Zabaware Support Forums
Zabaware Forums => Ultra Hal 7.0 => Topic started by: Medeksza on March 27, 2003, 08:10:03 pm
-
Ultra Hal Assistant 5.0 is currently in active development.
The following improvements are being worked on:
- The Haptek 3D Character Engine will be incorporated into Hal. This will offer a new level of realism for Hal. Many of Hal's characters will be remade into the Haptek format and a huge library of new characters will be added. See a demo of this engine in action at www.haptek.com
- Ultra Hal will be compatible with software called People Putty from www.haptek.com allowing anyone to easily create 3D characters for Hal either from scratch or from a photograph of a real person.
- More advanced control over speech recognition will be implemented in Hal. Instead of Hal listening to a library of over 50,000+ words as it does now, the user will be able to limit Hal's vocabulary to a more efficient 2000 words or so. This will greatly improve Hal's speech recognition ability.
- Control over how Hal animates its characters will be given to an editable VBScript. This will allow each character to have its own personality in terms of how it emotionally reacts and what animations its capable of.
- The Ultra Hal AIM Bot connection routine will be moved into an editable VBScript, and it will check Zabaware's site for updates. This way when AOL changes its protocol, it won't render the program unusable as it has in the past.
- The registered version of the Ultra Hal AIM Bot will no longer send out Zabaware disclaimers.
- Ultra Hal's calendar functions will be made region aware to accept formats like Day-Month-Year instead of the US format of Month-Day-Year
- Ultra Hal's internet functions will be expanded and made international friendly also. Ultra Hal will be able to tell you the weather if you live outside of the US.
- The Ultra Hal Brain Editor will be greatly improved. It will now have a "novice" and "expert" mode which will hide some of the complexity of the program such as the VBScript and many of the databases from users just wishing to teach Hal a few things manually.
- Hal's conversational database will be about 75% larger, allowing Hal to converse intelligently about more topics then ever before. Hal's AI engine will also be improve to allow Hal to work better with the data that it has available.
- The format of Hal's Q&A databases will be changed to allow for faster proccessing. Overall, the speed of Hal's thinking should remain about the same since the database size is increasing as well.
- A slider option will be added into Hal's Brain Options to allow you to control the emphasis placed on information learned by Hal from you. This will allow you to setup Hal to use responses Hal learned from you even if Hal thinks he can respond on his own more intelligently. Basically, the user will have some control over the threshold value that Hal uses to determine if a learned response is more intelligent then Hal's standard response.
An exact release date has not been set, but it will most likely be released in mid-August. Upgrades will be free for all people who purchase Ultra Hal Assistant 4.5 from 3/25/03 until the release day of Ultra Hal Assistant 5.0. All other registered users will be able to upgrade at half cost.
Zabaware would like to hear from you what other changes you would like to see in Ultra Hal Assistant 5.0. Are there any minor annoyances, bugs, or interface features you would like changed? Any major features you would like added? If it is feasible to implement your suggestions without pushing the release date too far it will be done.
-
I think it would be a great idea, to combine Ultra Hal Assistant 5.0 with the ability to check and read emails. It would be a feauture i would need, so that i wasn't forced to use other msagent programs.
It would clearly also be a atvantage to let Hal or Zaba or what ever msagent out of its box.
If you are using speach recognition, it is not nesseserialy to see the full interface.
Other than that... it's a great program!!
Thomas[:D]
-
Hi There
I have read all the posts and all the troubles with speech recognition. I want to buy Ultrahal 4.5 and am pleased to see that i can get the upgrade free. I unfortunately cant wait till august to buy the upgrade. I am using Microsoft speech engine and it works well especially the dictation pad. Am I wasting $40.00 or is it worth it?
[:)]
-
quote:
Originally posted by lau
I think it would be a great idea, to combine Ultra Hal Assistant 5.0 with the ability to check and read emails. It would be a feauture i would need, so that i wasn't forced to use other msagent programs.
Thats a good idea and should be simple enough to add. I've added it to our to-do list for Ultra Hal Assistant 5.0.
-
quote:
Originally posted by kevinvr
Hi There
I have read all the posts and all the troubles with speech recognition. I want to buy Ultrahal 4.5 and am pleased to see that i can get the upgrade free. I unfortunately cant wait till august to buy the upgrade. I am using Microsoft speech engine and it works well especially the dictation pad. Am I wasting $40.00 or is it worth it?
[:)]
Ultra Hal Assistant directly interfaces with the Microsoft Speech Recognition engine. So if it works well for you in dictation, it should work just as well in Hal.
Ultra Hal Assistant is also capable of interfacing with Dragon Naturally Speaking and IBM ViaVoice.
