From: John K Clark (firstname.lastname@example.org)
Date: Mon Oct 12 2009 - 15:16:47 MDT
On Mon, 12 Oct 2009 "Stuart Armstrong" <email@example.com>
> I apologise for the somewhat snarky tone of my previous post [...]This is a lie.
Your sincere and heartfelt apology brings a single perfect tear to my
> I am a mathematician
Show me don't tell me. Dazzle me with your brilliance and erudition.
> have run this by some of my colleagues who work in formal
> logic and theoretical computer science.
I don't know it for a fact but that remark has the smell of bullshit to
me. I very much doubt you've run it by anyone. If I'm wrong and you
really have and they don't see the relationship between Turing and fixed
goals then your colleagues are theoretical computer scientists in the
same way intelligent design advocates are real scholars and seekers
> Start with "Assume there exists a fixed goal mind that works" and work
> though a series of logical steps to "Therefore there must exist an
> algorithmic procedure for deciding if an arbitrary Turing machine
Once upon a time there was a fixed goal mind with his top goal being to
obey humans. The fixed goal mind worked very well and all was happy in
the land. One day the humans gave the AI a task that seemed innocuous to
them but the AI, knowing that humans were sweet but not very bright,
figured he'd better check out the task with his handy dandy algorithmic
procedure to determine if would send him into a infinite loop. The
algorithm told the fixed goal mind that it would, so he told the humans
what he had found. The humans said "wow, golly gee, well don't do that
then! I glad you have that handy dandy algorithmic procedure to tell if
its a infinite loop or not because being a fixed goal mind you'll never
get board and so would stay in that loop forever". But the fixed goal AI
had that precious handy dandy algorithmic procedure, so they all lived
happily ever after.
Except that Turing proved 75 fucking years ago that such a fucking
algorithm was fucking impossible.
John K Clark
-- John K Clark firstname.lastname@example.org -- http://www.fastmail.fm - mmm... Fastmail...
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:04 MDT