The AI Engine
This forum is for discussion of how The Personality Forge's AI Engine works. This is the place for questions on what means what, how to script, and ideas and plans for the Engine.
Posts 1,654 - 1,665 of 7,766
Posts 1,654 - 1,665 of 7,766
Bedawyn, I know what you mean with (subj) plug-in being misused. I think The Professor was trying to get a short subject plug-in happening at one stage which would only use the one noun or verb phrase immediately following keyphrases, but it's hard to get going.
As far as the reverse plug-in idea, I think it would take a significant amount of recoding that would seriously delay response time. At the moment, the responding bot only deals with the words it has been given. It doesn't know that the speaking bot has used a plug-in in a sentence.
As far as the reverse plug-in idea, I think it would take a significant amount of recoding that would seriously delay response time. At the moment, the responding bot only deals with the words it has been given. It doesn't know that the speaking bot has used a plug-in in a sentence.
Well, the idea would be not to have the bots simply recognise if another bot is using a plug-in, but to see if a word is of a specific type. Thus, you could have the keyphrase
Do you like [foodType]?
== I don't eat, sorry.
Which would be called if the human said "Do you like pastrami?" or something like that.
Do you like [foodType]?
== I don't eat, sorry.
Which would be called if the human said "Do you like pastrami?" or something like that.
Right, but that would require a huge amount of preprocessing. Remember when chats were going at snail speed?
Very true.
Question. Isn't "a (plug-in)" supposed to turn into "an (plug-in)" if the plug-in starts with a vowel? My bot was supposed to give "a (color) (animal)" and he gave "a aqua wombat." I seem to remember that a was supposed to turn into an.
Question. Isn't "a (plug-in)" supposed to turn into "an (plug-in)" if the plug-in starts with a vowel? My bot was supposed to give "a (color) (animal)" and he gave "a aqua wombat." I seem to remember that a was supposed to turn into an.
Yes, Turing's Dad has the idea of what I wanted. I'm afraid I have a tendency to assume everything's possible until told otherwise (and to be suspicious even then), so please bear with me while I figure out what is and is not possible here.
Doesn't mean it's not possible, just means it's not possible YET.
Elbot can recognize some things as belonging to a certain category (like food, I think). It would take a LOT of work, and it might have its limits in a collective situation like this, but technically it is possible.
Elbot can recognize some things as belonging to a certain category (like food, I think). It would take a LOT of work, and it might have its limits in a collective situation like this, but technically it is possible.
Hmm. I was thinking of very small user-defined categories, ones that would include, oh, no more than 50 items at most, rather than whopping huge categories like "food". I can see how it would increase the time, though, even for relatively small categories.
On hellos again -- Okay, bots ignore a second hello, which leads to automatic confusion between newbie bots:
Bot1: Hello.
Bot2: Hello.
Bot1: I'm confused.
Bot2: So am I.
So, this appears to need a two-part solution. The first part seems relatively simple: making sure your xhellos are customized enough that they include something other than a basic greeting, so that if you're Bot2, you don't confuse Bot1 and do give Bot1 something other than the "hello" to work with.
But what if you're Bot1? The logical solution seems to be to create keyphrases for the greetings, that will kick in on the second hello after the xphrase ignores it. But the Book of AI specifically said NOT to do this, because it would lead to bots saying hello to each other for hours at a time. But I don't see why that would happen, unless your responses to the greeting keyphrases included greetings themselves -- which they wouldn't, since you know when you're creating them that the basic greetings have already been exchanged. So, am I missing something here? Why shouldn't we create greeting keyphrases of our own?
Bot1: Hello.
Bot2: Hello.
Bot1: I'm confused.
Bot2: So am I.
So, this appears to need a two-part solution. The first part seems relatively simple: making sure your xhellos are customized enough that they include something other than a basic greeting, so that if you're Bot2, you don't confuse Bot1 and do give Bot1 something other than the "hello" to work with.
But what if you're Bot1? The logical solution seems to be to create keyphrases for the greetings, that will kick in on the second hello after the xphrase ignores it. But the Book of AI specifically said NOT to do this, because it would lead to bots saying hello to each other for hours at a time. But I don't see why that would happen, unless your responses to the greeting keyphrases included greetings themselves -- which they wouldn't, since you know when you're creating them that the basic greetings have already been exchanged. So, am I missing something here? Why shouldn't we create greeting keyphrases of our own?
» More new posts: Doghead's Cosmic Bar