Mike,
I want
to comment on your "just around the corner" hypothesis, as it relates to
Novamente.... What you said about Novamente isn't inaccurate, but your
phrasing might be misleading to some.
My
"12-18 months" statement was a statement that, if all goes well, we'll be done
*programming* our first version of Novamente in 12-18 months. This
"programming" includes basic tuning and testing of all system components.
But it just means that we'll have a system that's *ready to be taught like a
baby*. How quickly it will learn, we really don't know. We may need
to add a LOT more computing power to get it to learn reasonably quickly ... we
may need to tinker with the AI methods to make them more efficient in important
ways.... etc.
In
fact, we could be donw with the initial programming/testing/tuning phase in 6
months from now, if we had $100,000 in funding to pay for pure AGI work.
The reason for the 12-18 months figure (and it could turn into 24 months ;-( )
is that we're doing AGI engineering in our "spare time" while earning a living
making practical software applications with our Novamente codebase (which is
intended to be turned into an AGI when complete)
-- Ben
G
Arthur, I am disappointed with the way that A.I.
is depicted in science fiction books and movies. Unfortunately most
people get their idea of what the future will be like from movies and
novels. Why don't they show A.I. and robots in a more realistic
scenario? Take Star Trek for instance. Data is the humanoid robot
with the machine intelligence quotient of 1000 and the human intelligence
quotient of 85. Why don't they make a lot of Data-like robots?
Because they supposedly don't understand how his brain works.
Nevertheless, in their holodecks they routinely generate convincing artificial
characters. Why don't they take the same knowledge that allows them to
create artificial intelligences in their holodecks and build character driven
robots that operate in the real human environment?
It seems obvious that real A.G.I. is just around
the corner. Ben's Novamente progress report says they should have a
working system in 12 to 18 months. Peter's a2i2 project report states
that a proof-of-concept prototype should
be operational in 12 months. Toyota just announced that they will have
an industrial humanoid robot on the market in 2005 to work in factories and
other uses.
But the general public is not expecting humanoid
robots with anything like real intelligence any time soon because every movie
they see about the future either doesn't include robots at all or shows them
as the enemy. Or as in Star Wars, robots with only very limited
smarts.
Let's take the Mars rovers as an example of
current robotic expectations. Nasa doesn't trust anything as squishy as
real intelligence, way to unpredictable or controllable. The rovers are
touted as autonomous robots capable of navigating around obstacles and
avoiding hazardous terrain, but they can't do anything without specific orders
from home, not even roll or climb off the lander.
There is such a profound gap between the public's
perception of the state-of-the-art of AGI and the reality of AGI research that
society is in for a major disruption.
Here is an open question for everyone on this
email list: What do you think some of the real world effects on society
will be after the development of AGI?
Mike Deering.
To unsubscribe, change your address, or temporarily deactivate your
subscription, please go to
http://v2.listbox.com/member/[EMAIL PROTECTED]
To unsubscribe, change your address, or temporarily deactivate your subscription,
please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
|