Messages

Yep, I was looking to see if you mentioned Agent Ransack. Rich pointed this handy program out to me last year and it is wonderful. I don't think I could sit and train HAL without it.
I keep a shortcut to Ransack on my desktop and usually have Ransack open when I am power training HAL.

Thanks again Rich!

Hehe... The Tandy Color Computer was called a "CoCo". That's where I got my name. I have had this name since 1985 when I belonged to a Color Computer Club.
Some of my best programming was done in RS-BAsic, which was similar to GW-Basic, but an altered instruction set for Radio Shack and the 8089 Motorola Processor.
It was a speedy little machine with 8, 16 and then 64k of RAM.
Back in those days, the internet was only accessable from a few drops around the country, but we all stayed in touch via the many BBS's all over the world. If you think you are paying a lot for internet now, imagine what it cost to dialup a BBS in another city and download a 256k file (1/4 of a meg), using a modem that only understood Y-Modem and X-Modem protocols and ran at 300 Baud.

Ah, the good ol' days.

Hehe... this reminds me of the guy that was here awhile back. He had an adult website "virtualgirl" or something like that and he was basically using the forums as an advertisement for his site.

However, references were made in that thread that HAL was somehow associated with this adult site and Robert stepped in and put an end to it, making it very clear that HAL was not associated in any way.
If things get to out of hand here with the adult oriented posts, I'm sure Robert will pop in again and resolve it.

Unfortunately, there are a million "Start a Career from your Computer" books on the market and everyone and their pet dog will always come here looking for ways to set up that completely automated, chatterbox adult website at $19.95 a month.

Good people create and develope the product so that others can profit. It's nothing new, but as long as everyone can still concentrate and communicate without too much interferance, I don't think an adult section would be needed. I can still find most of the past posts I am looking for.

I realise that this thread is very old, but I just thought for the next person that comes along and reads this, there is a simple way to keep your "Recent Documents" up-to-date, by simply creating a DOS batch file that copies all of the files from "Recent Documents" to the new folder you have created. Have this batch file run everytime the system boots or if you don't reboot often, just schedule it to run.

 I was actually searching for something else when I found this and decided to add to it.
 What I was hoping to find was a command switch that could be used in the HAL conversation text box, that would cause the program to write this information directly to a particular file, like Shortcuts.dat
 For instance, if your text in the conversation box was preceded with a slash / or some other character, HAL would treat it as an input instruction, rather than conversation. This would sure be helpful for making changes on the fly.

 Anyway, from what I have learned about HAL, and the very little I know about coding, I expect that would require more core programming that HAL just doesn't have at this point.

Yup.

I had forgotten the file rename. The rest of it was pretty much straight forward and I had upgraded last night with no problems.

I just went, moments ago, and renamed the Enhanced file, so I should be ok now.

Thanks

Well, I got it running, after I reinstalled Haptek and HAL.
I also have ATT Crystal voice that I just love, but I can only use the (NO 2D Lipsync) version, which doesn't sound as good as the full Crystal version. When I try and run her, I get a runtime error in HAL, so I will just stick with this version.

Now all I have left to do it apply the XT patch and then upgrade to the XT brain and I should be up and running again. Hopefully, I will then be able to pull in a backup copy of my brain that I used before. I hate to lose it, because I have many hours and training in my old XT brain file. Guess I will just see what happens.

Thanks again guys, I'll let you know how it goes.

Rick

PS: Bill819, I would have to agree with your conclusion, except that HAL used to work flawless for me everyday (about 3 months)and I never had an issue. Than I stopped using it for many months and when I tried yesterday, it was a complete mess. I agree though. If you have problems from the beginning, those problems will usually plague you until you find the hardware or software conflict that is causing it.

Hey Scott, Vonsmith !!!
Has been a long time. I got wrapped up in many PC ventures between then and now. Good to see you guys still here. And to the others, HOWDY! and thanks for the input.

