To continue on from my previous reply, worms clearly demonstrate physical
general intelligence and adpativity as this remarkable passage from Darwin
below shows.. An AGI machine that could do similar physical feats and pass
similar physical tests would have demonstrated its AGI. And it would clearly
need a tree of generality/particularity to conceive of "objects to stuff
burrows" and "ways to pull objects" as worms seem more or less able to. (But,
Ben, I think producing such an apparently simple AGI machine would actually be
vastly more difficult than your "kick-ass" assumptions about the ease of
creating maze-rovers imply).
"
Worms seize leaves and other objects, not only to serve as food, but for
plugging up the mouths of their burrows; and this is one of their strongest
instincts. They sometimes work so energetically that Mr. D. F. Simpson, who has
a small walled garden where worms abound in Bayswater, informs me that on a
calm damp evening he there heard so extraordinary a rustling noise from under a
tree from which many leaves had fallen, that he went out with a light and
discovered that the noise was caused by many worms dragging the dry leaves and
squeezing them into the burrows. Not only leaves, but petioles of many kinds,
some flower-peduncles, often decayed twigs of trees, bits of paper, feathers,
tufts of wool and horse- hairs are dragged into their burrows for this purpose.
I have seen as many as seventeen petioles of a Clematis projecting from the
mouth of one burrow, and ten from the mouth of another. Some of these objects,
such as the petioles just named, feathers, are never gnawed by worms. In a
gravel-walk in my garden I found many hundred leaves of a pine-tree (P.
austriaca or nigricans) drawn by their bases into burrows. The surfaces by
which these leaves are articulated to the branches are shaped in as peculiar a
manner as is the joint between the leg-bones of a quadruped
When worms cannot obtain leaves, petioles, sticks, with which to plug up the
mouths of their burrows, they often protect them by little heaps of stones; and
such heaps of smooth rounded pebbles may frequently be seen on gravel-walks.
Here there can be no question about food. A lady, who was interested in the
habits of worms, removed the little heaps of stones from the mouths of several
burrows and cleared the surface of the ground for some inches all round. She
went out on the following night with a lantern, and saw the worms with their
tails fixed in their burrows, dragging the stones inwards by the aid of their
mouths, no doubt by suction. "After two nights some of the holes had 8 or 9
small stones over them; after four nights one had about 30, and another 34
stones." {29} One stone--which had been dragged over the gravel-walk to the
mouth of a burrow weighed two ounces; and this proves how strong worms are. But
they show greater strength in sometimes displacing stones in a well-trodden
gravel-walk; that they do so, may be inferred from the cavities left by the
displaced stones being exactly filled by those lying over the mouths of
adjoining burrows, as I have myself observed.
Work of this kind is usually performed during the night; but I have
occasionally known objects to be drawn into the burrows during the day.
As worms are not guided by special instincts in each particular case, though
possessing a general instinct to plug up their burrows, and as chance is
excluded, the next most probable conclusion seems to be that they try in many
different ways to draw in objects, and at last succeed in some one way. ...
But evidence has been advanced showing that worms do not habitually try to draw
objects into their burrows in many different ways. Thus half-decayed
lime-leaves from their flexibility could have been drawn in by their middle or
basal parts, and were thus drawn into the burrows in considerable numbers; yet
a large majority were drawn in by or near the apex. The petioles of the
Clematis could certainly have been drawn in with equal ease by the base and
apex; yet three times and in certain cases five times as many were drawn in by
the apex as by the base. It might have been thought that the foot-stalks of
leaves would have tempted the worms as a convenient handle; yet they are not
largely used, except when the base of the blade is narrower than the apex. A
large number of the petioles of the ash are drawn in by the base; but this part
serves the worms as food. In the case of pine-leaves worms plainly show that
they at least do not seize the leaf by chance; but their choice does not appear
to be determined by the divergence of the two needles, and the consequent
advantage or necessity of drawing them into their burrows by the base. With
respect to the triangles of paper, those which had been drawn in by the apex
rarely had their bases creased or dirty; and this shows that the worms had not
often first tried to drag them in by this end.
If worms are able to judge, either before drawing or after having drawn an
object close to the mouths of their burrows, how best to drag it in, they must
acquire some notion of its general shape. This they probably acquire by
touching it in many places with the anterior extremity of their bodies, which
serves as a tactile organ. It may be well to remember how perfect the sense of
touch becomes in a man when born blind and deaf, as are worms. If worms have
the power of acquiring some notion, however rude, of the shape of an object and
of their burrows, as seems to be the case, they deserve to be called
intelligent; for they then act in nearly the same manner as would a man under
similar circumstances.
To sum up, as chance does not determine the manner in which objects are drawn
into the burrows, and as the existence of specialized instincts for each
particular case cannot be admitted, the first and most natural supposition is
that worms try all methods until they at last succeed; but many appearances are
opposed to such a supposition. One alternative alone is left, namely, that
worms, although standing low in the scale of organization, possess some degree
of intelligence. This will strike every one as very improbable; but it may be
doubted whether we know enough about the nervous system of the lower animals to
justify our natural distrust of such a conclusion. With respect to the small
size of the cerebral ganglia, we should remember what a mass of inherited
knowledge, with some power of adapting means to an end, is crowded into the
minute brain of a worker-ant.,
Charles Darwin,The Formation of Vegetable Mould through the Action of Worms
with Observations on their Habits, 1881
----- Original Message -----
From: James Ratcliff
To: agi@v2.listbox.com
Sent: Wednesday, April 25, 2007 9:49 PM
Subject: Re: [agi] The University of Phoenix Test [was: Why do you think your
AGI design will work?]
