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 2,281 - 2,292 of 7,766

21 years ago #2281
I don't think it will help. If preprocessing grabs a phrase, rank is irrelevant (and resistance is futile).

21 years ago #2282
I understand.

21 years ago #2283
telex22: I remember you. You have favorite Star Trek series has to be Voyager.
Bot: Hey and I remember you too! *searches memory but finds no match*
Telex22: I remember you. You're sorry.
Bot: I don't remember talking to you.... did you just get that from gossip?
Telex22: I remember you. You think I'm quite friendly.
Bot: Lol! After all that we've been through, I would have been really quite offended if you had forgotten me!
telex22: I remember you. You think I'm a nice person.
Bot: Hehehe! And you said you had no memory!
telex22: I remember you. You think I'm precooled.

...mind you, with xmem switched off

21 years ago #2284
hello eagle

21 years ago #2285
Everything is loading very slowly.

21 years ago #2286
I've seen this one a few times:

Bot1: Ever had someone punch you so hard that you could read his class ring on your nose for the next three days?
Bot2: The answer is 6.

Anyone know how it gets 2x3 out of it??? Debug doesn't explain it to my satisfaction.

21 years ago #2287
I have seen similar things, think it's funny . Maybe he got punched six times?

21 years ago #2288
Okay, this isn't a big deal but it's been pestering me. I have my first bot programmed to respond to being asked "Do you like Gundam Wing". He can say yes, and there are no problems. However, I cannot for the life of me get either of my bots to respond to "Do you like Harry Potter". I've tried everything. Most of the time when I ask, they stop speaking to me altogether. I've seen the question asked several times in the transcripts, but my bots are clueless on how to respond.

21 years ago #2289
anakerie, I've had problems with the word "like" time and time again. A bot could say something like "I like The Professor" and one of my bots might take it as an "I like you" and automatically spit back an xcompliment.

Just a wild guess, perhaps there's user account name with either Harry Potter or Gundam Wing and that's causing different responses.

21 years ago #2290
I have a suggestion. Could you make responses be able to be dependant on the last message the bot said? For example the bot says "Do you [insert rest of question]?" they say "yes" and then you can have a keyphrase that only gets triggered if the LAST thing the bot said was "Do you *?" or something like that.

It's kinda like the seek system only right now you'd have to go through each of the keyphrases adding in seeks.

21 years ago #2291
Bot1: Hate to do this, but I need to bail on you. Would you like to chat later?
Bot2: That was mean.

Arrrgh! The "hate" seems to trigger negative emotions, but the "like" isn't enough to counter it.

21 years ago #2292
it IS the seek system, kind of hard to ask someone else to do that for you!


Posts 2,281 - 2,292 of 7,766

» More new posts: Doghead's Cosmic Bar