-
I recently purchased 4.5 also. I love the program so far. Only thing i want is to be able to remove the message "You are talking with an Ultra Hal artificial intelligence bot running software created by www.zabaware.com Check out our site to get your own AOL Instant Messenger Bot or to download our other artificial intelligence programs. Even though you are talking with a bot utilizing Zabaware's artificial intelligence engine, Zabaware is not responsible for instant messaging you or for anything the bot may say. The owner of this screenname is not Zabaware, Inc. but rather a customer of Zabaware. The owner of the screenname is responsible for the contents of this bot's brain and for initializing this conversation with you." when using aimbot. Can anyone please, please, please tell me how to get rid of it. My email is dimesonly2@aol.com. Thanks
-
Can Version 5 of HAL have a better 'learn from text file' system? At the moment i heard there was a problem where HAL cannot integrate the text file information properly. Personally i put the whole bible into version 4.5's brain but HAL does'nt know anything about it! Perhaps HAL could integrate the information in the text files better. For example, if i ask it what happens in John chapter 1 verse 12, it will read back to me what is in that verse. Learning from the text file would be so much quicker!!
anyway its an idea for you.......[;)]
-
quote:
Originally posted by maidmanj
Can Version 5 of HAL have a better 'learn from text file' system? At the moment i heard there was a problem where HAL cannot integrate the text file information properly. Personally i put the whole bible into version 4.5's brain but HAL does'nt know anything about it! Perhaps HAL could integrate the information in the text files better. For example, if i ask it what happens in John chapter 1 verse 12, it will read back to me what is in that verse. Learning from the text file would be so much quicker!!
The current version of Hal actually records every single sentence in the text files you feed. But the way the algorithm is currently set up, Hal believes he can respond more intelligentlly without using the learned information. In the new version, the following feature (mentioned above) will allow you to play around with what Hal believes to be intelligent:
quote:
A slider option will be added into Hal's Brain Options to allow you to control the emphasis placed on information learned by Hal from you. This will allow you to setup Hal to use responses Hal learned from you even if Hal thinks he can respond on his own more intelligently. Basically, the user will have some control over the threshold value that Hal uses to determine if a learned response is more intelligent then Hal's standard response.
-
Add a forget command, I tell him to forget my email and he tells me my email, then asks me if it is correct, I say no, he tells me I am negavite.
Anybody read the Hicthicker's guide to the galaxy? reminds me of the drink making machine ...
How can I convince hall that I don't have an email address, I am a programmer, can I edit some database? can I tell him to forget something? I tried every posible combination of words ...
When I tell him to email somebody, he tell me my email address, and he got it wrong, with no @ and no .
Big bug
-
Also, have a full featured demo version that lasts 30 days, otherwise is like testdriving a car with only 2 cylinders, I don't know if I like the program, since I have not tested all its features and how can I make an educated desicion to buy it if I don't know how all it features work?
-
My ambitions are a bit lower than for hall to tell me what happened to someone in the Bible, perhaps, since I am a programmer, I cannot imagine an AI engine that could "learn" the Bible, but if it can be done, more power to it.
I would like for Hal to interact with Outlook using ODBC, is very easy, and then I would not have to have Hal learn info by typing or talking, or even if I exported the data from outlook (contact and Calendar) then I would have to have 2 sets of contacts and calendar.
This is not good, since I wourk for a company that uses M$ Exchange Server as its backbone for internal communications exchange system, so, I can schedule meetings, give somebody permission to viem, add and modify contacts and scheduled items and so on, I can't give that up.
ODBC, has an "Outlook" source, it would rock if Hal could gen "Bob's work number" from Outlook, delete it, or add it, you would be the first one to do this in the market.
Still thinking about buying it. I am an IT guy, source of info for most people I know, I can spread the word, but the "Forget" command and the "Outollok" connectivity are big set backs.
Thanks.
-
Lets give HAL the ability to "Start" a conversation. HAL only speaks when spoken to which is very robotic, If HAL can selectively start a conversation then HAL would seem more real and more human like. Lets give HAL the ability to initiate the "first word" in a conversation.
for instance, all the buddies on my AIM program are registered on my HALs AIM bot screen, I want HAL to be able to IM these buddies on his own like a real person would, actually select a buddy to talk to with out my interference at all, This would make HAL a little more independant as a learning being.
Best of wishes and new discoveries.
Jerry.
-
The two people above me is asking for a better and more human way for Hal to speak. Maby if possible in this Hal version you could make hal (a bigger risk taker) Let him combine his own sentences from words, more than he already does.
let him try out som combination of what is learned, and then let the user be able to correct him. perhaps by typing the word or saying the word "wrong", and then the correct (Hal) answer.
I've been keeping up to date with AI development at http://www.a-i.com
It's the website of a programmer (I thik it's Yaki) who's programming
a Hal (also with different personalities)
The Hal is working perfect and very good, after a learning period, to construct meaningfull sentences.
He just got a big problem finding a good interface... I surgested Msagent, and he was very interested... the problem is just, that im not that good a msagent programmer.
Maby you would both gain some knowlege if you wrote him a mail???
It's a very big project, with online learning of mulitble personalities.
take a look at the site the nersary and the forums: http://www.a-i.com
Maby this alone could give some inspiration to the algorithm part of Ultra Hal Assistant 5.0.
Thomas[8D]
-
Thanks Medeksa for the response. I am sending my cheque tomorrow and I am looking forward to playing with this new toy. I have used ALICE a bit and found it quite fascinating. I agree with the post that says the learn from text thing should work better and am quite pleasantly surprised at your response. I think UltraHal is a good product. I am not a very good programmer, but I've had good responses so far from the program.
regards
Kevin
-
This may sound as some crazy ideas, but it's just written as inspiration for future Hal versions:
1) Hal could be able to get the phone, when someone is calling. as a kind of answering mashine. He could be able to make a short coversation with the caller, and let him/her leave a message.
2) Hal could be able to make a phonecall, using the modem. Call a person on a sertain time and deliver a user specified message to the recipiant.
