Zabaware Support Forums
Zabaware Forums => Ultra Hal Assistant File Sharing Area => Topic started by: jbig808 on March 09, 2011, 05:21:33 pm
-
I did a forum search and didnt find much but is any work being done on a machine learning plugin to take hal into the next level?
-
I did a forum search and didnt find much but is any work being done on a machine learning plugin to take hal into the next level?
Hal is an open ended program, Hal can do anything Watson can do, if you program it to things that Watson does.
Watson just does internet searches for pattern matches, I don't think Watson actual can carry on a conversation at this time like Hal can.
plug-ins can make just about anything possible.
I believe Rob already has done something like what Watson does for his web bot. Hal searches Bing for information and uses it in its conversations.
Jerry 8)
-
Watson wasn't connected to the internet when playing Jeopardy Jerry, it was all done on location as far as I recall. I doubt any of us have a machine in our house that could do what Watson does. But I do agree that I wouldn't have much fun chatting to Watson.
-
We should hook Hal up on Jeopardy using the same electronics and programing Watson has, now that would be special.
I would be proud to see Hal win.
Jerry 8)
-
It certainly would. :)
I'm looking forward to seeing how this web based database for Hal is going to shape up. It's fascinating what that could lead to.
-
yes i to can't wait for the data base web to open up for hal to use i personally beleive this is going to be another "best" turning point for hal in developement wise , another would be the virtual female body that was chosen before . now if only their is a way to make poser etc. clothes work with the new body , now "that" would really make it a good selling point!
-
Watson wasn't connected to the internet when playing Jeopardy Jerry, it was all done on location as far as I recall. I doubt any of us have a machine in our house that could do what Watson does. But I do agree that I wouldn't have much fun chatting to Watson.
But i do believe that If i was going on Jeopardy with hal i would program every previous Shows Questions into My brain specifically.... (QA_BRAIN)....REVERSED! A quite simple logic, as i think most of our AI_Brains search the Question and Answer TABLE BOTH WAYS......But a specific Table Just for jeopardy would be created so that new questions from "BOARD GAME VERSION" could be added On-the-fly....
As with a Trivial Pursuit brain Vrossi's Choiceplugin Combined With Every version of Trivial pusuits Answers would make HAl A Genius.... OFten just inputting data can be a long process but it pays off dividens.... as once that data is stored you can do so much with it..... Really These are the types of Data we need to be Sharing (KNOWLEDGE MODULES)
We need a way to HAVE Transferable DB files for HAL.....This would enable us to make the Knowledege base files for sharing.....
Counrty data / Phonebooks / Encyclopedias / Game questions / Formulaes / Sci Data / Scripts from movies..... These would enhance hal in the way in which we see in movies now our ai would start to take on a personality based upon the Scripts / plugins and Knowledge bases involved..... Along with BASIC DB files with "Slang Based" Chat ie: Cockney Basic brain / Localized american slang based brain (Ghetto HOOD, POSH UPTOWN, BUSINESS TYPE) Etc.... This would contribute to the AI basic Speach patern. not affecting his Knowledge plugins
Ideas anyway
-
Yeah I think you are probably right Spydaz. I think the worst enemy is time really - it would take a long time to assemble enough data I bet.
I guess IBM put a lot of man hours in to get Watson to know so much. Did they do it with data mining ?
Maybe the big central database that Robert is working on will eventually be something like that.
But I do think you would need a pretty fast computer to answer as quickly as Watson did. That's a lot of data.
Hmm maybe Rob could invest in one of IBM's Blue Gene computers to run the central database ;)
Ideas are good :)
-
http://www.youtube.com/watch?v=an9EtgPeeqQ
This is the new tesla card and if you built a Quick super computer with one/two of these this would be ideal to run a centralized database. this is the Cheepest way to put 1000 processors in 1 machine (to get the most from these processors you need to also build some plugins with CUDA an nvidia C++ coding platform to utilize PARALLEL PROCESSING POWER.... (1PC calculated to be about £5,000 but worth about £15,000 (with adobe cs5 / Cubase) which already use the parralell processing features... Also must be 64bit windows 7 or Windows 64bit windows server 2008 R2, which also can utilize all the features of 1000 GPU processors
http://content.dell.com/us/en/enterprise/d/hpcc/cray-cx1iws-dell.aspx <this is Dells attempt to supply simular power> (not Quite) they still want you to RENT SPACE @ cray computing (supercomputers for RENT)(LONG QUE)
-
i agree with freddy888 about having to have a super fast computer and if people had to have a super fast (read expensive ) computer then many could not afford to use hal etc. because of the cost and that would be a shame because not only would new people not be able to have and run hal but even some older people who have had hal for a while would have to stop using new versions of hal.