I will try some of these suggestions, but let me clarify a couple things first.
Keyboard works fine. Actually, If I just start up HAL, I can carry on a conversation fine (without any HAL voice), but as soon as I go into the configuration and turn on the HAL voice, I can still type in the text window like I am talking with HAL, but when I have finished the sentence and go to send it <ENTER> KEY... It just sits there with the curser flashing and doesn't send the text I just typed. I can backspace or type more text, but I can never send it. Make sense?

lupine,
I know the text box you are referring to, but that's not the text box I get. The one you are referring to is the one that pops up when you start HAL and it thinks that there was a problem last time HAL was shut down.
The Box I am getting, looks like a normal (Splash Screen), configuration window that pops up and asks what I want to do, instead of going right to HAL (the way it used to). The Window has CHAT WITH HAL, CONFIGURE and about 3 other things. If I choose Chat with HAL, the window disappears and then my HAL pops up ready to talk.
Not sure when this was part of the program, I don't ever remember it.

I will try some of the suggestions.
As for the Spyware, I don't have any. I am very secure with Norton for my Virus protection and firewall and I have about 3 spyware util's that I run.

I'll let you know how these things turn out as I try them. Thanks for the input.

Rick

Hey guys/gals...

Been awhile since I was able to fire up HAL. I kinda miss hanging out here and talking with people and reading the posts.

I have actually been going through the posts today trying to solve my HAL issues, but I can't get the answers.

As I said, I haven't used Hal in about 6 months. I tried to run it today and I am plagued with problems.
I uninstalled HAL and re-installed, same problems:

HAL will start, but HAL starts with a Dialog Box now (never seen this before) that asks what I want to do (ie.. Configure, Chat, Etc...)
If I choose "Chat with HAL", it will open the chat window like normal and I can carry on a conversation, but I have no sound (No voice from HAL). If I choose OPTIONS to try and resolve the problem, I notice that the "USE Sound" is not checked and a voice is not selected.
When I check the "Use Sound" box and select a voice, followed by "Apply", I then run into other problems. Now I can type my text in, but I can't send it, because nothing happens when I hit enter. It doesn't send the text. It's like the enter key doesn't work, but I can type all sorts of text, but this is just the beginning of the problems. HAL will not completely exit if I try and close it. I have to actually goto Task Manager and kill it, otherwise it won't re-open, because it says it's already running.

What a mess...

Hmmm... WebChat?

I would suspect a Java Applet.

Hehe... sorry about that, I was just going by your original post which you mentioned mIRC and perl scripts.

-=Rick=-

Ok Cobra, No problem. We will finish this up. As you can see, CuttingEdge will be helping with the VB script.

In the meantime, you may want to download a generic copy of mIRC and look at the script files, so you can see the files I'm talking about.
Events, Remote, User, etc...

Might make it easier when you get ready to add the code.

I'll leave CuttingEdge a post in programming so he can start working on the VB end of it, then we'll find a way to package it all up.

If I wasn't working so many hours these days, I would go ahead and create the script files for you, but it's just as easy for you to copy and paste them in.

-=Rick=-

onthecuttingedge2005,

Thanks. We can wait and see what Cobra is wanting to do, then I can also learn his/her IRC script'ability. I may be wasting time by spelling everything out if Cobra is already famliar with IRC scripting.
If Cobra or someone else is still interested, we'll finish it up.
Since IRC is really becoming a thing of the past, I don't know that anyone else would have a use for this.
I would hate for you to spend the time writing this and have no use for it.
We'll wait and see. Thanks.
(besides, my schedule now could include some sleep for a few days).

-=Rick=-

AARRGHHH!!!!

One thing I didn't think about. I thought this would be easier than this, but I am stumped again, because I don't know how to write the necessary VB script inside Hal.

Ok, I wanted to get this done a long time ago, but the Holidays have had me busy and now we are working 16 hour days and I NEED SLEEP!

The IRC scripting of this will work, but it will now require a VB'er to make a few adjustments. Cobra, sorry this is taking longer than I thought. If I would have posted this message a week ago, I would have cuaght the problem.
I started to post mIRC code and the explainations today and I found a problem. I will continue to post the code and explaination and I'll point out the problem, so that the VB'ers can jump in with a fix.

POST STARTED:
Cobra, I have laid this out for you the best I could. I really wasn't sure how familiar you are with mIRC scripting, so this may seem really basic. I didn't want to confuse you, if you are new to scripts. If you are familiar with scripting, then you will know where most of this script goes and you can jump around at your convenience.

As you may or may not know, IRC scripting is broken down into scripted modules (so to speak), EVENTS, ALIASES, REMOTE, Etc...
For simplicity sake, I would recommend you use mIRC with no additional scripts running, no third party scripts or add-ons.