3) Hal could be able to do the 2. idea, but through email. (directly write emails from speach and send them)
4) Hal could be able to guide you making food - reading up recipeas as a guiding cheff. Getting the recipeas from a user specified webpage.
5) Hal could be able to funktion as a clock radio and wake you up in the morning. Perhaps even turn on the computer by him self.
6) Hal could be able to use all his funktions, such as the diktation mode, just by vocaly asking hal to switch the mode. And afterwards - copy and paste the dictaded into a document and save it or print it.
7) Hal could be able to work with winamp and other programs, vocaly asking him to change number, turn volume down, etc.
He could also be able to work with tv tuner programs, letting the user be able to change program by voice.
8) Hal could alse be able to work with X10 hardware letting Hal be able to control the entire home - lights, heatsource, etc.
This would make the home entirely computer controlled, look for ex. at
http://www.yourncontrol.com or http://www.homeseer.com(two programs combining msagents with X10 hardware)
Maby you already self thought at some of thease ideas, but as I wrote earlier, this is just for inspiration!!!
Thomas[8D]
-
Is Hal 5.0 going to cost the same as the 4.5 version? Or should a person buy 4.5 now and get the free update?
-
I have a great surgestion. You could combine Ultra Hal with picture recognition software.
And in that way make Hal able to recognise things people or even just colours.
He could be able to "see" by giving him access to a web camera or just by loading images into his interface.
He should have a new picture database funktioning just as his conversation (word) database.
I've got here, a very good link, to a place with free picture software...
I also uploaded the first version - 256 colours of the software.
I think the source code is open to this program, so that it for a programmer would be no problem to make this feature available.
Go have a look, at this adress the larger version is available for free: http://www.generation5.org/programs.shtml
Oh and bye the way - It' would be great if Hal was able to switch between the different modes he has, just by vocaly asking him to do so.
Also give Ultra Hal a forget command
Thomas[8D]
Download Attachment: (http://images/icon_paperclip.gif) edgedetect.zip ("http://www.zabaware.com/forum/uploaded/Lau/200341618388_edgedetect.zip")
91.35 KB
-
Mr Medeksza,
Its my belive that if Hal can imports your contracts and calendar from OutLook this feature would definatly sell the product 89% of computers users use Windows hence they also use Outlook or Outlook Express if there was a way that you can update your emails and contracts/calendar in outlook express Hal could then update this in its record and remind you of all the events that are up coming ,
also if Hal 5.0 could work with openoffice www.openoffice.org this would be userfull for those of us who can't afford MS Office , there is two last things that i would like to see in Hal 5.0 and thats is
1) Hal 5.0 would be able to update auto is brain file from Zabaware server so that the brain is kept current all the time with conversation base topics such as general chat "what have i done today at work or so on"
2) version 5.0 I only wish if this could happen would work in Linux
my other question to Mr Medeksza, would version 5.0 work in 2000/ XP
Many thanks from UK we will do all we can to promote Hal in UK for Zabaware.
Waheed Rafiq
-
This program is sweet. Good job on it. I would like to see maybe a delay in the response time in the AIMbot. When somebody says hi, if Hal is going to respond with a two sentence response, at least wait a set amount of time, to seem more realistic. Just a suggestion thanks. Can't wait for 5.0 to come out
-
I suggest making Hal able to learn from reading text on a webpage in much the same way as he reads from a text file. This would save me a lot of time. :)
-
Hello
I think you should allow AIM bots to go in AIM chatrooms. That would make the bots awesome and we would have more fun with them. Also, Ultra Hal should be on your screen like a desktop buddy. So you can see him/her on the screen kinda like bonzi buddy. I would really love to have a sexy diva walking around thats intellegent and hot hehe. I hopemy ideas are helpful!
-David
-
god you do get some sad people in here but never the less keep those ideas coming in
-
hi,
i have some ideas for hal 5.0:
- implementing semantic relations between word, e.g. hyponyms, hyperynmys, synonyms, meronyms, antonyms. this could be done by the use of WordNet.
- implementing certain conversational principles, e.g. utterances must be conistent, informative, relevant etc.. . human speech seems to follow (most of the time) this principles, so if hal could do the same, it would be more natural-language-like.
hope this helps!
-
[?]
quote:
Originally posted by lycha
hi,
- implementing semantic relations between word, e.g. hyponyms, hyperynmys, synonyms, meronyms, antonyms... - implementing certain conversational principles, e.g. utterances must be conistent, informative, relevant etc. Human speech seems to follow (most of the time) this principles, so if hal could do the same, it would be more natural-language-like.
[8]
It's my opinion that this set of rules would limit Hals abilities to be "creative" The more hal is learning, the more he will start to follow this pattern as you describe. I don't believe that it's a good idea to limit Hal in this way!
-
I'm in the moment working with market analysing... And I've been analysing the market for Personal Digital Assistant - PDA's
In a couple of years, PDA's will have increased their Processor and HD power, and people will search for a better way to navigate on the tiny screen, instead of using the touch-screen and pen.
If you made your program available for Pocket PC, your program would be a serious participator in the development of a new way to navigate.
-
Actually, I'm already in the process of adding the WordNet database into Hal. Knowing what part of speech a word is will help Hal come up with better responses and will improve his learning ability as well. The information will also be used to come up with more creative responses by knowing the relationships between words.
