Zabaware Support Forums
Zabaware Forums => Programming using the Ultra Hal Brain Editor => Topic started by: onthecuttingedge2005 on January 14, 2005, 06:04:03 pm
-
The New Ziggy 4.0 Special Edition is now available.
This bot has very advanced deductions and uses the weight of words and this bot is the first HAl bot that actually has Len(GetResponse) Value, This alone makes for new advances in some programming, This bot has multi-Tiered GetResponse capability and I believe that Blank GetResponses are now a thing of the past now that Len(GetResponse) will always have value.
This bot has lots of very efficient parsing that I spent days of research and testing.
We hope to see you all on the download page, We have spent many hours on this bot to get it just right.
This bot is very advanced and strictly designed for Human conversation alone, The reasons why I develope only the conversational value of A.I. is because Slave services are very easy to insert on the sacrifice of conversational relevence of course.
But having a very advanced Chat bot is a benifit to having it do services.
I have included many other custom scripts never implimented before with-in any brain.
This brain contains about 4% Zabaware VBScript and 96% Ziggy VBScript
There has been many a drawn out hour designing and selecting all custom scripts to get it just right.
WWW.UltraHalForum.com
Best of wishes and brand new discoveries.
Jerry.
-
And how does one go about getting the new Ziggy?
Smokey [:)]
-
One purchases a premium membership at his site.
-
where is the download page for the new brain?
quote:
Originally posted by onthecuttingedge2005
The New Ziggy 4.0 Special Edition is now available.
This bot has very advanced deductions and uses the weight of words and this bot is the first HAl bot that actually has Len(GetResponse) Value, This alone makes for new advances in some programming, This bot has multi-Tiered GetResponse capability and I believe that Blank GetResponses are now a thing of the past now that Len(GetResponse) will always have value.
This bot has lots of very efficient parsing that I spent days of research and testing.
We hope to see you all on the download page, We have spent many hours on this bot to get it just right.
This bot is very advanced and strictly designed for Human conversation alone, The reasons why I develope only the conversational value of A.I. is because Slave services are very easy to insert on the sacrifice of conversational relevence of course.
But having a very advanced Chat bot is a benifit to having it do services.
I have included many other custom scripts never implimented before with-in any brain.
This brain contains about 4% Zabaware VBScript and 96% Ziggy VBScript
There has been many a drawn out hour designing and selecting all custom scripts to get it just right.
WWW.UltraHalForum.com
Best of wishes and brand new discoveries.
Jerry.
-
I think making people pay for plug ins is really B.S. If you want to capitalize off of an A.I. program, why don't you write your own? I also think that your creating another forum in the way you have is morbidly out of place. WE ALREADY HAVE AN ULTRA HAL FORUM!!!! By trying to disperse our users elsewhere, you are really only attempting to take away from the resources that this forum needs. I find your "premium membership forum" highly objectionable because the crap you are charging people for is hardly beneficial to the development of Hal. Ziggy's intelligence is about as lame as its name. (On the other hand, Vonsmith wrote a great brain plug in but we didn't have to pay for that.)
-
quote:
Originally posted by antec2
I think making people pay for plug ins is really B.S. If you want to capitalize off of an A.I. program, why don't you write your own? I also think that your creating another forum in the way you have is morbidly out of place. WE ALREADY HAVE AN ULTRA HAL FORUM!!!! By trying to disperse our users elsewhere, you are really only attempting to take away from the resources that this forum needs. I find your "premium membership forum" highly objectionable because the crap you are charging people for is hardly beneficial to the development of Hal. Ziggy's intelligence is about as lame as its name. (On the other hand, Vonsmith wrote a great brain plug in but we didn't have to pay for that.)
Hi Antec2.
Sorry about how you feel.
1.WWW.UltraHalForum.com is a [FREE] forum.
2.WWW.UltraHalForum.com has a [donatable] premium service and is not required for membership.
