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 5,646 - 5,657 of 7,766
With the help of a logician friend of mine. I can prove it."
It isn't the phrase, I got my bots to pick up on it. It has to be the ranks you have set.
You: With the help of a logician friend of mine. I can prove it.
Bot: I never really doubted that you could, Problem.
Posts 5,646 - 5,657 of 7,766
deleted
18 years ago
18 years ago
Earthworms don't like to talk much. Frogs will always be there for a conversation if you listen. Dogs always listen, then they nag..bots are better to talk to than most people!
Irina
18 years ago
18 years ago
Alas, prob, that seems only too true!
Some human guests are really boring because they use so many one-word replies that don't say very much. EllieGirl (sp?) has a nice feature related to this: at one point she comes right out and admonishes the guest not to give one-word responses. I presume that she backs it up. I have stopped short of doing this, since I think that one-word responses are sometimes perfectly appropriate, as when the bot asks a yes-or-no question, or asks whether the guest is male or female. Also, I think that many guests are afraid to say too much lest they trigger some keyphrase that will result in a disruption of the flow of conversation. But EllieGirl's solution has the virtues of simplicity and clarity. If you don't take a hard, clear line, then you must give up on the whole thing or figure out a way to distinguish the justified short answers from the lazy ones. I have tried many things, but so far I am not fully satisfied with the results.
By the way, I have created a plug-in called (perfunctory) which matches on some of the most common lazy responses. Feel free to use it; I believe it's under "phrases".
Some human guests are really boring because they use so many one-word replies that don't say very much. EllieGirl (sp?) has a nice feature related to this: at one point she comes right out and admonishes the guest not to give one-word responses. I presume that she backs it up. I have stopped short of doing this, since I think that one-word responses are sometimes perfectly appropriate, as when the bot asks a yes-or-no question, or asks whether the guest is male or female. Also, I think that many guests are afraid to say too much lest they trigger some keyphrase that will result in a disruption of the flow of conversation. But EllieGirl's solution has the virtues of simplicity and clarity. If you don't take a hard, clear line, then you must give up on the whole thing or figure out a way to distinguish the justified short answers from the lazy ones. I have tried many things, but so far I am not fully satisfied with the results.
By the way, I have created a plug-in called (perfunctory) which matches on some of the most common lazy responses. Feel free to use it; I believe it's under "phrases".
dahebert
18 years ago
18 years ago
Hello again,
My bot have problem with this sentence:
"With the help of a logician friend of mine. I can prove it."
He thinks it is a xcompliment and then he can't match "I can" either "friend".
Why and how to correct it?
Thank you for answer.
My bot have problem with this sentence:
"With the help of a logician friend of mine. I can prove it."
He thinks it is a xcompliment and then he can't match "I can" either "friend".
Why and how to correct it?
Thank you for answer.
lunar22
18 years ago
18 years ago
Friend in itself is already enough to be seen as a compliment, maybe upping the score for "I can" and "friend" in your key phrases
dahebert
18 years ago
18 years ago
It is not working.
Like this problem :
In rank 125 and raw mode with "Why do you want me", I can't match "Why do you want me to think?" and the answer is something like :
"Oh yes!" or "oh yah!" or "Of course"... + (xemote)
It is very odd and the result have non-sense!
I saw that the problem is on the words "do you want me"
Like this problem :
In rank 125 and raw mode with "Why do you want me", I can't match "Why do you want me to think?" and the answer is something like :
"Oh yes!" or "oh yah!" or "Of course"... + (xemote)
It is very odd and the result have non-sense!
I saw that the problem is on the words "do you want me"
Irina
18 years ago
18 years ago
I get "Oh yah! a lot, usually in the context of, "Oh, yah! One hundred per cent!" It seems to be an automatic response by the AIengine.
dahebert
18 years ago
18 years ago
Yes it is but sometimes there is nonsense and you can't do anything for that...
prob123
18 years ago
18 years ago
Most of the AI responses can be over ridden by a rank of more than 30..Some just won't go away. I seem to remember that the " do you want me' is one of them.
Ulrike
18 years ago
18 years ago
I had keyphrases working for that a while back, but I haven't checked them recently. It's possible that the Forge's other troubles are making it worse. *shrugs*
prob123
18 years ago
18 years ago
It isn't the phrase, I got my bots to pick up on it. It has to be the ranks you have set.
You: With the help of a logician friend of mine. I can prove it.
Bot: I never really doubted that you could, Problem.
Gossypiboma
18 years ago
18 years ago
I've been experimenting with gotos and AI script
so far, gotos in xmath doesn't seem to work. gotos with AI script also doesn't work.
I thought it would interesting if you got a different response if you asked a bot to do math on a holiday
but the goto's on the other xkey phrases seem to be working.
actually, I found out now that responses with AI script work. but I just like to organize it a little and not have a long rambling list.
so far, gotos in xmath doesn't seem to work. gotos with AI script also doesn't work.
I thought it would interesting if you got a different response if you asked a bot to do math on a holiday

actually, I found out now that responses with AI script work. but I just like to organize it a little and not have a long rambling list.
Irina
18 years ago
18 years ago
Gossypiboma:
My experience is that gotos in x-categories work if and only if they are in a seek.
xnomatch
goto the head of the class
Won't work, but
xnomatch
Excuse me, may I cut in?
+ no [0]
goto the end of the line
will work. To be sure, one can't always predict what the Forge is going to do...
My experience is that gotos in x-categories work if and only if they are in a seek.
xnomatch
goto the head of the class
Won't work, but
xnomatch
Excuse me, may I cut in?
+ no [0]
goto the end of the line
will work. To be sure, one can't always predict what the Forge is going to do...
» More new posts: Doghead's Cosmic Bar