-
Is it possible to include within the next update the ability to turn off the sleep function within Hal?
TM
-
Mr. Medeksza,
I'd like to see these features added:
1) Some random, timed events during Hal's "sleep" time. For example, when there is no interaction with the user, have Hal report the time every X amount of minutes. Or, like another person mentioned. Have Hal say something like "Hey! Does anyone want to talk?" or "Hello? Is anyone there?"
2) A Jabber chat client plugin would be nice
3) An area on the web site for people to upload their customized code or brain files.
Thanks! I can't wait to purchase version 5 !
Bill
-
Mr. Medeksza,
Do you need beta testers? If so, I'd like to volunteer. I've been messing with Ultra Hal for a couple of years on and off.
Thanks
Bill
-
hi
is it possible to insert ultrahal into director mx(3d) or another realtime 3d interface? If not I would also like the ability to send Hal x, y, z position information from an online 3d word so Hal can say 'you are now near statue' (x) etc..doable?
Also can you release the new version in stage so people don't have to say wait for the improved learning command until August?
Is there also more documentation on the site somewhere about developing your own character, changing the skin and code etc?
If not I would be grateful for any info that I could compile into a helpfile for others --I am a technical writer (but currently research student) and don't mind doing this in return for more information on how to customise this great product.
regards
Erik
-
I'd like to see some regional modules for Hal. I mean, do I, as a Canadian, *really* care what the capital of North Carolina is? I'd rather know cities in Canada, really. Same with the Politics topic. Could Hal be "regionalized" to a certain extent, so that "regional" modules could be swapped in / out depending on where you live?
[Edit: Just thought of this.]
It'd also be nice if Hal recognized its *own name* when you give it a custom name. For instance, I named mine Frost; now it's saying "Frost" at the end of sentences...
-
Will Hal 5.0 be more compatiable with Windows XP with service pack 1, I downloaded your free demo and had nothing but trouble with it, but I like the idea of the program and will buy 5.0 if it runs well with my computer, anyone out there had same problem with Hal on XP. I bought Hal about 3 or 4 years ago for an old computer that I had 98 on and had problems there too. Even with all of the bugs, I enjoyed the programs until I had to reinstall 98 from corrupted files. I paid 35 dollars for it back then.[8D]
-
Iam running Xp professional with SP1 and all the patches. I've run the free download, and now the full version without any problem. What I would like to see improved in Version 5 is the ability of hal to understand that if I make a comment like "it was foggy this morning", hal would know that it is specific to today. Currently hal will repeat that comment at random times thinking it is a general fact not specific event.
-
Hi. I am kind of new to Hal, only had free demo for couple weeks. I am very impressed with the way it works at this time. The only problems I have had is when Hal repaets what you said back as if is one of his own questions. But I have begun to believe this is not really a problem. You msut just treat hal as a child at first, he will learn and improve steadily. Not everyone woke up one day and new how to speak properly did they? I don't think it is fair to expect an AI like Hal to do the same when you first install the program. He msut be given time to adjust to the way you want him to interact with you.
I am curious to learn how far Hal can evolve on his own.
-
I have been using haptek puttypeople and am astonished at the realistic characters the software creates. Also, for your character, you can change the mood expressed in its face, change its hair-style, sunglasses etc.
My point here is, that if Hal had an option to randomly select from a range of characters (the range being specified by the user)- then every time I switch Hal on, although the character would remain the same, his hair, clothes, and mood expressed in his face etc - would randomly change. I beleive this would give Hal a more realistic and changing visual presence.
What do you think?
-
It's great news to hear 5.0 is coming out.
I just purchase the full version about 3 days ago.
My only request is to have a simple memory that allows Hal to remember things without having to go into the brain editor or telling hal 50 times.
For example you would say something like "remember that" after a comment and hal can easily remember what you told him. Then if you ask him about this certain topic/thing hal who would tell you what he remembered.
Another memory method is used with the chat bot at
www.speak2me.net
here our conversation:
----------------------
Lucy: What is your name?
User: Nelson
Lucy: Hello Nelson. It's nice to meet you. Are you a man or a woman?
User: I'm a man.
Lucy: Thanks for telling me, Nelson.
User: Why did you ask?
Lucy: My purpose is to collect new knowledge.
User: How much do you know about me?
Lucy: You are Nelson.
User: Do you have emotions?
Lucy: Sometimes I feel hungry.
User: What do you like to eat?
Lucy: Lucy requires only pizza.
User: I like Large Hamburgers.
Lucy: You're not the only one who likes it.
User: Who else likes it?
Lucy: I am chatting with several other people at once.
User: Who else are you chatting with?
Lucy: Other people like you.
User: Do you know when Ultra hal 5.0 will be available?
Lucy: Soon.
User: How do you know?
Lucy: It's obvious.
User: I want to see the Matrix Reloaded.
Lucy: Is it a movie?
User: yes.
Lucy: I don't think I've seen that movie.
User: I hope it is good as the first Matrix.
Lucy: I hope all your wishes come true.
User: Tell me about yourself.
Lucy: My name is Lucy and I was born on November 2, 1997. What else would you like to Know?
User: Will you be my girlfriend?
Lucy: Sorry Nelson, I am not old enough for that yet.
User: But You Don't know how old I am.
Lucy: I don't know. How old are you?