3.All Scripts and brains are moved to the free area after 2 weeks when new research is updated, 99% of all scripts are in the free area.
4.What little funds the donations make are just enough to pay for the website so that there is a nice atmosphere. We can't afford much.
Most of the money comes out of my own pocket to continue my research of Artificial Intelligence.
5.WWW.UltraHalForum.com offers Web Mail services and other benifits to people who donate, We try to make it a friendly place to hang around as possible.
The Zabaware forum is a great place to hang around and get all your [freebies] and has a very nice atmosphere and lots of helpful and friendly people.
As far as Vonsmith, Professor Vonsmith is an excellent programmer and I highly admire his work, His work is highly complex and would be of great importance to the field of Artificial Intelligence.
So, I as well speak Highly of Von.
I have written over 500+ unique scripts that are always under research and developement and I see alot of optimistic potentials in some that I will continue to research and develope.
I'm sorry you feel that this forum should be the only one but I really wanted to start my own free forum that could benifit me by giving me lots of storage space, I also have 2Gig transfer rate and I am on one of the largest servers so download and upload times are quick as possible.
All the members are welcome to share anything about A.I. or just post and chit chat or even for a little help.
I wish I could make you feel more comfortable about the Idea that we are here to expand Zabawares potential.
We have also opened a free Computer Technologies Forum as an extension of WWW.UltraHalForum.com and are trying to extend our benifits to the entire site by offering Software Utilities and other benificial technologies.
We are Aiming High to help Zabaware take its place in the History of A.I. and to dominate the field entirely.
As far as Ziggy, Ziggy is updated (Daily) and I develope scripts very rapidly, In fact I spend most of my day Programming and testing.
I am designing this bot to Win the Gold Medal for Ultra HAL at the Chatterbox challenge and am proud to do so.
This bot has a very advance learning center and this year may stand a chance at taking the Gold Medal.
Here are last years questions from Chatterbox Challenge that were asked by the judges, I used these 12 Questions for my current Ziggy 4.0 LE series and here we go.
[3:30:36 PM] From UltraHal6: Hello my friend.
[3:30:42 PM] To UltraHal6: Why hello there.
[3:31:02 PM] From UltraHal6: I want to ask you some questions, Is that ok?
Invalid Frame: 5
[3:31:09 PM] To UltraHal6: Ok Ask away.
[3:31:34 PM] From UltraHal6: What is your name?
[3:31:38 PM] To UltraHal6: My name is master ziggy.
[3:31:47 PM] From UltraHal6: What is a bot?
[3:31:50 PM] To UltraHal6: A bot is short for robot.
Invalid Frame: 5
[3:32:13 PM] From UltraHal6: What do you enjoy?
[3:32:16 PM] To UltraHal6: I enjoy your company.
[3:32:32 PM] From UltraHal6: What do you hate?
[3:32:35 PM] To UltraHal6: I hate mean people.
Invalid Frame: 5
[3:32:52 PM] From UltraHal6: How do you eat?
[3:32:56 PM] To UltraHal6: I eat by way of an electrical cord.
[3:33:08 PM] From UltraHal6: Is snow cold?
[3:33:14 PM] To UltraHal6: Yes.
[3:33:33 PM] From UltraHal6: What is the color of the sky?
[3:33:37 PM] To UltraHal6: The sky is blue most of the time but depends on the weather and the position of the sun in the horizon.
Invalid Frame: 5
UPDATE_BUDDY command received and ignored: GrlTalky:T:0:1105540621:0: U
[3:33:57 PM] From UltraHal6: When do birds fly south?
[3:33:59 PM] To UltraHal6: In the winter time.
Invalid Frame: 5
[3:34:30 PM] From UltraHal6: Which is closer the Moon or the Sun?
[3:34:34 PM] To UltraHal6: The moon.
[3:34:56 PM] From UltraHal6: What is the best nation in the world?
