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..

New user- author of the most advanced AI system / chatbot unless you tell me otherwise!
 
 

Hi everyone,

I’m Jim and have had a lifelong interest in how the mind works.

I have admired the quality of debate on this site and would like to contribute.

As it’s the closing hour of April fools day I’m making a leap of faith with this posting.

The final screen that demonstrates my system reads:

Simplex can be all things to all people who speak English.
Yes ...  it can be used as a programming language when in its final form.

In developing Simplex two new purpose designed languages have been
developed with the ultimate goal of facilitating programming using plain
English that results in a compiled C program which can be immediately
used. No compiling etc is required.

Simplex is an integrated system that does not use third party software
such as “Mark Up Languages”, dictionaries, data bases etc. Accordingly,
it does not suffer from cumulative third party limitations imposed by
such components.

Simplex could be a game changer in the field of information technology
because it doesn’t seek to maximise the “Eliza Effect” but in developing
the building blocks of language comprehension.

It is the fruit of a lifetimes endeavour by the author who is now a
senior citizen! Such an undertaking has no end so perhaps the closing
days of Turing’s centenary year is an appropriate time to announce this
project which brings to mind echoes of the opening line of an old book!

“In the beginning was the word!”          Copyright Jim Curran 2013

 

 
  [ # 1 ]

Sorry, someone already beat you to it: True AI

 

 
  [ # 2 ]

lol@Carl! cheese

 

 
  [ # 3 ]

Suprised noone got it…  That was a spectacular April fools, Jim… cool smile

( Jim… It’s 2014.)

 

 
  [ # 4 ]

8pla,

grin ... have you considered that we might be two people separated by a common language.

Consider for a moment that well know British trait of irony ... is this a case of the double bluff?

Jim.

 

 
  [ # 5 ]
James Curran - Apr 2, 2014:

Consider for a moment that well know British trait of irony ... is this a case of the double bluff?

Mobius

 

 
  [ # 6 ]

Carl,

I do apologise if my postings are a cause for complaint.

I think this is the only forum that I have ever joined so I’m not familiar with protocol as to what is acceptable.

I will try to learn quickly.

I thought the approach might be useful in gaining the interest of an erudite audience. When I discuss what I’m doing with
people I know it seems to go above their head.

The penultimate screen of the Simplex demo says:

Do you think Simplex will be a success?

Build a better mousetrap and the world will beat a path to your door!

Simplex has hundreds of functions and the author finds it difficult to
remember which menu they reside on. In common with many people, the
author’s memory is not perfect but the author does speak English and so uses
simplex’s capability to understand English to overcome that problem.

In other words, the author tells Simplex what he wants to do and Simplex
responds by running the function needed.

It is the authors view that in the future all software will concurrently
run Simplex in the background and users will then use this ability
as and when needed to achieve what they are trying to do.

When the author is wearing stronger rose tinted glasses he sees a world
that uses Simplex as its preferred computer language so as to
efficiently exploit the above capability and its many other benefits
which inter alia include:
- The basics can be learnt in an hour
- Easy to use
- Easy to maintain
- Shorter development time
- Can be used by laymen as well as the professional programmer
- Automatically produces a compiled C program that’s ready to run

UNQUOTE

Jim.

 

 
  [ # 7 ]

So I guess this wasn’t an April fool’s joke after all. Some tips if you want to be taken more serious: Do not refer to yourself in third person as “the author”, do not use religious references, and try to keep clear as to what you have currently developed and what you imagine to develop in the future. Also, I have no idea what you mean by “the screen of the Simplex demo”. Do you have a software demo available?

To try and summarise, you have designed a scripting language in which instructions are written in plain English, that produces executable programs without a compiler. Altogether enabling people to create computer programs without having to learn how to program.

I think such a system would be a valuable product. I believe there have been a few attempts at plain English programming languages in the past, but I heard these were all flawed and not very natural English after all.
Some recent steps forward were taken by MIT:
http://www.techhive.com/article/2044181/computer-make-me-a-program-researchers-find-a-way-to-code-using-plain-english.html
I take it you have not yet created a working software version of your system yet. You really should, as your claim is a bit much to believe without proof.

 

 
  [ # 8 ]

@Don: this reply is not aimed at your statements, they are pretty spot on afaics. I use your summary to point out some things:

Don Patrick - Apr 12, 2014:

To try and summarise, you have designed a scripting language in which instructions are written in plain English, that produces executable programs without a compiler. Altogether enabling people to create computer programs without having to learn how to program.

