AI Zone Admin Forum Add your forum

NEWS: Chatbots.org survey on 3000 US and UK consumers shows it is time for chatbot integration in customer service!read more..

Next step towards Singularity?
 
 

Among yesterday’s featured articles of codeproject.com was this blog entry:
http://www.techhive.com/article/2044181/computer-make-me-a-program-researchers-find-a-way-to-code-using-plain-english.html

which in turn is based on

http://web.mit.edu/newsoffice/2013/writing-programs-using-ordinary-language-0711.html

In short, the people at the MIT have managed to build a system (an AI) that is able to build rules how to transform specifications given in natural language to Regular Expressions.

It should be comparably easy to extend this system to generate source code for computer programs.

From the other side, what we now need is a robot that can tell what kind of programming problem it needs solved.

Put these ends together, and we’d have a self-programming AI, wouldn’t we?

 

 
  [ # 1 ]

nice Peter!!!! It would be interesting to elorate on this further. We’ve tried something like this before

SELECT XXX FROM YYYY WHERE CONDITION

modern variant

GET “3 letters words” FROM “english dictionary” WHERE “first letter = ‘X’”

the “x letter word” is a human concept and should be translated into “LEN(STRING) = 3”

actually, this would be mean that we’ll teach computer human concepts. We could build a library of language concepts on SQL, and create a new language.

On top, it should also handle equivalent description

‘words starting with X having 3 letters”

 

 

 

 
  [ # 2 ]
Peter Wolff - Jul 16, 2013:

In short, the people at the MIT have managed to build a system (an AI) that is able to build rules how to transform specifications given in natural language to Regular Expressions.

It should be comparably easy to extend this system to generate source code for computer programs.

From the other side, what we now need is a robot that can tell what kind of programming problem it needs solved.

Put these ends together, and we’d have a self-programming AI, wouldn’t we?

Yes, you do have a self programming AI. The programming language I developed, JAIL (JavaScript Artificial Intelligence Language) relies heavily on regular expressions. When applied correctly, it allows the AI to determine the kind of programming problem that needs to be solved and then writes the code to solve the problem in real-time.

A thinking machine?

 

 
  [ # 3 ]

I wouldn’t get too hopeful about this. The earlier article also said…

“I don’t think that we will be able to do this for everything in programming, but there are areas where there are a lot of examples of how humans have done translation,” says Regina Barzilay

 

 

 
  [ # 4 ]

I couldn’t tell whether we’ll ever be able to build an AI that can emulate every aspect of human behavior. But anyway, this is one important step of a journey of a thousand miles.

 

 
  [ # 5 ]
Peter Wolff - Jul 21, 2013:

But anyway, this is one important step of a journey of a thousand miles.

True. I’m just cautious about making that journey’s first step a misstep. grin

  We shall now try to show not only that human behavior can be regular
without being governed by formalizable rules, but, further, that it has to
be, because a total system of rules whose application to all possible
eventualities is determined in advance makes no sense.
  In our earlier discussion of problem solving we restricted ourselves to
formal problems, in which the subject had to manipulate unambiguous
symbols according to a given set of rules, and to other context-free
problems such as analogy intelligence tests. But if CS is to provide a
psychological theory—and if AI programs are to count as intelligent—
they must extend mechanical information processing to all areas of
human activity, even those areas in which people confront and solve
open-structured problems in the course of their everyday lives.
  Open-structured problems, unlike games and tests, raise three sorts of
difficulties: one must determine which facts are possibly relevant; which
are actually relevant; and, among these, which are essential and which
inessential. To begin with, in a given situation not all facts fall within the
realm of possible relevancy. They do not even enter the situation. Thus,
in the context of a game of chess, the weight of the pieces is irrelevant.
It can never come into question, let alone be essential or inessential for
deciding on a specific move. In general, deciding whether certain facts
are relevant or irrelevant, essential or inessential, is not like taking blocks
out of a pile and leaving others behind. What counts as essential depends
on what what counts as inessential and vice versa, and the distinction cannot
be decided in advance, independently of some particular problem
, or
some particular stage of some particular game. Now, since facts are not
relevant or irrelevant in a fixed way, but only in terms of human pur-
poses, all facts are possibly relevant in some situation. Thus for example,
if one is manufacturing chess sets, the weight is possibly relevant (al-
though in most decisions involved in making and marketing chess sets,
it will not actually be relevant, let alone essential). This situational
character of relevance works both ways: In any particular situation an
indefinite number of facts are possibly relevant
and an indefinitely large
number are irrelevant. Since a computer is not in a situation, however,
it must treat all facts as possibly relevant at all times. This leaves AI
workers with a dilemma: they are faced either with storing and accessing
an infinity of facts, or with having to exclude some possibly relevant facts
from the computer’s range of calculations.
  But even if one could restrict the universe for each particular problem
to possibly relevant facts—and so far this can only be done by the
programmer, not the program—the problem remains to determine what
information is actually relevant
. Even in a nonformal game like playing
the horses—which is much more systematic than everyday open-struc-
tured problems—an unlimited, indefinitely large number of facts remain
as possibly relevant. In placing a bet we can usually restrict ourselves to
such facts as the horse’s age, jockey, past performance, and competition.
Perhaps, if restricted to these facts from the racing form, the machine
could do fairly well, possibly better than an average handicapper; but
there are always other factors such as whether the horse is allergic to
goldenrod or whether the jockey has just had a fight with the owner,
which may in some cases be decisive. Human handicappers are no more
omniscient than machines, but they are capable of recognizing the rele-
vance of such facts if they come across them.

(“What Computers Still Can’t Do: A Critique of Artificial Reason”, Herbert L. Dreyfus, 1992, pages 257-258)

 

 
  login or register to react