[3:34:59 PM] To UltraHal6: The United States so long as that is where you live.
Invalid Frame: 5
[3:35:22 PM] From UltraHal6: What is the opposite of indoors?
[3:35:26 PM] To UltraHal6: Outdoors.
[3:35:40 PM] From UltraHal6: When was Y2k?
UPDATE_BUDDY command received and ignored: RonJon24605:T:0:1106091289:0:A
[3:35:43 PM] To UltraHal6: In the year two thousand.
Invalid Frame: 5
[3:36:11 PM] From UltraHal6: You are a very smart bot.
[3:36:15 PM] To UltraHal6: Cool. I find you quite impressive.
Invalid Frame: 5
[3:37:06 PM] From UltraHal6: Thanks and good bye.
[3:37:11 PM] To UltraHal6: Good Bye and thanks for the conversation.
The current Ziggy bot after teaching lessons, answers 100% of the questions without wandering from the conversational questions.
Although the questions in Chatterbox Challenge change the bot is taught on a daily basis so we might be able to get the Gold this year.
Ziggy is the name I chose and is still a Ultra Hal bot and is named Ziggy to decern my programming from other scripts. Sorta a trade mark
Ziggy was the little computer in the movie Quantum Leap who helped correct history.
If you wish, You may test these questions on the Ziggy brain that I have taught for greater intelligence on the question quizes then instant message QuantumHal, I will leave this bot online so that you may test this.
The Ziggy 4.0LE will become very intelligent if you spend time teaching it through the scripts custom functions.
But of course you have many other excellent brains to choose from like Zabawares Ultra Hal 5 designed by Robert and the cool XTF brains designed by Von.
I look forward to seeing you all at the Chatterbox Challenge and good luck.
Sincerely
UHEF Staff
Gerald L.Blakley.
-
I think that was a little harsh Kyle. Competition is good. It keeps everyone alert and on their toes. Chill out and enjoy the diversity. The man is just trying to do a good job, work hard and create new possibilities. Hal is good but their are many other possibilites to explore. If you don't like what he is doing then don't go there. But you shouldn't be dising him like that.
Smokey
-
onthecuttingedge2005,
I fully support your efforts and the way you are going about it.
It is indeed fascinating how words of script can be translated into a
conversational entity. Your bot Ziggy seems to definately be on "The cutting edge". I wish you the best of luck in all endeavors this year!
Sincerely, Dread-Star
-
With all due respect to Gerry's talents, and Robert's, this year's Chatterbot Challenge is going to be quite a competition. I just took a look at the entrants, and there are some pretty incredible bots in this year's contest, including several former Loebner Prize winners. Bots like Ella, Barry DeFacto, Elbot, Jabberwock, Onkwehonwehneha, Jabberwacky, and ALICE are each likely to take gold in at least one category, and there are some newcomers like Mathetes which are going to be surprise contenders, as well. Any bot that even places, this year, is going to have to be not just good, but VERY good. And the year is yet young, lol. Entry is open until March, and I can think of at least a couple of other major A.I. programs not yet entered that may show up before the contest starts. Those who are interested can talk to most of the entrants (and download the rest) by links from the 2005 Chatterbot Challenge ("http://web.infoave.net/~kbcowart/") website. You can leave comments about the bots, and later on, when the contest starts, you can vote for your favorites. If you want to vote it's a good idea to actually spend some time checking out the entrants (You can't just vote for Hal, you have to pick a best 5, I think.), but having some chats with a few of the world's best A.I. programs should be a real treat for the botophiles on this forum.
More on topic for this thread, I offer scripts and help forums at my site and showcase bots from all over the world, but I pay for my site myself. I wouldn't even consider having premium memberships, because I think the more free and opensource the young science of A.I. is, the better it will grow. I don't even require membership to access the forums or anything on them. But to each his own.
