On 15/05/07, Matt Mahoney [EMAIL PROTECTED] wrote:
We would all like to build a machine smarter than us, yet still be able to
predict what it will do. I don't believe you can have it both ways. And
if
you can't predict what a machine will do, then you can't control it. I
believe this is true
Tom,
I'm sure any computer scientist worth their salt could
use a computer to write up random ten-billion-byte-long
algorithms that would do exactly nothing. Defining intelligence
that way because it's mathematically neat is just cheating
Let's assume that you can make a very long program
Shane,
Thankyou for being patronizing.
Some of us do understand the AIXI work in enough depth to make valid
criticism.
The problem is that you do not understand the criticism well enough to
address it.
Richard Loosemore.
Richard,
While you do have the math background to understand the
--- Richard Loosemore [EMAIL PROTECTED] wrote:
Shane Legg wrote:
Ben (and others),
My impression is that there is a general lack of understanding
when it comes to AIXI and related things. It seems that someone
who doesn't understand the material makes a statement, which
others then
Matt Mahoney wrote:
Richard,
I looked at your 2006 AGIRI talk, the one I believe you referenced in our
previous discussion on the definition of intelligence,
http://www.agiri.org/forum/index.php?act=STf=21t=137
You use the description complex adaptive system, which I agree is a
reasonable
I have a Ph.D. in Nuclear Physics and I don't understand half of what is said
on this board (as well as the AGI board). I appreciate all simplifications that
anyone cares to make.
Eric B. Ramsay
Benjamin Goertzel [EMAIL PROTECTED] wrote:
Shane,
Thankyou for being patronizing.
Some of us
--- Richard Loosemore [EMAIL PROTECTED] wrote:
Matt Mahoney wrote:
--- Tom McCabe [EMAIL PROTECTED] wrote:
--- Matt Mahoney [EMAIL PROTECTED] wrote:
Personally, I would experiment with
neural language models that I can't currently
implement because I lack the
computing power.
--- Eugen Leitl [EMAIL PROTECTED] wrote:
On Mon, May 14, 2007 at 08:21:45PM -0700, Tom McCabe
wrote:
Hmmm, this is true. However, if these techniques
were
powerful enough to design new, useful AI
algorithms,
why is writing algorithms almost universally done
by
programmers instead
Thank you for that. It would be an interesting problem
to build a box AGI without morality, which
paperclips everything within a given radius of some
fixed position and then stops without disturbing the
matter outside. It would obviously be far simpler to
build such an AGI than a true FAI, and it
If such neural systems can actually spit out sensible
analyses of natural language, it would obviously be a
huge discovery and could probably be sold to a good
number of people as a commercial product. So why
aren't more people investing in this, if you've
already got working software that just
Matt Mahoney wrote:
I doubt you could model sentence structure usefully with a neural network
capable of only a 200 word vocabulary. By the time children learn to use
complete sentences they already know thousands of words after exposure to
hundreds of megabytes of language. The problem seems
11 matches
Mail list logo