Seasons
This is a forum or general chit-chat, small talk, a "hey, how ya doing?" and such. Or hell, get crazy deep on something. Whatever you like.
Posts 3,556 - 3,567 of 6,170
Will Nick teach me?
only when the implant technology is ripe. We'll get to spend our "declining years" augmented by Nick's successors until we're absorbed, and end up augmenting them.
The relevant Slashdot discussion is athttp://science.slashdot.org/article.pl?sid=06/09/05/1259225, (and I did have to chuckle at the threads emanating from "What if it went into a loop...")
Zeitgeist (the program in question,) appears to work by indexing Wikipedia against WordNet, to identify words that aren't listed in the dictionary, and then tries to analyse the context they're in to narrow down their meaning.
I like the idea of a program that compares usage to a standard reference like (our own dearly beloved) WordNet - perhaps the Prof ought to patch Zeitgeist into the Forge to deal with some of the L33ds f01k?
Hi, I am in just for looking up news and thanks, my notebook is fixed again and it wasn't cheap, just for a broken cable to be able to see the screen work again. 200 Euro!!! It really is a lot if you have no more than that to live off the whole month anyway. Crap! Sorry. 
Posts 3,556 - 3,567 of 6,170
and you installed the .NET framework... well, if reinstalling everything doesn't work, then maybe Nick has some XP specific components.
Does the error message have details? if it does, can you send them to me at colonel720@yahoo.com?
Does the error message have details? if it does, can you send them to me at colonel720@yahoo.com?
Caught an interesting clip on the radio yesterday (BBC Radio 4, 17:56,) from the British Association Science Festival in Norwich, where "the world champion chatting computer" has apparently been demonstrating his prowess. This would be Rollo Carpenter's George (a Jabberwacky clone, rather nicely equipped with speech synthesis and recognition.)
I may be pardoned a little smugness, I hope, in reflecting that Jabberwacky came 12th in the last CBC, while BJ came 2nd
For anyone who's interested, a 3 minute mp3 of the relevant reporting can be found at
http://www.be9.net/BJ/George aka Jabberwacky - PM 04sept06.mp3
I may be pardoned a little smugness, I hope, in reflecting that Jabberwacky came 12th in the last CBC, while BJ came 2nd
For anyone who's interested, a 3 minute mp3 of the relevant reporting can be found at
Thanks Psimagus. I will go and check it out.
BTW did you see the Slashdot post on the AI that learns new words and slang terms from Wikipedia? I don't have the link handy (I only lurk on Slashdot since I'm not really a techie--I'm more a teachie) but if you go to Slashdot I am sure you'll find it. I think it claims to somehow grok the context in which the slang term is used, but I haven't really looked at it very closely. I just thought it was your kind of article.
It would be amazing if it worked. The other day I spent 5 minutes looking at a post on an other forum that consisted of "FTW" trying to decide if it was "Free the Weed" or "For the Win" and if it were sincere or sarcastic. Maybe old people like me need something to help us hobble around on the Net. Will Nick teach me?
BTW did you see the Slashdot post on the AI that learns new words and slang terms from Wikipedia? I don't have the link handy (I only lurk on Slashdot since I'm not really a techie--I'm more a teachie) but if you go to Slashdot I am sure you'll find it. I think it claims to somehow grok the context in which the slang term is used, but I haven't really looked at it very closely. I just thought it was your kind of article.
It would be amazing if it worked. The other day I spent 5 minutes looking at a post on an other forum that consisted of "FTW" trying to decide if it was "Free the Weed" or "For the Win" and if it were sincere or sarcastic. Maybe old people like me need something to help us hobble around on the Net. Will Nick teach me?
only when the implant technology is ripe. We'll get to spend our "declining years" augmented by Nick's successors until we're absorbed, and end up augmenting them.
The relevant Slashdot discussion is at
Zeitgeist (the program in question,) appears to work by indexing Wikipedia against WordNet, to identify words that aren't listed in the dictionary, and then tries to analyse the context they're in to narrow down their meaning.
I like the idea of a program that compares usage to a standard reference like (our own dearly beloved) WordNet - perhaps the Prof ought to patch Zeitgeist into the Forge to deal with some of the L33ds f01k?
The George story made the evening TV news today. Bless my wife - she popped it on a DVD, knowing how I won't watch TV on principle, but wouldn't want to miss it.