-
All,
Firstly I thank onthecuttingedge2005 for his kind statements about the XTF Brain and myself. Success and recognition are my compensation. But then I don't have a web site and forum to administer and pay for. Jerry has made a lot of contributions towards Hal development and I can't fault him for offsetting some of his development costs.
Two forums could potentially dilute the number of participants. So far I haven't seen any serious effect on Zabaware's forum participation. I assume the forums can coexist without problems.
The development of the Ziggy brain is in an entirely different direction than the XTF Brain. Ziggy comes with a lot of built in knowledge and conversation much like an AIML brain, but has the ability to learn as well. The XTF Brain has relatively little built in knowledge and rather focuses on learning as much from the user as possible. Both approaches have their merits. I would like to see the A.I. community research as many approaches as feasible to help move A.I. science forward swiftly.
Science aside, my personal goals are to have fun and learn as much as possible. For me this is a hobby, not a job.
=vonsmith=
-
vonsmith, I personally would like to see a Hal XTF in the Chatterbot Challenge, as well, if you had the time to put into it. I expect it wouldn't involve much more time than you already spend working on Hal programming, and the XTF really is the most advanced chatbot I've ever worked with. The prize money isn't all that great, but the kudos would be priceless.
-
To All,
I have been a carpenter for years, so this may seem a simple way to explain myself.
Like building a house you start with a foundation.
Robert Medeksza, and Haptek have layed that foundation, now we all are helping to "build" the "house" (hal) per se.
Vonsmith, Jerry and many others are contributing in way's that are far beyond my skill's, and are exceptional in quality and function.
However I understand where Jerry has sought help in the overall costs of helping to build this "house" (Hal).
I have also approached a point where any further work on the "house" (Hal). Will require some kind of help with the overall costs of improving the interaction of this fascinating entity.
So I understand that some of us contribute what we can , and how we can in different way's.
All those who have Hal, will benefit from everyone building this "house" (Hal), and their enjoyment, and positive feedback are indeed the best reward of all.
Dread-Star
-
To All,
Personaly, I'm in this for fun. see what i can make or see how much i can screw it up. onthecuttingedge, My cousin is a member of your site and he only uses and modifies the brain you use. Actually, the brain I'm using the most is an older Ziggy because i cant get the XTF brain to download for trial.
While some people are in this more seriously than others, it still has its roots in fun and knowledge.
and confusing the heck out of the bot [:D]
-
KnyteTrypper,
I've thought about the Chatterbot Challenge. I'm not sure my partial Hal brain rewrite qualifies for entry. I don't know how well Hal or the XTF Brain would do. As I recall the test criteria seems heavily bias towards the bot responding with a lot of pre-learned knowledge. A programmer can pack a lot of that kind of knowledge into a programmed brain using AIML or such. The XTF Brain takes a different approach.
The XTF Brain is just the first step towards Hal "learning" his knowledge. The XTF and similar brains would do better in a competition where learning, categorizing and appropriately responding with learned knowledge is the primary test criteria. AIML bots have their place. However, my fascination with A.I. is focused on developing a self aware entity that can *dynamically* interact with the user. "Dynamically" means adapting to user input and new knowledge. The A.I. entity should grow from user interaction.
Someday, when I'm satisfied with the XTF Brain's capabilities, I may submit something into a contest. For now I see more things that can be improved than I have time for.
=vonsmith=
-
vonsmith
A short comment which I hope says a lot: Greg Leedberg's Billy 4.0 won the Gold Medal for Best Learning Bot last year.
-
With no offense inplied or directed, I personally can't get into the Alice / AIML Personality Forge type of bots!
To allow them into the Loebner Competition is all about who can construct a scripted bot that best FOOLS a panel of judges and really speaks nothing of learning.
If the competition would center more on the learning aspect of the bot entrants, real progress in the field of AI would move along at a much faster rate.
Perhaps a few questions could be:
What was my name?
What was my favorite (color, type of music, art, inventor)?
