The AI Engine

I think it's great that our bots now recognize a lot of words even when misspelled. Can we have them recognize the names of major cities? For example, Los Angeles:

Guest: I live in Los Angeles.
God Louise: I've spent many a happy day walking through loss an gel. Beautiful place.

I've found the spell checker doesn't like proper names.

It's on my list for the spell checker to be smarter about Proper Names. It's funny to see what it comes up with, though.

Good eyes, Turing's Dad. Actually, that was in there, but in the wrong order. Now you're not an arena.

Beastial Boys

How hard would it be to make it so if a letter has so many keyphrases in it, to put another list below the list of letters saying page 1, page 2, etc. to break it up into smaller chunks so it loads faster? Or failing that, how long will it be until you get import/export bug-free?

btw, damn good job on the new features I'm drooling to try them out, if I was patient enough to wait for the load times to do it hehe

Export/Import is next on my list. I'll be working on it today.

I just had an idea... not sure how feasable it is though. Maybe you could have a feature where whenever a human is talking to your bot it stores what they say and then you can use a keyword command sorta like goto to have the bot just decide for itself what to say based on how other people have responded to the same or similar questions/statements.

This wouldn't always be useful but I think it could make the bots a lot more humanlike in some situations...

anyways, just an idea

That'd be basically making them into learning bots

The problem with that style (as I hear it from those botmasters) is that a lot of people who chat with bots like that teach them all sorts of unsavory things, or talk garbage, and then the bot basically becomes insane. If you have an engine like that, you have to raise it in a trustable environment or do a lot of weeding.

A did a little work a few days ago working the design for a sort of memory network. It'll be tons of (simulated) pointers. For example if somebody says "Mark got ice cream" you have the words "Mark" and "ice cream" saved. Then you relate them with the verb "got". The next time "Mark" is mentioned, the node is connected to a new verb-node, but it's simple to get other information about "Mark". This goes on long enough and you have a huge memory network of connected terms and ideas.

That's the gist of it, but it can encompass relevance, time sequence, and learned emotional meaning as well.

Sounds good prof, but with stuff like names it could get tricky. I mean what if one guy talks about Mark, his friend who lives across the street, and some other guy talks about Mark, his parole officer? Other than that, it sounds rather amazing though.

As for the goto # thingies, could you just have it look for all occurrences of 12345 in a bot, then detect whether 12345 is being used elsewhere, then if it is change it to the first available number? Sounds reasonable enough, I just dunno if it'd be feasable timewise.

Prof, just a request for exports... Could you maybe put a dash (-) before each of the responses in the seek? So you'd haev something like

    Why?
        + because [0]
        -Oh, That's a fairly good reason.
        -That response is fair enough.

Just to separate them out from the normal responses

Jabberwacky learns based on user input. It sounds incredibly human at times, but it is more schizophrenic than Gaia.