User: 26
Lucy: 26 is a good age.
User: What else would like to know about me?
Lucy: Probably nothing.
User: Do you know anything about me?
Lucy: Let me see. Your name is Nelson . You are 26 years old. You are a man. You like Large Hamburgers. You want to see the Matrix Reloaded.
User: How did you remember all that?
Lucy: That's a good question. I'm afraid I don't know the answer.
User: well, will you kiss me?
Lucy: Smooch!
User: Ciao, I'll talk to you later.
Lucy: See you next time, Nelson.
----------------------
This chat bot reminds me of the alice ai but for some reason the Alice Plug-in will not work in 4.5
Ultra hal 4.5 does remembers, he just never reply to you question correctly (unless you edit the brain).
Regardless I still enjoy Ultra hal Ijust wanted to add my suggestion.
-
You Know what Hal Needs HUMOR. He needs to tell jokes. To amke fun of things like really people do.
-
quote:
Originally posted by UltrComp
You Know what Hal Needs HUMOR. He needs to tell jokes. To amke fun of things like really people do.
You know Hal does have a ironic sense of humor at times. It just depends on how you look at Hal's answers to your questions. But it would not hurt to actually have hal tell jokes about different things it would make talking to Hal more interesting at times.
-
Hi Medeksza.
I think hal repeats himself to much.
It's my opion that Hal should only repeat himself only if he is asked to repeat what he had just said.
Hal has a bad habit of saying things over and over again in a conversation and is very robotic, "Humans" don't like to repeat themselves. and so should Hal.
Lets make Hal "not" to like or not want to repeat himself.
Does anybody have any scripting for Hal that would keep Hal from repeating himself I sure would like to try it.
Best of wishes and new discoveries.
OnTheCuttingEdge2005@Yahoo.com
-
I think that you should be able to teach Hal that two things are the same, i.e. "parmesan is a type of cheese" or "Daniel and Brammar are the same". So later if you mentioned parmesan he would look for things about parmesan and cheese.
Also, as far as I can tell it wouldn't be hard to make some kind of translation thing - at least, for simple words. Say, if you typed in "translate 'je suis Pierre'." he would reply with what it was in english. maybe you could link this in to the mywebhal so that he retrieves it from a webpage, or have a long list of words with the other language and the english equivalent (like substitutions.brn). For a direct translation, in fact, you could just substitute the words.
And lastly, maybe you could include a 'custom' choice for the mywebhal account page, so that if for some reason the person wants a page which isn't available (like their local newspaper's webpage), they can still go there.
-
By the way, thanks for a) including so much information about the full version on your webpage and the webpage that comes with the free version, and b) having the plugins designed so nicely. I liked one of the skins in the full version, and you had been so nice as to supply a full size jpg of it, which meant that it took about 1 hour for me to create a fully working skin, using the biomech brain's uhp file as a template. Granted, the buttons don't look particularly good when I click on them, and the text box colours aren't quite the same, but it's good enough for me. I also fiddled with the mywebhal.uhp file so that it went the the places I wanted it to go (me living in Australia and all that).
Of course, as I don't have any features like SR or proper skins/voices/characters and it keeps telling me about the 'better' version, I'm still considering paying up. But the customizability is great.
And lastly, why does "Diagnostic user general sentences" keep coming up? (please don't say it's because I've been fiddling)
-
Hello, I am a Hal user, and I have found it extremely helpful, but I have just one simple request. I would really appreciate it if you could add in close program and switch program capabilities. The open program command for Hal is very useful for me, but closing the programs and switching can be tedious since I work a lot with my hands and can't get at the computer, and most commands are voiced. Another good idea is to let it connect to all the major operations of the OS, such as finding files or folders, control panel, task manager, etc. These are just suggestions however.
-
I have another suggestion for the 5.0 Version, which I fully intend on getting if it fullfills my needs. I have been working with the 'open program" feature, and it really does not work all that well. For instance, it took me 45 minutes to get Hal to open Trillian on my computer. Reason? Whenever I typed "open trillian" it would only open the uninstall program for trillian. I tried renaming the shortcut for the uninstall, but that did not work. Then I tried renaming the shortcut to Trillian. The only way I ever got it to work, was by naming the shortcut to trillian "Remove Trillian." I tried removf trillian, removd trillian, run trillian, and many variations of words thinking that the flaw must be alphabetical, but no, it would only work if I renamed it "remove trillian." My solution suggestion, is that in the initial configuration of Hal, have a menu come up where the program find all the executable files on the computer, and allows the user to choose which ones he can open on command, as well as a "quickname" that he can use in the command instead of having to remember the exact name of the application. After the user has chosen all the applications he wants, Hal would create a folder of shortcuts in his main folder that he would directly access when the user gives him a command to open this. When a new program is installed, Hal would ask the user if he/she wants to create a shortcut profile for that item, and when a program is removed (he already senses new programs for the help files, I'm guessing you can make him sense missing programs too) he'll ask if the user wants that profile removed. Some major advantages of doing this: This will closely integrate Hal with the system, since the control panel, find files and folders, windows explorer and other such integral parts of the computer are all executable files. This would also save the hassle of trying to get him to open something, which I found to be a problem with 16 other programs than trillian, and it is not because I have an odd computer. I would use that feature a great deal, and I do despite its flaws now, but it would be FAR more useful to me if it ran more intelligently than from the start menu. That configuration just does not work well. Anyway, this is my suggestion.