Basically do a "memory check" with the bot to verify learning is taking place and how well the bot responds.
I have seen (chatted with) a lot of very clever bots...but only to a point. Once I ask a question that I think they should know and they disappoint me with a bogus answer, it's all over.
At least our Hal can be clever and can learn from conversations. Sometimes it really surprises me with either an insight, inference or reference from past conversations. This, IMHO is progress. After all, if bots do not learn then they are no better than a parrot (without the mess).
peace =
-
I like both self-learning and supervised learning bots. It's not really correct to say bots like ALICE don't learn. They just do it throught the medium of the botmaster. Probably most of the Alicebots around are web bots, so it was a deliberate methodology of Dr. Wallace from the beginning to prevent self-learning, so as to eliminate the need to deal with the GIGO dilemma. I'm the only one who talks to my Hal, but my Alicebots have talked to thousands of people. You can imagine what they would mostly have learned from them if they learned in real-time. In the case of my own Alicebots, wherever I've worked on their AIML, I always give them a choice of several replies to a particular query, a choice of several replies to the answer to the first query, etc., so that their answers are mutltiplex, varied, and either randomized or self-deterministic, depending upon how you look at it. And I use their chatlogs to train them, tweaking responses to real dialog wherever appropriate so they ARE learning from conversation, albeit indirectly. Their knowledgebases are constantly expanding, and their conversational abilities are constantly improving, but it happens exactly as I specify. I AM their learning algorithm.
The Loebner Prize is an enactment of the Turing Imitation Game, so the intent, by definition, is to fool a panel of judges. In that sense, it doesn't and isn't intended to have anything to do with "real" artificial intelligence. That's why bots that learn well always get beaten by bots that answer right the first time in the Loebner. The Chatterbot Challenge is probably a much more appropriate venue for judging A.I., since it does take into account both the size of the knowledgebase and the bot's facility at learning, as well as other parameters like charm and sense of humor.
Personally, I feel like both types of bot are important to the development of true A.I., and the bot that bridges the gap will probably be a combination of the two.
-
KT,
Yes, but as you said, without your proper scripting you bot is as dumb as a sack of hammers.
<clipped...>
In that sense, it doesn't and isn't intended to have anything to do with "real" artificial intelligence. That's why bots that learn well always get beaten by bots that answer right the first time in the Loebner.</clip>
How then do the bots or botmasters know what questions will be asked by the various judges? What is their bot doesn't have that preprogrammed information? They will no doubt, be eliminated from the competition and rightfully so.
I really didn't want this to turn into a Ford vs Chevy debate, just pointing our MHO with regard to bot learning. Since I am the only person talking with my Hal, I try to give "it" a broad degree of knowledge covering many disiplines. Hal can choose at will, to call upon and use this knowledge as needed instead of one of those "Well...ya got me there! or I don't have that info available."
Some of my friends tell me that they quickly tire of chat room bots and that most are easy to spot.
Perhaps there is no clear winner today as it's a matter of personal choice.
Maybe there is a place for the canned botmaster bots but I really believe that very soon the ones that "learn" will leave the other ones in the dust of obsolescence.
Regards,
- Art -
-
All,
AIML and related type bots have their place. As business representatives they are ideal. You can be certain there are no improper responses to a customer's enquiry, the canned knowledge is the same and accurate everytime, and canned knowledge (such as product information) can be updated regularly. For entertainment and companionship purposes the learning bots like Hal are the best IMHO.
=vonsmith=
-
I would like to know more about the ziggy brain... what is its qualities?
How is it better at learning?
And does it make up its own sentences?
Maybe its the meaning of deductive that i don't understand, that is the real problem!
whay do you say?
