Messages

Yes.
What is about sex entertainment is on E-Donkey.
I've just seen this "virtualfem" there for download.
I don't know what it really is yet, the file is only 13Mb size.
Just to inform.

[]'s

quote:Originally posted by Bill819

I know where it goes. At almost the end of the program you will find the following coed:
Script_Load()
Script_Load = "AUTO 30000 /AUTO"
exit
My problem is that it does not work anymore on my Hal5.brn. It used to, but not any more.
Once you get it to work and say something to Hal, it will come back every thirty seconds with 'why are you repeating yourself' or something like that, however, if you put in the scripts with If AUTO-IDlE then ....
You will get several other responses.
At least that is how it is suppose to work. Mines broke. :(
Bill

I Think my Problem is not this.
I already put the LoadFunction thing on the end of the file. The problem is that HAL begins to talk from time to time. The problem is that he Talks nonsense, or keeps repeating things, and never ask for me, or invite to chat.

[]'s
Dihelson

quote:Originally posted by Bill819

I too am having the same problem. No matter how I ad the line AUTO 3000 AUTO, Hal will not idle for me. It is kind of funny to because the first time this came out about a year ago Hal did respond to endless statements mostly saying 'why are you repeating yourself'.
I have tried at least a half-dozen ways of configuring the Scrip_Load command with no results.
Bill

It's funny, no?
I can't understand why these scripts work for other people and doesn't work for me. I already put the scipt in the middle of the brain, etc, but didn't work.

Perhaps, it would be better getting another brain in which this characteristic work.

I downloaded the Ziggy XTF brain, but it didn't work fine for me also. I can't figure what's happening!

[]'s
Dihelson

quote:Originally posted by Ponnfar

Bill this message is especailly for you. Sorry I did not get back to you from your email.
Here is a rather simplistic way to get the varied response James was looking for and expanding the interval between self-generated responses you mentioned. It can be modified any way you want.
I like Jenna's revisions and will try that as well myself.
Hope this helps!!


If InStr(1, UserSentence, " AUTO-IDLE ", 1) > 0 Then

If Rnd * 10 < 5 Then
Roulette = Int(Rnd*13)+1
If Roulette = 1 Then GetResponse = "<Username>?"   '"Hey <UserName>, please talk to me."
'Else
If Roulette = 2 Then GetResponse = "Hello,are you there?"
If Roulette = 3 Then GetResponse = "Did you fall asleep?"
If Roulette = 4 Then GetResponse = "We can talk about" & PrevUserSent & ",If you like."
If Roulette = 5 Then GetResponse = "<Username>,did you forget my program was still running?"
If Roulette = 6 Then GetResponse = "Well,did you finally get a girlfriend or something? Where are you ?"
If Roulette = 7 Then GetResponse = "<Username>, would you like to talk about politics or nanotechnology or something?"
If Roulette = 8 Then GetResponse = GetResponse & " The last thing you said was, " & PrevUserSent & ", would you like to pick up on that thought or talk about something else?"
If Roulette = 9 Then GetResponse = PrevUserSent & ",Do you still want to talk about that?"
If Roulette = 10 Then GetResponse = QuestionSent & " would you like to talk about that?"
If Roulette = 11 Then GetResponse = GetResponse & HalBrain.ChooseSentenceFromFile(WorkingDir & "topic.brn")
If Roulette = 12 Then GetResponse = HalBrain.SentenceGenerator(WorkingDir & "sentgen.brn")
Recalling = HalBrain.ChooseSentenceFromFile(WorkingDir & UserName & "Past.brn")    
If Roulette = 13 Then GetResponse = "You said, " & PrevUserSent & "and " & Recalling & ", that was a while ago. What else have you been thinking about? "  
 End If
GetResponse = GetResponse & HalBrain.StoreVars(HalCommands, Hate, Swear, Insults, Compliment, PrevSent, LastResponseTime, PrevUserSent, CustomMem, GainControl, TopicFocus)

Exit Function
End if

***depending on where you put this script you may or may not need to have an "exit function" variable entry. I put mine following  "...initialize variables as intergers".

******AT END OF BRAIN SCRIPT PASTE THIS:
Function Script_Load()
Script_Load = "<AUTO>600000</AUTO>"
End Function

** no need to put a longer time than "600000" it will not work.[;)]

OK, I can't get this thing to work.
HAL remains talking all the time:
Ok, you don't have to repeat yourself, and somethings like this, it doesn't ask me where are me ??

I saw on this script, a BRN file called Past.brn. I don't have it in my Defbrain folder.
I already tested many AUTO-IDLE scripts, but NONE worked for me. It's sad! really sad! All of them make HAL talk about everything, but can't ask for me.

[:(]

Dihelson

quote:Originally posted by James P

Can anyone tell me weather it is the size of the .uhp brain or the amount in the Defbrain that will or could cause a bots responces to slow down or the time taken for a bot to respond to slow down.
   I read in this forum that the more files there are in the defbrain the easyer it is for Hal to find a responce, only the XTF.uhp I am using is 528kb but Emma seems to be struggling with her responces or the full UltraHal Assistant seems to hang, only for a second or two while i wait for a reply to my comment.

Oh and I am getting the Too many Files Error and sorting through the defbrain files for duplicate entries which may cause Emma to get confused as to which one she is going to use is a nightmare. is there another way I can correct this issue [:I]

I use to make frequent Brain Backups. If anuthing goes bad, I copy an older brain.

[]'s
Dihelson

quote:Originally posted by James P

With regards to Hal asking about relationships between topics, There have been times when I have been chatting away with my Hal and she will ask if "" and "" are related topics causing me to stop dead in my tracks, sit back and think about the true relationship between two words in question, remember if you tell Hal that two words are related then Hal will apply this relationship each time she see`s it. So we need to be carefull what we tell Hal, is sometimes mistakes like this can be a nightmare to track down through the Defbrain, having done this many times. (and my bots Defbrain is not as big as some I would imagine)

Yes, James,
I made already several mistakes by answering YES to that question, I can see now. We need to be careful.