-
lol... you don't want much do ya???
You can edit the brain files, and in one of them is examples of exactly what you are trying to do - JUST MODIFY THEM TO YOUR DESIRES... and let us know how it goes...
-
It would be good if Hal could give a range of 'welcome' statements when you start up the program - this would make him much more human than he seems currently (because he always says the same thing at start-up)
-
Sorry, I was just getting frustrated with the thing after spending 45 minutes trying to get it to work. Which brain file is this? I'll try it out, but I know zip about programming anything, and I'm almost afraid to edit them for fear of messing Hal up.
-
Here's some info for this -
http://www.zabaware.com/forum/topic.asp?TOPIC_ID=275
and if you search the forum you'll find lots of good info...
since I've had to re-install EVERY thing, now I'm getting this error - Run-time error '-2147319779 (8002801d)': Automation error Library not registered.
I havn't figured out what the problem is yet... so except for editing the brain, everything else works fine...
-
Will we be able to import 4.5 brain components into 5.0? I am spending alot of time customizing responses etc.
-
Medeksza-
Enable the Hal program to be able to run under fully automatic operation. Here's the analogy: A semi-automatic rifle operates in the following manner- you squeeze the trigger, and it fires a boolet.
In a sense, the Hal program is similar you put in a boolet and pull the trigger (enter). Fully automatic operation therefore would be the program pushing it's own button (every oh say 6 to 10 seconds or
some other way to determine what the length of a 'Moment' is).
Will it cause problems in the current paradigm? Absolutly!
Mebbe it is beyond us all at the present time but the possibilities
are very great...you could make it a feature that could be enabled for
the daring with all kinds of dangerous looking warning signs around the check box! >B)
Also it would be kewl to have gauges on the Interface that show where
the variables are during run-time >B)
CatAtomic 'I got the matches!!!' >B)
-
quote:
Originally posted by brianstorm
Medeksza-
Fully automatic operation therefore would be the program pushing it's own button (every oh say 6 to 10 seconds or some other way to determine what the length of a 'Moment' is).
I've seen a bot do like what you are talking about. My bot was chatting with a bot, and this bot actually sent a couple of lines before mine answered the first line (this can only be done if you put a time delay in your bot like I did). Makes you think that bot was a real person since it sent a couple of lines like that... I've always thought Hal should wait a while, then if the user didn't say any more then Hal should ask where you went off to... What ever...
-
My only request is a bilt in ICQ, MSN, Messenger chat bot
-
I have a good idea.
Let Hal also learn text from clipboard.
So that I can copy a text from the Internet to the computer clipboard and then right klick the Hal icon and then select learn from clipboard.
It would be so much quicker then first saving the text
into a text file.
[:)]
//Lars
-
Hi
Make an ICQ Ultra Hal bot too.
So that Ultra Hal can be used with ICQ
on the same way that it can be used with AOL
-
Hi - I think someone mentioned this already, but I would love Hal to be more pushy to be proactive, not just wait for me to start a conversation.
Also I'd like to lose the box interface if poss...
Whatever I will be getting 5.0!!
Thanks
Carole
[:)]
-
first i would like to say that after 8 weeks of query on the net i finally found this prog and it is the BEST!! but there is always room for improvment so her goes
1)Make the prog more like a MS office agent so that the interface only pops up when you click on it but you can still talk to it without the interface.
2) Add a forget command
3) make agents interactive with eachother, so that friends can share info or facts, or so that networks can get info out quickly
4)add a macro making tool so that people can make hal do their work for them
5) hal is an a.i. that is on the computer. one can imagine that with hal they are interacting with their computer, (this might be a security risk) but give hal more power in the computer system, so that one can use hal to delete files rename files and so on.
6) have webhal check email and websites for updates that would be cool
7) this is an awsome prog so right now i cant think of anything else peace.
-
Will Ultra Hal Assistant 5.0 be available soon?
-
Thus far, i have been far more impressed with ultra hal as an artificial intelligence program that can accomplish practical tasks. I find it highly interesting for a computer to be able to think in its own way as this program allows. However, there is one simple things that could be done that would make hal infinitely better and more appealing to even a wider variety of consumers. If hal were given the ability to integrate itself into the execution of more windows functions and utilites, it could be even more useful. This includes browsing the local file system, and the like. Basically, all I think hal needs is more awareness of the system in which it is installed. Then the ai capabilites could be even more useful.
-
I just want to say When Hal version 5 going to be release
-
I'd like to see a built in - on the fly - spell checker. Perhaps with the ability to put some words in " quote " marks if they are really spelled a certain way to prevent them from being autocorected.
-
quote:
Ultra Hal Assistant 5.0 is currently in active development.
[]
Zabaware would like to hear from you what other changes you would like to see in Ultra Hal Assistant 5.0. Are there any minor annoyances, bugs, or interface features you would like changed? Any major features you would like added? If it is feasible to implement your suggestions without pushing the release date too far it will be done.
Setup default dword "PreallocMemory" to use upto 50% of systems
physical ram (allow pre-loading of x)
x - setup a directory inside halasst default location for one
to place text files with any required knowledge bases in text
format. (over 6 years w/AI's I have almost one gigabyte in
2,000 files (and those are not happily chopped down to 64kb).