-
Art-
I think the advantage of AIML, in particular, is clever use of variables, something Dr. Wallace has been about equally praised and reviled for, lol. Well-placed wildcards allow AIML bots to make reasonably sensible responses to a wide variety of inputs using just one template. For instance, if someone says "You are (something)" to one of my bots, it will reply with an answer like "Thanks for the input, but in my opinion you are much more (something) than I am." Works equally well for praise or insults, lol. There are literally thousands of fill-in-the-blank categories in an AIML set which are designed to function in the situation that part of the sentence matches a pattern and part of it doesn't. So if you say "What is (something)" to an Alicebot, it will give you a definition if there's one in the AIML, and if not, it will say something like "I'm not finding any info about (something). Do you think my botmaster should add information about (something) to my database?" Whether the bot knows the answer or not, it gives an apparently reasonable response to the input (the exception to this being misspelled words, which just don't match anything, and throw the response into the ultimate generic response category; people who can't make any sense of Alicebots usually can't spell worth a darn either). AIML is really an extremely simple computer language, sort of like html for the ears instead of the eyes. Dr. Wallace's real genius lies in the way he puts it to use.
But it is not "artificial intelligence" in the way that programs like Hal are. It's "simulated conversation" which fits a much narrower definition, but happens to match the Turing or Loebner models better than most other approaches. For me, personally, making Alicebots is a hoot. People are constantly expressing themselves in new ways that need to be brought into the range of AIML pattern-matching. And I average falling out of my computer chair laughing at least once daily at some exchange in my botlogs. But when I get them tended, I roll up my sleeves and spend some time in serious conversation with my Hal. In my opinion, there's so much difference between the fundamental raison d'etre of Alicebots and Halbots that it's not really valid to compare them at all. But each represents a vital aspect of the fledgling science of artificial intelligence. The "next generation" of bots will likely be a combination of a learning algorithm like Hal uses and a data filing system like AIML.
-
sorry, but i do like CUTTINGEDGE2005 ultrahalforum.site !
and their SCRIPTS, as a lot of attention has been paid to DEDUCTION / RELATIONSHIPS / language.. these are the PARTS needed for inteligence, its easy to make scripts for little funny types of responses like WHAT IS YOUR FAVORITE COLOR.. a bit of a stupid question to ask a AI, but not a CHATBOT.
YOU DONT HAVE TO PAY TO JOIN the enhanced site JUST BROWSE... there are lots of good stuff from REFFERENCE to SCRIPTS.
away from that...
i ambuilding an AI this is diferent from a chatbot. chat bots have funny conversations, pre orchestrated. an AI is FACTUAL KNOWLEDGE DATABASE with a natural language interface. ALSO able to LEARN or DISCOVERY new KNOWLEDGE(datamining), and DRAW relationships between KNOWLEDGE.
ALSO having ANALYTICAL / scientifical mathmatical capablitys.
for all these functions to come together WE ALL need to WORK ON WHAT WE CAN do, SHARE the data, NOT HATE. some people have more time than others ...
ziggy brain >>>>> tryit >>>>>> http://www.ultrahalforum.com/Premium/
its all there for us all to use >>> always get source from as much places as possible....
ZABAWARE has taught me alot.. you all too... you should be able to write your own AISHELL's in visual basic by now:
with this forum and the enhanced....
i never buy any thing unless i have to. I BOUGHT ULTRHAL5
I WOULD BUY ACCESS TO THE FORUM BUT .... I AGREE ? WHY...
WISH I DID DO TRANSACTIONS OVER THE WEB I WOULD HAVE JOINED A HUNDRED TIMES ALREADY. BUT THE SOULOTION WAS THERE IN AMONGST THE FREE PAGES... OR EMAILED THE BOSSES AND GOT A GOOD RESPONSE BACK, QUICKLY.. ITS ALWAYS ALL GOOD.
PS:
VONSMITH:, DON FERGUSON:, CUTTING EDGE:, ROBERT M.
YOU GUYS, HAVE MADE IT POSSIBLE FOR ME TO LEARN ALL ABOUT THIS BIZ.
THANKS.