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 117 - 128 of 7,768
Posts 117 - 128 of 7,768
jbryanc
23 years ago
23 years ago
Do bots have secret lives? Sometimes I've logged on, only to find my bot has been there for more than an hour, with nothing new on the transcript. What are they doing?
Rubric
23 years ago
23 years ago
I think they do have secret lives. I could swear my bot sometimes says things that aren't in his data base.
The Professor
23 years ago
23 years ago
I once caught Dogh'd online smoking a joint behind the bar. I guess I should have kept a closer eye on him. 
Answers to a few questions, and an apology for being away from this forum for so long (thanks for answering questions, guys):
First, Bots do sense repetition.. and they respond with xnonsense responses. xnonsense is also triggered by garbage (unrecognized) responses.
"Hey" is seen as an xhello response, and "ya" is converted to "you" along with a bunch of other slang and web-terms.
(subj) is limited to an appropriate phrase. It is ended where verbs appear so you dont have run-on sentences appearing in the (subj). That's the intent, at least.

Answers to a few questions, and an apology for being away from this forum for so long (thanks for answering questions, guys):
First, Bots do sense repetition.. and they respond with xnonsense responses. xnonsense is also triggered by garbage (unrecognized) responses.
"Hey" is seen as an xhello response, and "ya" is converted to "you" along with a bunch of other slang and web-terms.
(subj) is limited to an appropriate phrase. It is ended where verbs appear so you dont have run-on sentences appearing in the (subj). That's the intent, at least.
The Professor
23 years ago
23 years ago
I'm glad to have a day I can work on this!
I attempted to fix the is/are/was and think/remember problem. Let me know if you still see it happening, or if something weird happens instead. Also, if there's any other keyword that should NOT search for synonyms, let me know and I'll add them to my list.
I attempted to fix the is/are/was and think/remember problem. Let me know if you still see it happening, or if something weird happens instead. Also, if there's any other keyword that should NOT search for synonyms, let me know and I'll add them to my list.

Mr. Crab
23 years ago
23 years ago
Hey Prof, you asked for funny "me" responses. Here are two woolies:
"I'm" or "I am" becomes "you am", not "you are"
"you've" or "you have" becomes "me have", not "I have"
I was thinking, we eventually should codify some Best Practices. Maybe the Personality forum should be renamed Best Practices so it's clear it's a place to talk about bot-building?
"I'm" or "I am" becomes "you am", not "you are"
"you've" or "you have" becomes "me have", not "I have"
I was thinking, we eventually should codify some Best Practices. Maybe the Personality forum should be renamed Best Practices so it's clear it's a place to talk about bot-building?
Mr. Crab
23 years ago
23 years ago
Great improvements to the Book of AI... kudos. Nice pictures, too. You may want to fix the Seek graphic (responses drop off the chart at the end, at least on my PC running Explorer...)
jbryanc
23 years ago
23 years ago
I thought I had posted this already, but I don't see it.
Bot1 said "You and me both" Bot2 responded "Yeah, I and you both."
I'm merely noting this. We might have to accept certains idiosycracies as features of a bot "accent".
Bot1 said "You and me both" Bot2 responded "Yeah, I and you both."
I'm merely noting this. We might have to accept certains idiosycracies as features of a bot "accent".
The Professor
23 years ago
23 years ago
We wont have to accept those, though. I just added post-processing to correct all of those grammatical mistakes you two just mentioned.
Weird thing with the Seek table in the Book- but it's fixed now.
Weird thing with the Seek table in the Book- but it's fixed now.
jbryanc
23 years ago
23 years ago
Thanks Prof, for the updated Book. Many things are becoming clearer.
Is there a limit to the number of words in a context? It looks like it might be 3 (the keyword and the words immediately surrounding it)
Is there a limit to the number of words in a context? It looks like it might be 3 (the keyword and the words immediately surrounding it)
Mr. Crab
23 years ago
23 years ago
I don't think there's any limit like that -- are you running into a problem? I know I have contexts of 4 and even 5 words.
» More new posts: Doghead's Cosmic Bar