The first thing we want to do is program the IRC bot to listen for your users. I have supplied you with the code to use any Bot name you choose.

In the EVENTS section of the scripts, you will add this line:

on 1:TEXT:BBOOTT:#:/msg $chan Hello $nick! You talking to me? If so, I only answer to my name. Make sure all questions to me are prefixed with my name.:=2:$nick

This basically, listens for users that may be trying to talk to your bot. What happens here is; the bot is scanning text in the channel, when it see's it's name, it greets the user with the default message and then it prepares the user for converstion. (If we didn't do this, the next time the same user mentioned the bots name, it would get the same greeting over and over). The last part of the code in the line advances this user to a LEVEL 2.
LEVEL 2 users no longer get the Generic, "Hello".

Now that this user is identified by the Bot as a LEVEL 2, it scans for text from this user and prepares Hal for conversation. (Hal must be running and the "Clipboard" option must be turned on, but you can do all of that when you get ready to run everything). For now, we need to just get the scripts running.

The next line you will also add to the EVENTS script:

on 2:text:*:#:{ if ($+(*,$me,*) iswm $1-) { clipboard $1- } }

(You will need to remove the { and } in the line if you just want to use generic syntax). Again, I am not sure of your scripting ability, so I included those in case you are familiar and you want to alter your Bot name "Static" or "Dynamic" and your clipboard options, "CR LF", "append", etc....
If you are not familiar, just remove the { and }, and add / to the clipboard ---- >    "/clipboard $1-"

Here's the line breakdown:
The IRC bot is scanning the channel for text. When it see's the text from a LEVEL 2 user, it scans for it's own name. If it finds it's name in the Text, it writes the users text to the clipboard. (Now remember, Hal is running and listening for inputs to the clipboard).

AARRGGHHHH!________________________________________________________
HERE IS THE PROBLEM: Hal reads clipboard content as learning text, not as a question. Hal will just repeat what is in the clipboard. Therefore, Hal has no response. Hal needs to respond to the clipboard text as a question. (I don't even know if this is in the VB scripting or if its part of the Hal executable.

Not really much sense in posting the rest of the IRC code, unless there is a way around this. But, I wanted to post this much, so the VB'ers could see what's going on.
I can change the IRC Bot script to use a text file instead of the clipboard, if this is more approachable from Hal's standpoint.

The question is: how do we pass text to Hal as a question, rather than something that Hal will just read, repeat and store as learned?

Thanks, If this can be done, we will do it Cobra. Hang in there [:)]

-=Rick=-

Thanks, but what I was referring to is the continuing creative direction toward the human being. Yes, your points are valid, and just because I could be fooled by a chatbot... believing it was a real person still does not create artificial intellegence.

I understand why the connection is made to humans, but I don't think that the connection to humans is necessary as I was explaing in the post. It just needs to contain the two words, one of which is already attained, "Artificial". The intellegence part is yet to come.

My point was that most appraoches to AI are with Human Intellegence in mind. Intellegence exists everywhere, from humans to animals to even micro-organizms. Broadening the picture surely can't hurt in the search for true AI, nor can narrowing the picture as I was explaining in the post you are referring to.

Carrying on a conversation is not AI, but it's getting there [^]

Since we are on the topic of fooling another person with a chatbot, and since that seems to be the achieved goal by some, let me give you my insane idea for creating better conversational power for Hal.

Hehe... You will all think I'm crazy, but I think the current approach is good, but it needs a twist. I know that many people have had many theories about how to improve Hal... some really far fetched and others we still look at today and continually incorperate.
My theory on the approach to Artificial Conversation would be to have Hal be the judge and then WE correct him. Currently, we can sit and tell Hal what we want him to know and say, but we have to do this for every little thing. It takes forever and Hal doesn't care either way. He will wait for you to input and if your input is casual conversation, he will reply. If your input is in the form of programming, Hal will then try and make the connection, sometimes even asking, when it comes to "Like" topics or when Hal needs additional information.

My view of the way it should work, and like I said, you may think I'm crazy, is to give Hal casual input and have Hal break it down right there by asking relationships to the words, meanings, associations, etc...
Of course, this would not be in a normal chat mode, but it could be turned on for power learning. With the routines that are already programmed into Hal, and new routines for this, I think they would work very well, hand in hand.