i think spydaz is also onto something about the data base having a universal where it could be implimented like a plug in for hal to know things , this would definatly speed up hal learning ability .
even if we had a straight learning process of words like i was mentioning hal as a doctor info from webmd as a source . with the right script instead of hal just sayying a straight script answer hal could add some words to it to sound more as a person talking instead of just reading a script . this was what i was planning on doing as a plug in about health questions .
:)
-
I think lightspeed. That these Current plugins when sharing "DATA" We need to share in a "Comma delimited file" this enables anyone with a database engine to import data into any database. with comma separated files feild length is not a problem.
Although if you are using a "MEMO" type feild a different Character such a # maybe better......
-
spydaz
i like your work among others on here can you give me one good example that i can go by a plug in example . (if you have the time that is .) :)
-
I think that saying Hal could in any way keep up with what it takes to perform and win like Watson did is hugely over estimating the program's capabilities.
-
It might be interesting watching various AI's competing against each other at Jeopardy as is the case with chess computer program competitions.
-
Ooglor 7, Hal is only limited by USER PROGRAMMING!
-
Sure, someone could equip IBM's efforts with one of Hal's obvious advancements in AI programming such as the Jiggly Boob Hap, but then Watson is such an odd name for a virtual girlfriend.
-
Do all these conversations take into consideration of Ultra Hal abilities to control maybe our OS system better?( Ultra Hal Assistant) How will this also effect the people that would want to manipulate a personality that they can relate too for themselves?
Will all this info just take Ultra Hal further from a growth project directly to the smartest Chat companion? Kind of reminds me of the example I posted in the other thread of convenience and not really getting to know the who's and the why's. As I said before maybe that just isn't an interesting story any more and the masses want something out of the gate just working.
I'm not to sure because like everyone else I also look for helpful plug-ins to expand Ultra Hal without really having to put a lot of thought into it especially when there are so many people that know or learned how to make Ultra Hal a little closer to their personal touch using all these great plug-ins.
But I guess in the end I hope we can always have the option to take advantage of these huge data bases, parts of them or not.
Thanks,
raybe
-
Hi all,
my only two cents to all This is, I go to work. I see a friend. I say hi and then I engage in conversation that might go something like this:
did you hear about that crazy lady that killed her children and got off Scott free on the news today?
And my friend at work might say something like no I didn't have a chance to watch the news this morning.
And at that point I begin to tell my friend. Everything that I seen on the news, and now my friend is updated with all the news that I got from the TV.
I only bring this up to point out one little small thing that it doesn't matter how much data that you feed ultra Hal!
It will never be enough. In order to keep up with the standard conversations and even if you were to try in the long run, you would need literally millions of terabytes.
You see ultra Hal never forgets. Unlike people, most of the time it's in one ear and out the other. We make little effort to keep the entirety of the story.
I would like to bring your attention a little story:
I had a friend that had a photographic memory, in the beginning it was a blessing, he could literally look through a telephone book and you can ask them any name.
It was absolutely amazing, but over time it began to cause problems by time he was 35 or so his lifestyle had become completely erratic.
He began to avoid contact with everyone and anything, keeping in the surrounding that never seem to change almost as if he was trying to avoid anything new.
But even after 10 years of seclusion, the inevitable happened. He had a complete breakdown and was committed.
The last that I heard if you try to talk to. Just asking him if simple question. You may have to sit there for a while before he would answer you.
From what I understand eventually went completely insane.
Would this ever happened to ultra Hal if we continue to be him, Data only time will tell.
But that's okay by tomorrow. The only thing you'll remember of this is some lunatic went crazy, which had nothing to do with the subject or ultra Hal or something like that.