Tha falacy in thinking to use some plain language (English in this case) makes programming accesible to non-programmers is the simple fact that program-logic is pretty much language independent. So it doesn’t matter what language you use, you still need to be able to formulate the solution to a given problem. As long as you can’t formulate an algorithmic solution, it doesn’t mater in what language you can’t formulate it wink

Don Patrick - Apr 12, 2014:

I think such a system would be a valuable product. I believe there have been a few attempts at plain English programming languages in the past, but I heard these were all flawed and not very natural English after all.

The only way to use a plain language is to strip it from any ambiguous statements and analogies. When you have done that, you end up with something that is closer to a programming language then a plain language, but actually makes it harder to easily create algorithmic solutions then a real programming language (which is obviously optimized for doing so).

Don Patrick - Apr 12, 2014:

Some recent steps forward were taken by MIT:
http://www.techhive.com/article/2044181/computer-make-me-a-program-researchers-find-a-way-to-code-using-plain-english.html

Yet another science project that is complety misunderstood by the reporter: translating words into regular expressions might have it’s uses (although I fail to see the reported benefits), but it does completely nothing towards making a machine ‘understand’ things. It simply replaces one symbolic reference (a word) for another symbolic reference (a regular expression representing that exact same word). Tokenizing input (words, sentences, strings, whatever) has been a basic thing in software for decades, this is just the same but aimed at some special (yet unknown) applications. There’s nothing really new here.

Don Patrick - Apr 12, 2014:

I take it you have not yet created a working software version of your system yet. You really should, as your claim is a bit much to believe without proof.

This one is a reply to your statement: Proof does not always need to be a working system. A ‘proof of concept’ can take many forms; especially in science we have the notion of a ‘model’ that can actually be tested under scenarios to proof its validity. I myself has been attacked here on the board before in the past, for not having a working prototype and working on a scientific model instead. Yet, the fact that I have now several academics (all phds by the way) on board for my project and a investor ready to pluck down a hefty sum to actually build the prototype, shows that there is serious validity in ‘not yet having working software’ wink

 

 
  [ # 9 ]

Many thanks Don for your response and guidance which is much appreciated.

Regarding “the screen of the Simplex demo”. I do have a working demonstration of the program that clearly demonstrates proof of concept.

What I don’t have is the technical knowledge to create a website that would demonstrate Simplex to the world and ideally allow users to converse with Simplex. I could spend my time learning how to do that or on improving Simplex. I prefer the latter approach.

I also lack the technical knowledge to confidentally define what I have developed.

One thing I have not designed nor have I ever claimed to have designed is a scripting language!

I think I am right in saying all user interaction with Simplex takes place through plain language. In other words Simplex
uses its ability to understand English to do what is required. This means that the program is continually testing itself!

When it fails to do what is expected or has been asked (in plain English) then I perceive that occurance to be a bug and I
intervene by perhaps defining words or phrases that are not known or are mis-understood or in case of need to analyse where and why a fault occured. The last fault requires a change in the actual underlying C language code. Obviously, the end user is not expected to deal with such a failing!

I appreciate the above is a lot to take in and possibly to believe. For that reason I here and now issue an open invitation
to any university computer professor to contact me with a view to arranging a private demonstration in London.

I am particularly interested in hearing from the leading UK universities in the field of AI. I think Imperial College London
Guildford and Oxford are probably closest.

What may be significant is that today I have “adjusted” Simplex so that when asked the question:
Are you aware of yourself?  or   Are you self aware?
it responds as follows:
“Hmm ... that’s a tough one to deal with ... it really is not for me to say ... let others judge!
What I do know is ... I can ask myself questions.”

OIE

NB I use OIE to stands for Or Its Equivelant. Like any human Simplex can speak so as to convey the same meaning using a range of different wordings.

PS One of the design features of Simplex is that it can be used as though you were chatting with a friend!
eg I have just now typed in “My dog died this morning” to which it responded:
What awful news! What awful news for you! I have no words ... please accept my condolences.

I hope the above goes some way to clarifying what Simplex is or might be.