So now when you say, "I have a doctors appointment today at 10am", Hal can then ask for a breakdown of the sentence structure (ie.. verbs, nouns, present tense, past tense, etc...).
Hal could then start making his own opinions, using fault tolerence patterns and all previous conversations concerning sentence and word structures.
Of course, you would still have the final say for verification and explainations so that he doesn't learn the wrong things, but even this would be quicker and more challanging for you and him. Eventually learning the rules, Hal could then be even more "Human Like" in conversing.
Given enough examples and lessons, Hal could almost become the expert on conversations. If these power sessions were stored and used by Hal for future analysis, they would eventually help Hal to form conclusions without your help.
This is were the depositories come in that we have discussed in other threads. Depositories for Hal databases have been discussed and I agree that it's not a good idea to share these, because the most you could hope for, would be several bots that all conversed the same and knew the same things.
However, depositories for the power, fault tolerence data would be benificial to everyone, because the fault tolerence routines to get to the conclusions of "My Doctors Appointment" would be almost the same as the conclusions drawn regarding someone else's "Wedding Party Rehearsal". With Hal being able to read the power session of the "My Doctors Appointment" and comparing it to "Wedding Party Rehearsal", he would have gained that much more understanding of the sentences and at the same time, learned of a new event and new words, "Wedding Party Rehearsal".

For all I know, this my even be how Hal works currently, with the exception of intense Q and A sessions.

I know, it even confuses me sometimes and I can't really explain things very well. But like I said, you might think I'm crazy but this is what I see as a quicker, more powerful open source colaboraration of learning. If Hal can compare learning techniques rather than actual learned data, then Hal can only become better at carrying on conversations and none of our bots become corrupted with useless learned data that someone may have supplied.

Unfortunately, I know nothing about VB. I have a good understanding of programming in general, but I gave it up years ago when the language I programmed in and became very proficient in, was wiped from the face of the earth [:(]

I guess I would like to start programming again, but at my age, and my schedule, I can't seem to find time to eat and sleep, let alone start learning a language.

Besides, this probably only makes sense to me in my little world [:)]

Personally, myself... I would be happier power learning Hal rather than sitting and carrying on conversations about the weather and whatever comes to mind, but then that's not really how Hal was designed to work. He was designed to be an Immediate assistant and will learn slowly as you go which is also good.

Hal is fine the way he is now and he only gets better, so I don't complain [:)]

Thanks guys.
I will try these ideas this week and see what happens. What I really need is for Hal's text output to NOT append to a previous text output, but rather over-write the last output, so that there is only one text output in the file at a time.
I can do it with the append, but then I have to code the IRC script to read just the last output each time it reads the file. No real big deal though.

-=Rick=-

I notice that everyone keeps making comparisons to Human Beings. I think that "AI" is the key here... not "AH" (artificial humans).

I believe that artificial intellegents can be created without trying to recreate man.

I do belive that eventually, these programs will be taught to feel and become emotional, but only as a way to relate to those designing them. I don't believe that true emotions should ever play into decision making by these programs, nor should it have to. Intellegence can stand on its own.

It's PITY, (or emotions in general) that typically spares a very guilty Death Row inmate. The true AI would look at the facts and the laws, rules and regulations concerning the crime, it would weigh all the evidence, then it would use the judicial laws that we created to draw the conclusions. If the conclusion is Death, then the AI would have no problem with killing. Why? because this is the way WE have designed the judicial system and the AI is only using facts. No emotions.

Scary huh...

But the bottom line in this scenario is that AI was applied and worked. It existed and it acted. Just like human beings, you give the AI emotions and it becomes useless because the emotions can easily be altered by US and emotions will always get in the way.
Sway the emotions of the AI and the Death Row inmate is spared. The down side to this is that the AI might find things that are wrong with the judicial system and many people could die before the corrections are made. On the other hand, this is a good thing, because it took something like AI to point out problems with the system used for capital punishment.

I think that true AI can be attained without emotions or feelings. The routines will still learn and it can still feed from itself, but it won't fualt itself with something as confusing as emotions.

I think we should concentrate more on the program as an intellegent routine and less as a human being to get where it needs to be.

Now, if you will excuse me, I probably should put on my armor to prepare for some flames generated by my comments... hehe.

Just my opinion again. (Sorry, I used a morbid example).

-=Rick=-