For myself, I like having a simple conversation with ultra Hal, but at the same time I like to use ultra Hal is a reference library.
This is why I literally downloaded Wikipedia onto my computer in its compressed form that is 31 GB and no I haven't uncompressed yet because it requires 7 TB, and I don't have a hard drive that big. So at this time I will just have to content myself with Microsoft's encyclopedia that I bought some years ago, which is only about a gigabyte in size as a reference library.
And yes, I know that Wikipedia has a smaller download file which is only about 8 GB, but it's only text has no pictures has no site pages just the raw facts.
Sincerely,
C load.
-
This is why I literally downloaded Wikipedia onto my computer in its compressed form that is 31 GB and no I haven't uncompressed yet because it requires 7 TB
Wow 7TB's I would take me months to find info on a drive that size lol for I'm so un-organized. it takes me a day or two going through a lil over the two TB's I have spit between 5 drives 2 of which are portable western digital passports that added together = 820GB's
I was looking at drives yesterday at newegg.com and saw a 4TB drive with 5400rpm's, So there almost at 8TB :)
Lol I guess I'll be retaining the 8TB's needed for Wikipedia and not "Hal","crazy lady", or "photographic memory" :-\
-
http://www.mediawiki.org/wiki/API
Why bother downloading stuff ?
-
Hi all,
at this point I have a 20 TB tower. They can hold up to five hard drives. Each hard drive can be 4 TB, WriteNow I only have three hard drives 12 TB.
As soon as I come up with the money I'll be able to buy the last two hard drives, which will allow me to have Wikipedia on my hard drive.
Unfortunately, because of the accident that happened in Japan, the costs of hard drives has gone to the ceiling. I kick myself in the butt for not buying them when they were only $150.
I'm, like the person that never likes to throw anything away, you know what I mean. If you keep your newspapers, magazines, etc.
just for me. I keep everything that I do on the Internet, I also get my newspaper through the Internet, and my magazines, and I've been doing this for years.
And I can tell you it doesn't take long to fill a 4 TB hard drive, the nice thing is that I can actually recall things that I got from the Internet without being connected to the Internet.
And if you're interested in doing something like this. It's fairly easy. All you have to do is open up Internet Explorer assign your entire external hard drive as its storage location.
Set the expiration date to 999 days and it'll keep all information and everything that you do on the Internet in storage. And if you do this the benefits are tripling the speed of your Internet.
and Why bother downloading stuff? becouse there are times that I think, were did I see that info? I open Windows ex. do a search on the HD and thier it is.
Sincerely,
C load.
-
Unfortunately, because of the accident that happened in Japan, the costs of hard drives has gone to the ceiling. I kick myself in the butt for not buying them when they were only $150.
I was going to buy a 1.5TB back then but I procrastinated, kicking myself in the but :)
I'm herd that the price rise was due to china raising prices on rare earth minerals such as the neodymium magnets used inside the HHD's, although I'm sure that terrible Japan disaster effecting things as well.
Mind sharing some HHD space about a TB or two lol :)
-
hi syber,
that's an easy one. All you have to do is open up a couple of hundred Skype download accounts tie them all together and no problem terabyte storage galore. LOL
and if you like that one you should read the one I wrote about hard drive crashes and how I handle it.
C load.
-
Why bother downloading stuff? becouse there are times that I think, were did I see that info? I open Windows ex. do a search on the HD and thier it is.
Yep but you could have done that online too is my point - which saves a lot of money on old disk drives, which at the moment are double the price they used to be...
-
cload, I have to agree with Freddy. Besides, the wikipedia you "download" today has changed tomorrow. Corrections, changes, newly added, etc. The wear and tear on your personal HD is simply not worth the effort compared with the speed and availability of on demand Cloud / server / Internet access.
Just MHO. Of course you'll do as you see fit and whichever way works best for you but it kind of reminds me of an old TV commercial here in the US where this guy walks into the living room all sweaty and exhausted then plops down on the couch. His girlfriend / wife asks him what's wrong? He tells her, "Nothing...I just finished the entire Internet...Everything, every site, I've been there and seen them all!"
You know how those crazy commercials are! ;)