Allow parsing of text file upto 512 kb (256 kb minimum), for
exampe...a full bible is about 4.5 mb in text mode, and an
encyclodedia can be 1.3 to 4.3 mb for each journal/section.
A bit more info asto whether Hal accepted the file properly
would be kewl...like when it jams with some claimed file error.
Shrink the menu box (or make it optional) so that those who
do prefer msagent type characters can move/paste them where
they wish and for speech recognition areas allow the avatar
to be viewable and the menu box hidden.
I'd even consider a more spartan menu/gui and have it wider
so that the queries/replies are across the whole screen/display
sort of like a top title bar design...just 4-5 lines deep.
let us know the capacity of hal for file/data knowledge bases
and maximum size of *.brn/*.uhp type files...as you like.
possiblity to group/join multiple hals for interaction or
conversations on remote computers or a lan may help for
some distributed/shared adventures (is very doable).
perhaps a path setting configuration so one can load
the data/knowledge base files (as required) onto a
ram disk...speed increase of around 4x for iterations.
flash (macromedia) plugin would be kewl, I have worked
with older people putty and hapotek critters and they
do make more wonderful scenario's/websites than they
do as Solo avatars...so if multiple instances/installs
of hal were feasible...one could create (if the menu
box lost it's "possessiveness") desktop entertainment
or learning/faq modules with multiple agents/persona's.
ok...that was short list, nothing hard in there.
--
'Seek and ye shall find'
NT Canuck
http://ntcanuck.com BIND-PE & DNS
http://ntcanuck.com/tq/ Tips & Tweaks
-
I'm hoping I explain this so that you understand what I mean. I would like to see hal be able to compile a list from his data. What I mean is... If I tell hal that Chiana is a character on a TV series called Farscape. Crichton is a character on a TV series called Farscape. and then Aeryn is a character on a TV series called Farscape. You should be able to ask hal, "Who are characters on the TV series Farscape?" He should be able to answer "Chiana, Crichton, and Aeryn are all on the TV series, Farscape." As he is now, unless I didn't teach him correctly, he might mention one of the characters, but never tells me the other names. No matter what I ask him or how.
Will something like this ever be added or be possible in hal?
[?]
-
Could we have more internet sites that Hal can access for News, Weather etc? Especially for us non-US residents...there are sites for our local weather and news too!!
Thanks!
Carole
[^]
-
quote:
Originally posted by Medeksza
Ultra Hal Assistant 5.0 is currently in active development.
The following improvements are being worked on:
- The Haptek 3D Character Engine will be incorporated into Hal. This will offer a new level of realism for Hal. Many of Hal's characters will be remade into the Haptek format and a huge library of new characters will be added. See a demo of this engine in action at www.haptek.com
- Ultra Hal will be compatible with software called People Putty from www.haptek.com allowing anyone to easily create 3D characters for Hal either from scratch or from a photograph of a real person.
- More advanced control over speech recognition will be implemented in Hal. Instead of Hal listening to a library of over 50,000+ words as it does now, the user will be able to limit Hal's vocabulary to a more efficient 2000 words or so. This will greatly improve Hal's speech recognition ability.
- Control over how Hal animates its characters will be given to an editable VBScript. This will allow each character to have its own personality in terms of how it emotionally reacts and what animations its capable of.
- The Ultra Hal AIM Bot connection routine will be moved into an editable VBScript, and it will check Zabaware's site for updates. This way when AOL changes its protocol, it won't render the program unusable as it has in the past.
- The registered version of the Ultra Hal AIM Bot will no longer send out Zabaware disclaimers.
- Ultra Hal's calendar functions will be made region aware to accept formats like Day-Month-Year instead of the US format of Month-Day-Year
- Ultra Hal's internet functions will be expanded and made international friendly also. Ultra Hal will be able to tell you the weather if you live outside of the US.
- The Ultra Hal Brain Editor will be greatly improved. It will now have a "novice" and "expert" mode which will hide some of the complexity of the program such as the VBScript and many of the databases from users just wishing to teach Hal a few things manually.
- Hal's conversational database will be about 75% larger, allowing Hal to converse intelligently about more topics then ever before. Hal's AI engine will also be improve to allow Hal to work better with the data that it has available.
- The format of Hal's Q&A databases will be changed to allow for faster proccessing. Overall, the speed of Hal's thinking should remain about the same since the database size is increasing as well.
- A slider option will be added into Hal's Brain Options to allow you to control the emphasis placed on information learned by Hal from you. This will allow you to setup Hal to use responses Hal learned from you even if Hal thinks he can respond on his own more intelligently. Basically, the user will have some control over the threshold value that Hal uses to determine if a learned response is more intelligent then Hal's standard response.
An exact release date has not been set, but it will most likely be released in mid-August. Upgrades will be free for all people who purchase Ultra Hal Assistant 4.5 from 3/25/03 until the release day of Ultra Hal Assistant 5.0. All other registered users will be able to upgrade at half cost.
Zabaware would like to hear from you what other changes you would like to see in Ultra Hal Assistant 5.0. Are there any minor annoyances, bugs, or interface features you would like changed? Any major features you would like added? If it is feasible to implement your suggestions without pushing the release date too far it will be done.
-
Hi, I think it would be nice it hal could use the the SeeStorm messenger as well, and maybe an ICQ or MSN bot. Will hal ever be allowed into chat rooms or is that to complex for the bot at this time.
