Ben Goertzel wrote:
Hi
All who interested in such topics and are willing to endure some raw
speculative trains of thought,
may be interested in an essay I recently posted on goal-preservation in
strongly self-modifying
systems, which is linked to from this blog post
http://multiverseaccordingtoben.blogspot.com/2008/08/on-preservation-of-goals-in-self.html
(I've got another, shorter post on AGI systems with superhuman empathy
coming up ... but probably
not this weekend; I've got some real work to get through first ;-)
The following commentary appears on my blog at susaro.com.
**************************************************************
Preserving Goals in AI: First You Sort Out The Definitions, Then You Do
The Math (not vice versa).
This is a brief commentary on Goetzel's paper entitled "Toward an
Understanding of the Preservation of Goals in Self-Modifying Cognitive
Systems", which is to be found at
http://www.goertzel.org/papers/PreservationOfGoals.pdf
The purpose of his paper is to ask what happens when AI systems are
given goals (like "Make humans happy") and also given the ability to
modify their own design ... including the goals themselves.
In the following analysis I want to focus on the opening definition
offered in that paper, and its relationship to everything that comes
after it.
So, Goertzel begins by asking "What does it mean for system S to possess
goal G over time interval T?".
His suggested answer to this question makes the assumption that there
exists an "...observer O, who is hopefully a smart guy". With
thisassumption in hand, he proposes the following definition, couched in
terms of that observer:
"S possesses goal G over time interval T if, to O, it appears that the
actions S takes during T are significantly more probable to lead to the
maximization of G than random actions S would be able to take."
Let's analyze this.
The definition says that if we compare S's actions (in time interval T)
- which set of actions I will henceforth call A[T] - with some
randomly chosen set of alternative actions - which I will call A'[T],
and if the comparison shows that A[T] are significantly more likely to
lead to a maximization of G, than A'[T], then the system will be deemed
to have possessed goal G.
But this entirely depends on the intellect and subjective judgement of
the observer O. So much so, that we might as well say that S has the
goal G if the observer believes that S has the goal G - which would be
an empty definition.
More specifically, there at least five points on which the definition
depends on subjectivity in the observer:
1) The actions A[T] have to be enumerated and compared with a random
set A'[T] .... but 'actions' are not quantum entities, nor are they
always obvious to an observer. What if the observer does not notice
that a particular action occurred, either because it was too subtle or
too abstract?
2) What is the meaning of a "significant" difference between the
outcomes of the two sets of actions?
3) What exactly is the "maximization" of a goal? The best possible
achievement of the goal in all possible worlds? Some goals can be
stated only in qualitative terms, not quantitative terms, so the
observer may be in a position of having to make subtle judgements about
the relative merits of different kinds of goal achievement. Is it
better to maximize happiness by making absolutely sure that no person
ever experiences a degree of happiness that deviates from the average by
more than 0.01%, on a particular measure? Or would maximization of
happiness allow greater variance with a higher average? The more
abstract the goal, the more meaningless it is to speak of its maximization.
4) And the actions must be judged, by the observer, to "lead" to the
maximization of the goal. Who is to say how actions are causally
connected to outcomes? Does a reduction in income tax for the
wealthiest people lead to a 'trickle-down' increase in the overall
wealth of the poor, or does it just lead to greater income disparity?
5) When exactly are the effects of the actions allowed to come into
play? If the actions A[T] do not have a significant effect during time
T, but then have a massive effect at [T + delta], does the observer
ignore that fact and say that the system did not have goal G during time
interval T (even though system S may verbally declare that it did have
the goal, but did not expect it to have any result until later)?
Now, if the subsequent analysis offered by Goertzel, in this paper, were
to result in a clarification of all these subjective aspects of the
definition, then we might hope that the subjectivity was on the way to
being reduced or eliminated. It is okay, I think, to start off with
some vagueness in your definition if the math that comes later is
designed to eliminate that vagueness in a believable way.
But this is not what hapens. Rather, the ideas embedded in the above
definition (like what counts as a goal, and what counts as its
maximization) are just left as primitives. The observer O is a crucial
character in this paper, because O is supposed to be ... you and me.
We are being asked to step into O's shoes and buy the idea that we all
agree roughly what it means for a system to have a goal.
But nothing could be further from the truth: primitive ideas like
"goal" and "maximization" are a million miles away from being cast in
objective terms, and so the mathematical analysis that comes later is
built on nothing firmer than quicksand. The primitive terms in that
opening definition beg so many questions that the later analysis cannot
be said to go anywhere at all.
Now, to be fair, Goertzel is sanguine about how much he has achieved in
this paper, saying quite honestly that "Essentially nothing has been
resolved in the above discussion. What I hope is that I have raised
some interesting questions."
However, he then goes on to say that "My central goal here has been to
replace vague conceptual questions about goal preservation in
self-modifying systems with semantically similar questions that are at
least somewhat more precise". With this I respectfully but firmly
disagree: I believe that he started with concepts that were so
subjective and vague as to be of no use at all, then built a
mathematical apparatus on top of that insecure foundation.
In my book the first thing you do is sort out your definitions. Then
you do the math. Not the other way around.
Sadly, the very existence of the mathematical apparatus that Goertzel
proposes will serve to disguise the fact that all of our attention,
right now, should be directed at the insecure foundations. In the
literature as a whole, the concept of a "goal" is bandied about as if
everyone understood that this was a moderately well-defined concept. In
fact it is anything but. It is all well and good to have philosophical
discussions in which we take a kind of Turing-esque, hands-off approach
and say that a goal is just what a "reasonably smart guy" would judge to
be a goal, but this kind of philosophical handwaving is not going to cut
the mustard if real systems need to be designed to do real intelligent
things.
We still await a calculus of goals and motivation that is founded on
basic concepts that are not defined in terms of subjective observers or
homunculi.
Richard Loosemore
-------------------------------------------
agi
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/
Modify Your Subscription:
https://www.listbox.com/member/?member_id=8660244&id_secret=111637683-c8fa51
Powered by Listbox: http://www.listbox.com