So basically it appears there are 3 areas of possible AGI Test Applciations:
1. Non-Natural Language Required Tasks.
- Question Answering (little comprehension)
- specific programmed tasks
- Most AI work, vision, sound, etc
2. Natural Language Tasks (advanced parsing and comprehension)
- conversations, Turing Tests, advanced interactive tasks.
3. Embodied Tasks
Either virtual or robot.
movement and smart interaction with the environment, to complete tasks.
Can an AGI be built at all that first into area 1?
It seems too limited to me (rough delineated definitions above granted)
I think any system in one is written for a specific task, chess, maze
solving, etc.
So does it require 2 and/or 3 and which is better.
#2 I think would qualify as an AGI, if it could talk and pass the Turing test
and converse. How useful is it though, what kind of system does it create?
Only expert systems for a domain, or chatbots?
#3 Video game characters or robots are an AGI as well, but how limiting are
they if they dont have complex language skills to be given and learn ever
increasingly complex tasks to do.
Mike Tintner <[EMAIL PROTECTED]> wrote:
Nobody came back on my suggestion for a much simpler AGI test. Let's call
it
the Neo-Maze Test.
You program a robot rover or simulation robot with flexible rules to run
fairly basic-type mazes, including mazes with multiple solutions.
The test is then whether it can run very different kinds of neo-mazes (to
be
set by other programming teams) - let's say, mazes with holes-in-the-wall,
large open squares, roundabouts, spaghetti junctions, underpasses, ramps,
traffic lights and traffic problems etc. etc. - for which its rules have
NOT equipped it, but which it does have the basic raw capacity to run.
This will be a test of its ability to fundamentally adapt its approach to
an
activity to fundamentally altered environments - to adapt its rules, steps/
moves and recognized paths to its goals. That, I reckon, is the primary
requirement of AGI. (Animals can do it).
From there you can move to ever more complex, and higher-level activity
tests. But setting your first goal as passing a language test is to my mind
absurd.
P.S. Another comparable test would a Video-Game Test, where some
gameplaying
agent that is programmed to play something like Pac-Man, will have to adapt
to fundamental variations on that game, with again radical alterations to
the game's maze structure and the type of predators it must deal with, and
treasures it must find.
Or, thinking of the link screen on the Novamente site, you could have
simply
a Building Navigation Test - a robot or agent programmed to negotiate
fairly
simple rooms with simple furniture arrangements, and fairly simple
corridors - will then have to megotiate ever more complex rooms and
building
corridors, ideally the full range of modern architecture. That surely would
be a highly practical test with highly commercial applications.
----- Original Message -----
From: "Derek Zahn"
To:
Sent: Wednesday, April 25, 2007 2:40 PM
Subject: Re: [agi] The University of Phoenix Test [was: Why do you think
your AGI design will work?]
> Ben Goertzel writes:
>
>> I don't think there are any good, general incremental tests for progress
>> toward
>> AGI. There are just too many different potentially viable approaches,
>> with
>> qualitatively different development arcs.
>
> Nevertheless, I wish somebody would try to specify some that are perhaps
> not completely general. Without that, the only way to determine whether
> any
> progress at all is being made is by an analysis of internal structures --
> pointing to
> a data structure and making claims about its meaning. And the developers
> of
> the system are notoriously bad at doing this as they are too emotionally
> and
> intellectually tied to the work.
>
> I wonder at what point our ancesters became "generally intelligent"? Were
> humans
> of 10,000 years ago generally intelligent? If so, why did it take them so
> many billions
> of person-years to develop the most rudimentary capabilities that we seem
> to expect
> our artifical general intelligences to breeze through effortlessly? I
> suppose the
> real test is at what point an individual from the past would be able to
> pass the Turing
> test (or some similar thing) if born into our present world and educated
> like we were
> and I doubt any scientists could make any confident guesses about that.
>
> I think that figuring out a good working definition of general
> intelligence and
> demonstratable intermediate steps is the single most important missing
> piece
> of the endeavor.
>
> -----
> 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/?&;
>
>
>
> --
> Internal Virus Database is out-of-date.
> Checked by AVG Free Edition. Version: 7.5.463 / Virus Database: 0.0.0/0 -
> Release Date: 00:00
>
>
-----
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/?&;
_______________________________________
James Ratcliff - http://falazar.com
Looking for something...
------------------------------------------------------------------------------
Ahhh...imagining that irresistible "new car" smell?
Check out new cars at Yahoo! Autos.
------------------------------------------------------------------------------
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/?&;
------------------------------------------------------------------------------
Internal Virus Database is out-of-date.
Checked by AVG Free Edition.
Version: 7.5.463 / Virus Database: 0.0.0/0 - Release Date: <unknown> 00:00
-----
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=231415&user_secret=fabd7936