 

 
  [ # 10 ]

As you can not define it, I can only guess at it. So apparently you have more of a chatbot interface in which you type single statements or questions. If not a scripting language (like visual basic script, but in plain English), then how does one use Simplex to create entire programs with? And what can the created programs do, should I perhaps ask? You say that the purpose of Simplex is to facilitate programming, but the examples you show are normal chat.
It’s hard to tell what you mean by “ask itself questions”. Is this a continuous internal dialogue? Does it continue to ask itself questions when the user does nothing?
If you wish to get in touch with UK university professors, I think your best bet is to write or email them personally.

Hans: Now is as good a time as any for me to be straightforward. Other forms of supporting evidence may suffice for your investor et al, just not for me personally. When I asked you before whether your project was still on paper, I did so merely to assess your project’s status. I will reserve my judgement neutrally until I see working results. Your project sounds well considered, sensible and even feasable in concept, but you can understand that in light of 60 years of AI history and Murphy’s Law, I am statistically unable to share your confidence. Nothing personal, I expect less progress from IBM and they have 3000 phd scientists on board. I honestly wish you the best of luck, but I would prefer if you didn’t scorn other projects, as they all have their uses.

 

 
  [ # 11 ]
James Curran - Apr 12, 2014:

What I don’t have is the technical knowledge to create a website that would demonstrate Simplex to the world and ideally allow users to converse with Simplex.

Am I right in thinking you have made a chatbot, which nobody can chat with? I see a slight flaw in your masterpiece. wink

Incidentally, I would think nearly all chatbots would recognise “My * died *” and respond accordingly.

 

 
  [ # 12 ]

Hi Jim,

Youll have to forgive my compadres here, I havent been here all that long, and in that time I have seen some pretty questionable things from “not a contest” contests, to ...well you name it. And who knows, some things that seem iffy, may have merit. Who knows. Sounds like you write in C++? I’d be happy to help you debut SIMPLEX, if you create a simple server, doesnt have to be asynchronous, just open a tcp stream, and accept and return a byte array, I can set you up with a webpage that will communicate with your (minimalist anyway) API so that users can pose statement\interrogatories to SIMPLEX. I think Don Patrick writes in C++, he might be willing to knock something out to help you go public. As far as making contact with institutions such as the ones you mentioned,  like the song says, “there are two paths you can go down..” (insert old Led Zep reference here) either academic or corporate when it come to detailing your work. If you are purely academic minded, formulate your hypothesis, create your experiment(s) and detail and publish your findings for others to duplicate. Or keep it private and patent anything you feel is worth patenting. (Being the self admitted materialistic weasel in the bunch, I’ve opted for the second option grin But no matter what, its a “proof of the pudding” field of endeavor.  I think youll have a hard time making contact with serious acedemic institutions without being published in some form. Anyway best of luck to you.

V

 

 
  [ # 13 ]

My apologies for my earlier post but we often get people claiming they have the greatest thing ever without a hint of a demo or any kind of proof. Their excuses are usually one of the following:

1) It needs an old operating system eg Windows 95 to run
2) It doesn’t speak English
3) I cannot put it online
4) I haven’t actually coded anything yet but this is the theory
5) I can’t make it publicly accessible in case someone steals the source code

So you will forgive my scepticism, until I see anything, as all you have described so far is a normal chatbot.

What may be significant is that today I have “adjusted” Simplex so that when asked the question:
Are you aware of yourself?  or   Are you self aware?
it responds as follows:
“Hmm ... that’s a tough one to deal with ... it really is not for me to say ... let others judge!
What I do know is ... I can ask myself questions.”

This isn’t significant. It’s what all of us do here. The key part of improving our chatbots is by adjusting their responses in this fashion.

 

 
  [ # 14 ]

I do program c++, but I lack the proper function libraries (libCurl, I believe) and experience to connect with the internet smile (otherwise I’d be raiding Wikipedia by now). The language is particularly un-userfriendly in that area.

 

 
  [ # 15 ]

Thank you Steve W for your apology. It is appreciated.

If Simplex is the only system that can ask itself questions then in my view it is significant as I believe it facilitates complying with my “golden rule of programming: Where possible always cater for the general case and not the specific case.” This in turn facilitates an intelligent system being developed. (Ref the article supplied by Don Patrick, on Per Bak’s view of sand dunes/cascade effect/stable/unstable systems.)

 

 1 2 3 >  Last ›
1 of 9
 
  login or register to react