There certainly should be an AGI Test/Prize. Ben suggested a Toddler
Interview. In fact, in the interviews linked I could only see one Q & A that
to me demonstrated any higher adaptive intelligence - with a child possibly
freely adapting materials to fit the problem - and then it wasn't the Q but
the A.
Where do you think he should sleep?
He will sleep in my room on a bunk bed!
We can make my old bed when I grow up into a crib! You just undo the old one
and then take it and put it on the crib.
The ICRA Robot Challenge - specifically the Planetary Robotic Challenge -
DOES strike me as a proper challenge of higher adaptive intelligence. Here
are some details from a blog:
"The robotic planetary contingency challenge is more ambitious. Organizers
hope to simulate an unexpected problem during a space mission and ask
participants to develop autonomous robotic systems that can quickly devise a
solution using only existing resources. In this case, the sandbox will
function as the planetary environment while a second area called the habitat
will be used by the robotics team to develop their solution to the given
problem. Some example missions include antenna recovery, base station repair
and buggy diagnosis and repair."
[Here's the link: but I can't get through today:
http://icra.wustl.edu/events/contingency.html]
Basically, the robot participants will have to cope with anything that could
reasonably go wrong in a space mission camp. So there will be no way IMHO
they can create a program in advance tailored to deal with the challenge.
The robot will have to be able to devise as well as implement an ad hoc
strategy.
I guess, off the top of my head, the conversational equivalent might be a
Story Challenge - asking your AGI to tell some explanatory story about a
problem that had occurred to it recently, (designated by the tester), and
then perhaps asking it to devise a solution. Just my first thought - but the
point is any AGI Test should be a focussed challenge, like the ICRA, not a
vague Interview Test or similar.
The lack of an adequate AGI Test shows up the deep confusion in the field
about both where it should be heading and the difference between AI and AGI.
P.S. The lack of a general testing ethos in AGI is, I suggest, unacceptable.
What's happening is that the various system-builders are setting their own
problems - acting as student so to speak AND examiner. The problems that
AGI's face should be set for them by independent teams. Otherwise,
system-builders will inevitably - I'm sure, quite unwittingly - "cheat."
Every good industry submits itself to independent testing.
-----
This list is sponsored by AGIRI: http://www.agiri.org/email
To unsubscribe or change your options, please go to:
http://v2.listbox.com/member/?member_id=8660244&id_secret=54976521-dfebc7
