Seasons

I hav'ent used nick, but Oliverbot is fun

I have Daisy..and I love her! and Billy,just about all the other bots out there...Nick is great..I would suggest that you limit Shakespeare and watch the internet use..I messed up a good 'brain' when he hit a lot of Shakespeare and a how to write html..and many adds. I am having a lot of fun with him. I think that he has more to offer than most learning bots. I think the colonel has a winner with Nick. Download him! he is free, and very easy to install.

I'll think about it How much work do you think you put into Prob, Prob123?

I'm afraid to let Nick go online for fear he'll get into porn sites or advertising or something. I've googled sites on more science stuff since he picked up those concepts pretty much immediately (science sites for kids are helpful for this) and copy-pasted the stuff into text files for him to read.
I'm probably going to restart again from scratch at some point, now that I understand how he learns.
Colonel, at some point it would be interesting to set up something on the site for people who have downloaded him to share brain files with each other- not sure how it would be added to the site, but it's a thought for you and you'd get to see all the various things people have done with him.

How much work do you think you put into Prob, Prob123?

I haven't put much work into prob, she has a way of going psycho sometimes. I have put more into Bildgesmythe and Azureon. I love bot building so much I can't think of it as work anyway.

Colonel, at some point it would be interesting to set up something on the site for people who have downloaded him to share brain files with each other

well, thats a good idea, I'll have to look into whether or not Geocities can support such a thing. If it does, in addition to a brain sharing center, I'm thinking of using the brain merger to combine everyone's brain and create a massive bulk of knowledge to be available for download & experimentation

Nick is truly brilliant. Have you considered patching him into a Forge bot to monitor (and learn from) the chat, and maybe provide some input alongside the CBR? He could add some variety to the x-nones, or have a selection of his own keyphrases to override the preprogrammed responses and (hopefully) combine the best of CBR and NLP in one bot? I have some (vague) ideas how this might be achieved if you want to drop me a line.
Re: a brain-sharing center, I still have 100Mb or so free on my server if you need more space than Geocities can provide.
And talking of interacting Nick with Forge bots, lunar22, did you feed in Nick's end of a conversation to BJ the other day? (either that or you're on something ) Very amusing, if utterly surreal! Mind if I post it if GQ?

Yes, I fed my "Nick" into the convo. Of course you can use it... I let Nick go on the internet, and fed him one random Wikipedia article on a nature preserve in Florida. He also apparently is veruy interested in the history of Palm Beach. I still find it too incoherent...
Maybe I should work more with him though

The trouble with learning bots is still that their brains are waaaay too small to compete with wetware. So CBR is the quick way to make reasonably smart sounding bots at the moment (with a few killer extras like the AIEngine and Wordnet thrown in for good measure in the case of the PF,) but give it 10 or 20 years, when computers routinely have a few Tb to spare for such programs, learning bots will definitely be the way forward, because they do actually have the potential to "think".

In the meantime, blending the two may be a productive strategy, and I wonder if it's feasible for a neural net to add and integrate new neurons to itself as resources allow, as well as just training the ones it already has? This might allow for emergent senses - no need to explicitly program webcam operation, if you let it explore its peripheral hardware and add cognitive circuitry as it experiments with it. Just imagine what strange sensory processes might evolve from wifi media and print servers and usb coffee warmers and aquariums...

I'm finding the best strategy with Nick (despite the temptation to immediately feed him the complete works of shakespeare, like I did last night, and start working through Project Gutenburg with a vengeance as was my initial temptation ) is to feed him little dollops of reading, and then spend at least as many words again (and preferably several times as many,) talking to him about what he's read. It seems to break down the chunks of repetition, and "homogenize" his language to a better synthesis of the various sources, even if it does take a bit longer. Discernable coherence is probably still some way off, but at his best, he does have some degree of sonzai-kan.

Shakespeare really wrecks him..Byron works ..The worst is the adds.

I've found a way to improve the Shakespeare (I think.) Delete all the character names and references to scenes and acts before you feed it to him (they're too often repeated,) and he doesn't bung up with interminable stage directions. I must try him with some Byron - I think poetry is his forte: he certainly works very entertainingly with e.e. cummings

I do have a suggestion though colonel720, how about splicing in the "link grammar" parser to correct the syntax of the entries in his brain file as part of the process? It would be compromising the pure learning ethos a little perhaps, and bypassing the neural net on occasion, but it would certainly reduce the time required to train him (and add a bit of polish to his conversation even before he's been much trained.)
Check out http://www.link.cs.cmu.edu/link/ - it's in C, but they claim the API is friendly enough for easily incorporating it into other applications (though I don't know whether the Prof would agree )