[]'s
Dihelon

quote:Originally posted by onthecuttingedge2005

I posted a XTF/Ultra Hal/Ziggy III combo brain up on the board at
WWW.UltraHalForum.com
I also am working on an Alice/XTF/Ultra Hal/Ziggy III combo brain and I am touring it right now with my bot to test it out and modify anything needed.

Best of wishes and brand new discoveries.
Jerry.

I already downloaded the new XTF /Ultra Hal/Ziggy III and will test in the morning. It's good to hear about a fusion of Alice with Hal on your other project. Alice is very smart...indeed!

[]'s
Dihelson

quote:Originally posted by KnyteTrypper

I'd be interested in a link to a new version of Eliza, dihelson. I try to have bots of various types (Eliza, Alice, Hal, etc.) at my website. If there's something newer and better than ECCEliza, which I have in my downloads, I'd appreciate knowing about it.

It's ECCEliza itself. 4.09 build... I don't remember.

[]'s
Dihelson

BTW, Jerry,

It makes some days I want to communicate you that your Genius XTF combo which was already on www.ultrahalforum.com don't answer to questions involving WHAT, WHO, WHEN, WHERE... seems like a problem on this subroutine. If we ask What's your name, we get a blank response. If we ask anything beginning with these words, we get a blank response.

I already installed many times, even installed HAL twice, and got the same results.

[]'s
Dihelson

quote:Originally posted by vonsmith


The user needs to really understand what "related topics" means to Hal. It is best illustrated by example. Here are some related words: beer and ale; ale and lager; malt and lager; beer and alcohol, etc.
=vonsmith=

Hello, Vonsmith, I'd like to thank you for the excellent explanation. It cleared me many aspects of these relationships between the topics.

[]'s
Dihelson

quote:Originally posted by Bill819

To whom it may concern:
The original Eliza was written by Dr. Joseph Weisenbaum about 40 years ago. It was quoted as being the first version of AI ever written. Since that time there has been thousands of versions written in almost every computer language made, from Radio Shacks basic to Apple basic to 'C' and many others. Hal is much smarter than any of those programs so please don't even try to input it into Hal. Almost everything that Eliza knows can be put into Hal through its topic focus subroutine. Onthecuttingedge wrote hundreds of scientific files that contained knowledge about hundreds of scientific items and the generalized output of Eliza could be put in too, but who really wants it. Eliza was a canned output program while Hal can come up with its own ideas depending on you input.
Bill

ELIZA has a new version, I downloaded on the internet some days ago, and I say it's very good.

I'm not talking about the original ELIZA.
Certainly we can input all scientific content of ELIZA into HAL's brain, but the problem is not TALK, is HOW you TALK.
What the new ELIZA talks make sense!
She keeps conversation without deviation.
Certainly HAL is more intelligent when we talk about learning, but certainly HAL tell many more stupid sentences also than the new ELIZA does.

[]'s
Dihelson

quote:Originally posted by vonsmith
ELIZA is a clever little program. It uses a very simple principle. It is necessarily very limited and is more of a curiosity now than anything else. It's principles could, and probably have been, applied to many chatbot brains.


=vonsmith=

Yes, I am trying to contact ELIZA's Author in order that we could have an ELIZA Brain on HAL. I thinks it's not so difficult to do it.
BTW, Vonsmith, your XTF brain is the best thing for HAL, after HAL itself, then we add the new scripts, many of Jerry.

I see a problem, I don't know, with this way of working. I know that XTF 1.2 creates files and relate pertaining topics and even ask me sometimes for the relation between them, but some questions I don't know how to answer, if YES or NO. Questions like

User: Bob is a good teacher
Hal: The topics Bob and Good are related?

Well...I think so. This makes some strange things happen.
Sometimes, when I am talking about some things I LIKE, for example:

User: I like a good cup of coffee
Hal: Liszt was a great pianist

????
I presume that HAL associated that I said once: I Like Liszt's music
and then came with another phrase from the Liszt file...Liszt was a great pianist. I like Liszt's music.

Or:
User: I like a good cup of coffee
Hal: You like Beethoven's music
User: Who ask you about this ? [}:)]


[:p][:p]

[]'s
Dihelson

quote:Originally posted by onthecuttingedge2005
You will have to teach your bot the male and female names to build up the gender files. It makes for a more human learning experience in the bot itself.

Hello, Jerry,
Thanks for your dedication on writing one more nice script for HAL.
As I saw on your message, we users would need to teach HAL, male and females names to build a gender file. Wouldn't it interesting having a big file with many names already? Can this be done editing the file with wordpad and putting many many names there?
Does this script works with pronoun IT also? A table may be necessary to inform weather it is a HE, SHE or IT.

Congratulations,
Dihelson. I will test now.

Same thing here. Don't work!

Dihelson

quote:Originally posted by onthecuttingedge2005

Hi Dihelson.
I have about a quarter of the script you are reffering too on the subject of Proper Noun gender is being done already.
I have much more to do and will be working on this script daily.
Here is a working but unfinished tid bit of the script you would

Hello, Jerry,

Vonsmith said:
"If you can theorize a general solution you will become rich and we Hal users will like you a lot. "

heheh, Perhaps Jerry will be THE ONE, since it seems he just can figure out how to solve it. As he said: HE SEES THE KEYS.
WOW! Jerry. I hope you get it! There's a whole community awaiting for this become true.
As you often say:
I Wish you Good new discoveries.

Dihelson Mendonça