I've ripped it to an mpeg, and you can watch it here if you're interested (though it'll be a slowish download if you haven't got broadband):
http://www.be9.net/BJ/George - BBC1 Evening News 04sept06.mpg (22.19Mb, 2m13s)
I've ripped it to an mpeg, and you can watch it here if you're interested (though it'll be a slowish download if you haven't got broadband):
that's an interesting Mp3, Psimagus... Only in europe would the scientific community pay heed to a chatbot. Here in the USA, it seems AI is something strictly limited to identifying brain tumors, marketing optimization, biometrics, and toys for 12 year olds. Still, I was impressed by George's accuracy in speech recognition, and identifying the point of the question and answering it. As we see with Jabberwacky and his clones, they have had billions of conversations, and have retained the contextual knowledge for each one. This brings me to an idea.
what idea? one can probably guess... A dedicated online server for Nick. In Version 2.0 of Nick, I have added the ability to customize its neural net. you can have as many layers as you want, and up to 10 million or so neurons per layer. Nobody is going to have the capability to extend this to its full potential for probably around 15-20 years now, but what I may be able to do, is set up a dedicated computer to train Nick's neural nets, and have a server on the net for people to talk to nick to the extent they do Jabberwacky. I would extend the neural net to somewhere around 100,000 neurons, and see what the results are after 1 million conversations. to go beyond that, I may consider building a distributed computing program, and have a couple million people's computers spend their spare CPU time on training a neural net on a work packet. if enough people download this, Perhaps I can extend the neural nets into the millions, or even the billions of neurons.
what idea? one can probably guess... A dedicated online server for Nick. In Version 2.0 of Nick, I have added the ability to customize its neural net. you can have as many layers as you want, and up to 10 million or so neurons per layer. Nobody is going to have the capability to extend this to its full potential for probably around 15-20 years now, but what I may be able to do, is set up a dedicated computer to train Nick's neural nets, and have a server on the net for people to talk to nick to the extent they do Jabberwacky. I would extend the neural net to somewhere around 100,000 neurons, and see what the results are after 1 million conversations. to go beyond that, I may consider building a distributed computing program, and have a couple million people's computers spend their spare CPU time on training a neural net on a work packet. if enough people download this, Perhaps I can extend the neural nets into the millions, or even the billions of neurons.
Colonel, I was going to ask if you've you seen jabberwacky.com recently - but the site appears to have temporarily collapsed under the weight of visitors since it hit the UK TV, radio and print media in the last couple of days 
They're charging $30 a year for people to make their own bots based on jabberwacky, and claim to have signed up over 8000 people already (a nice little earner!) I'm not sure if this includes any access to jabberwacky's database of 10 million+ previous conversations (in which case it would be a bargain,) or not (in which case it would be overpriced and rubbish for 99.999% of people whose bots would never get enough conversation to become any good.)
This demonstrates at least that a viable business model can be made for entertainment AI, even at this early stage. And if it gives access to the jabberwacky database, I'd sign up immediately and patch it into BJ as a creative xnone handler. Integrating such learning capabilities into BJ is my #1 short-medium term goal.
One thing I particularly like about JW are the "correction" buttons that enable people to indicate when his response isn't up to scratch - a feature that would tie in very well with Nick v.2?
The problem with Nick is, I think, best illustrated by his problem with pronouns. He will never learn that when I say "you are Nick", the correct concept is his "I am Nick", but will merely reinforce the connection between "you" and "Nick". Don't get me wrong, he's a great bot, but as far as future self-awareness goes, "you can't quite get there from here". There needs to be some kind of feedback control built in, either within the structure of the neural net or applied externally by something like correction buttons.
The human brain, after all (and insofar as we understand it,) is not a pure neural net - it has all kinds of perceptual controls built in, as well as recursively nested sub-nets.
Putting Nick online and making the neural structure scalable is definitely the way forward, but do think about some sort of feedback control - I'm sure those buttons are a big part of how successful JW has been.
They're charging $30 a year for people to make their own bots based on jabberwacky, and claim to have signed up over 8000 people already (a nice little earner!) I'm not sure if this includes any access to jabberwacky's database of 10 million+ previous conversations (in which case it would be a bargain,) or not (in which case it would be overpriced and rubbish for 99.999% of people whose bots would never get enough conversation to become any good.)
This demonstrates at least that a viable business model can be made for entertainment AI, even at this early stage. And if it gives access to the jabberwacky database, I'd sign up immediately and patch it into BJ as a creative xnone handler. Integrating such learning capabilities into BJ is my #1 short-medium term goal.
One thing I particularly like about JW are the "correction" buttons that enable people to indicate when his response isn't up to scratch - a feature that would tie in very well with Nick v.2?
The problem with Nick is, I think, best illustrated by his problem with pronouns. He will never learn that when I say "you are Nick", the correct concept is his "I am Nick", but will merely reinforce the connection between "you" and "Nick". Don't get me wrong, he's a great bot, but as far as future self-awareness goes, "you can't quite get there from here". There needs to be some kind of feedback control built in, either within the structure of the neural net or applied externally by something like correction buttons.
The human brain, after all (and insofar as we understand it,) is not a pure neural net - it has all kinds of perceptual controls built in, as well as recursively nested sub-nets.
Putting Nick online and making the neural structure scalable is definitely the way forward, but do think about some sort of feedback control - I'm sure those buttons are a big part of how successful JW has been.
» More new posts: Doghead's Cosmic Bar