.
IMO, the way it is likely to go is that we will figure out how to back up
and simulate human minds - after we develop artificial intelligence. Then
they will have the 'potential' immortality that comes with being able to
be copied and backed up. Making our meat sacks last forever seems
like a less significant project. After a while, no one will want a meat
sack for a body anyway - and then it won't matter very much if the
meat sacks age and die.
Sure, we have in-vitro and animal models. We can learn very quickly
that calorie restriction extends the life spans of fruit flies and
mice. We don't know if it works on monkeys. After decades of
experiments, it worked on one group but not another. There have been
no experiments on humans. We know that children reach puberty at a
younger age now than 100 years ago, probably due to more calories, but
people are also living longer. Calorie restriction probably works by
slowing growth. Fish convert 90% of what they eat into growth and 10%
to energy. Cattle convert 15% of their food to growth. Humans convert
0.3%.
FWIW, the theory (as I understand it) is that many organisms have a "famine
mode" -
in which they expend reproductive resources for maintenance processes (thus
living
to reproduce after the famine is over). It's an adaptive metabolic switch.
I actually have a video/essay about that topic here: http://cr.timtyler.org/why/
--
__________
|im |yler http://timtyler.org/ [email protected] Remove lock to reply.
-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424
Modify Your Subscription:
https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657
Powered by Listbox: http://www.listbox.com