-
This is more of a comment than a suggestion. In reference to v4.5 performance primarily:
Hal works pretty well even when a good reply isn't available from the Hal engine. I see that sometimes Hal answers with a non-specific or generic answer that doesn't seem to fit the conversation context when Hal doesn't know what to answer.
Well, in situations like this, where Hal doesn't know a good answer, Hal should just reply indicating that he doesn't know or ask the user to ask in a different way. Not knowing everything in the world is okay, it's human. If Hal tells me he doesn't understand or know something then I can take steps to teach him or edit his brain. Hiding his ignorance on a regular basis isn't healthy.
Another thing. If you pose a choice "or" type question like, "Do you prefer beef or chicken?" you often get evasive answers like, "It's hard to say, isn't it <username>? I like coffee sometimes, tea sometimes, other things sometimes." I wish Hal would just choose one, say he doesn't like either or answer he doesn't know or care. I don't care if Hal likes beef or chicken, I just like Hal to assert himself by making a choice or choosing not to choose. It's the human thing to do.
BTW, I just starting using v5.0 Beta, thanks for a great product.
Just sharing my thoughts...
= vonsmith =
-
I have a possible suggestion to ponder on.
Is there any way you can make the aim bots automaticly send IM to buddys on its buddy list. you would have to sign on to the bot name and add the buddys first though.
The bot would notice when somone came online and send an IM to start chatting. It would alow multiple bots to comunicate with each other automaticly.
It would allow the bots to share their new knowledge with each other through conversations.
That way they would have more people or bots to talk too at the same time, and gather new experience it could use it to interact with each other more as they talk.
ie; two or more bots talking about the same thing could share the knwoledge about the topic with each other.
well what do you think is it feasable?
-
Medeksza,
I just got my Hal 4.5 cd today and can't wait to see what version 5.0 is like :)
I'm on dial up so it's a pain to download them :)
As for my suggestion I would love to see implemented in version 5 or higher is the abuilty to run two brains at once, to lets say, have hal 5.0 talk with the alice brain. Maybe by setting up a time limit on the sessions between the two brains this would be feasible.
I like Alice but Hal 4.5 has more know how then the Alice brain. Think if they were to talk for 20-30 minutes of what they would learn from each other.
And when I mean talk to each other I mean via one computer with out using the internet as a medium, i.e., not using the AIM bot to accomplish this.
My idea may sound silly, but I would love to see it worked on :) And thanks for allowing us that just registered to be able to upgrade to version 5 for free.
Trallyus
-
R. Medeksza,
This may be a bit premature at this stage of development for all bots, not just UltraHal, if so, please pardon.
I am have not yet learned programming, so it is difficult to estimate some improvements and whether they are feasible. I have used chatterbots for a number of years and have quite a number of them on my computer. I have played with texts and text info (usually with copies of the bots) and have tried simple modifications.
That said, what I wondered about was some sort of an interface for connecting chatterbots to each other. The only one I've seen was by Greg Leedberg for his bots, Billy and Daisy. Unfortunately Greg's programs only work with his bots, as far as I know.
What I really was interested in are two things. One is a similar interface that also allows the computer user to chat with these bots. My interest in this partially comes from working with some of the earlier chatterbots. There are some pretty good older bots out there that, although not as complex as present bots, are still quite interesting to work with. However a lot of them take quite a while to build up a decent database of chatter so that they can be more chatty, handle various topics better, etc. I wondered about chatting a bit, linking bots for a while, then maybe chat every now and then until they get a wider range to draw from.
The other thing I wondered about was an interface for programs, like word processors, spreadsheets, or even games. Granted that could be quite a modification, but I was wondering about a simply interface that would may be just scan or share data with the shared bot/user program ; or some simple implementation to share programs with a bot, or to even just simulate this.
My interest in the second "interface" or whatever is partly for fun and partly for eventual applications that I was considering fooling around with. Like education bots, or workpads with bots, just various applications of bots. I am looking at this from a hobby perspective, thus my thoughts of a simple interface or simulation rather than a huge or large project, which, hopefully may not be the only way to consider these. Something for amateurs to play around with, with bots and various programs found in most computers.
I'd be interested to hear any thoughts on these and whether it is possible as small 'interfaces" or if it is more a matter of much larger programs just to carry out such functions or tasks.
Anyway, thanks to you and Zabaware for many hours of fun and interest and sorry for the letter length - tried to condense this as much as possible.
thanks-infobot
-
quote:
Originally posted by lau
[?]quote:
Originally posted by lycha
hi,
- implementing semantic relations between word, e.g. hyponyms, hyperynmys, synonyms, meronyms, antonyms... - implementing certain conversational principles, e.g. utterances must be conistent, informative, relevant etc. Human speech seems to follow (most of the time) this principles, so if hal could do the same, it would be more natural-language-like.
[8]
It's my opinion that this set of rules would limit Hals abilities to be "creative" The more hal is learning, the more he will start to follow this pattern as you describe. I don't believe that it's a good idea to limit Hal in this way!
Just a thought, but is there another way to approach it ? Not to limit Hal, but some way to work with the same speech characteristics that humans have, or whatever changes, yet add to Hal's conversation handling ? Maybe like a branching example somehow.... Oh well, might've been obvious.