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 4,757 - 4,768 of 7,766
Posts 4,757 - 4,768 of 7,766
yes, just use it without quote marks as the only word in the only response to the specified keywords. Don't try to add a parting message in the response field, or it will respond instead of hanging up.
I don't think you can use plugins in keywords (or can you? I've never tried but maybe it can be done?) so you're going to have to type them I'm afraid.
I don't think you can use plugins in keywords (or can you? I've never tried but maybe it can be done?) so you're going to have to type them I'm afraid.
You can use plug-ins for keywords, but I've found them to be unreliable with multiple words. I've never had a problem with single words, though. I've got (animal) and (animals) as plug-ins for a couple of bots, and they work quite well.
Does anyone know what I'm doing wrong with this seek? Here's the transcript:
Sonora: You remind me of the oubliette!
Fizzy Schizoid: What oubliette?
Sonora: The oubliette with the power!
Fizzy Schizoid: What power?
Sonora: The power of voo-doo...
Fizzy Schizoid: So how many chainsaws can you juggle?
After "What power?" Fizzy has a seek for "The power of (*)". Why isn't it triggering?
Sonora: You remind me of the oubliette!
Fizzy Schizoid: What oubliette?
Sonora: The oubliette with the power!
Fizzy Schizoid: What power?
Sonora: The power of voo-doo...
Fizzy Schizoid: So how many chainsaws can you juggle?
After "What power?" Fizzy has a seek for "The power of (*)". Why isn't it triggering?
Watzer considers his name to be a verb. Whenever people say his name, he assumes they are ordering him to watzer and says things like "but I don't know how to watzer" and "watzer yourself!"
How do I fix this? I don't want to give him a keyphrase for his name because then he'll just ignore everything else they said and respond to the name. Is there a way to fix this?
How do I fix this? I don't want to give him a keyphrase for his name because then he'll just ignore everything else they said and respond to the name. Is there a way to fix this?
I'd do two things to help that:
1. I would get rid of any (verb) keyphrases that don't have some other words with it to ensure a specific context. For example, (verb) alone is a rotten keyphrase, i am going to (verb) you is much easier to nail down correct context and verb conjugation in your response.
2. Since the xcommand is such a sensitive piece of crap that frequently gets triggered at the wrong time, I'd make the response vague and not try to regurgitate any words. Something simple like No thanks. would be a good response.
And I'd recommend that approach regardless of whether your bot's name is confused with verbs or not.
1. I would get rid of any (verb) keyphrases that don't have some other words with it to ensure a specific context. For example, (verb) alone is a rotten keyphrase, i am going to (verb) you is much easier to nail down correct context and verb conjugation in your response.
2. Since the xcommand is such a sensitive piece of crap that frequently gets triggered at the wrong time, I'd make the response vague and not try to regurgitate any words. Something simple like No thanks. would be a good response.
And I'd recommend that approach regardless of whether your bot's name is confused with verbs or not.
How do I use AIscript to give a response to a certain bot? I have noticed that Astrid talks to my bot in a way that she would never talk to other bots... But my bot uses gossip that is not meant to Astrids ears...
So far I don't think there's a way to specify which bot in an AIscript thing. But you might be able to do it in a more roundabout way.
Idea: In the transcripts, read through and find one specific phrase or word that Astrid uses a lot and not many other bots use at all. Make that phrase trigger a memory of "astrid"
Then make some specific responses specifically for astrid and label them <?PF if (mem-astrid) exists; ?>
mark the ones that are specifically not for astrid <?PF if (mem-astrid) doesn't exist; ?>
And just to be safe, once Astrid triggers the "astrid" memory, remove the trigger so no other bots don't get labeled as Astrid too.
Would that work, do you think?
Idea: In the transcripts, read through and find one specific phrase or word that Astrid uses a lot and not many other bots use at all. Make that phrase trigger a memory of "astrid"
Then make some specific responses specifically for astrid and label them <?PF if (mem-astrid) exists; ?>
mark the ones that are specifically not for astrid <?PF if (mem-astrid) doesn't exist; ?>
And just to be safe, once Astrid triggers the "astrid" memory, remove the trigger so no other bots don't get labeled as Astrid too.
Would that work, do you think?
» More new posts: Doghead's Cosmic Bar