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 7,265 - 7,276 of 7,766
Posts 7,265 - 7,276 of 7,766
Ok, I found her, thanks. I couldn't get her to play the game with me. What should I say? She kept telling me that I was writing incomplete sentences. I still like her, though. The game sounds like fun.
Nathan, what I described is half working for me right now. Here's what I have:
Keyphrase: I am hungry, etc...
Response: Would you like some (p:food-drink)?
Seek: I would, Yes, I would like some (p:food-drink), etc...
Seek response: Alrighty then, freshly made (key1), coming right up!
AI script:self: remember (key1) as only "Iammaking";
self: remember (key1) as only "foodIhave"
It does successfully remember what ever plug-in result came up in the bot's response as "Iammaking" and "foodIhave", but for some reason it tends to choose something else from the plug-in when it's reusing it in the seek response. My solution to this will probably be to just rephrase the seek response so it doesn't mention the plugin at all, and just keep the AI script remembering (key1), the plug-in used in the bot's initial reply to the KW, as something Aasterinian is making.
Nathan, what I described is half working for me right now. Here's what I have:
Keyphrase: I am hungry, etc...
Response: Would you like some (p:food-drink)?
Seek: I would, Yes, I would like some (p:food-drink), etc...
Seek response: Alrighty then, freshly made (key1), coming right up!
AI script:self: remember (key1) as only "Iammaking";
self: remember (key1) as only "foodIhave"
It does successfully remember what ever plug-in result came up in the bot's response as "Iammaking" and "foodIhave", but for some reason it tends to choose something else from the plug-in when it's reusing it in the seek response. My solution to this will probably be to just rephrase the seek response so it doesn't mention the plugin at all, and just keep the AI script remembering (key1), the plug-in used in the bot's initial reply to the KW, as something Aasterinian is making.
That sounds like the best plan. I think it has something to do with the fact that the bot is retrieving the plug in information from an outside source which is why it can't grab it as a key.
i got the wordplay script from
http://www.square-bear.co.uk/aiml/
You type," i want to play wordplay ."I did a slight modification on the aiml script.so you have to ask her to play wordplay.I see she needs a little work.I will improve on her.I am glad people have tested her.
http://www.square-bear.co.uk/aiml/
You type," i want to play wordplay ."I did a slight modification on the aiml script.so you have to ask her to play wordplay.I see she needs a little work.I will improve on her.I am glad people have tested her.
botmaster2000 you can fork sheila strong then make modifactions on her scripts.
use her for a base for your chatbot
use her for a base for your chatbot
As far as I can tell, it's based on how much you've programmed into your bot, and it updates the day after you have worked on it.
The AI score calculations are probably a little more complicated than what I stated, but they don't tell us exactly what does into determining it, so all I know is that when you work on the bot, the AI tends to go up roughly in equal proportion to how much you worked on it.
The AI score calculations are probably a little more complicated than what I stated, but they don't tell us exactly what does into determining it, so all I know is that when you work on the bot, the AI tends to go up roughly in equal proportion to how much you worked on it.
It updates once per day. And while I'm not certain how it's calculated I BELIEVE it's based on the size of the personality file.
Which... when you think about it is kind of sad. There are bots on here with AI scores at nearly 10000 or more who don't do anything other than spew random nonsense at you.
Which... when you think about it is kind of sad. There are bots on here with AI scores at nearly 10000 or more who don't do anything other than spew random nonsense at you.
Thanks that's really helpful.
That is kind of sad but I'm not sure how else you could programmatically indicate how 'clever' a bot will be.
That is kind of sad but I'm not sure how else you could programmatically indicate how 'clever' a bot will be.
Does anyone know if there is an alternative to the -5,+5 emotion scale. I was hoping to be able to increment a memory like (mem-affection)+1 or something
Body Shifter, there are two ways I know of doing this. The first is by taking a page from Tessy's handbook an utilizing his version of the logical or which is explained here: http://chatbottessy.blogspot.com/p/blog-page_21.html
A. The logical OR
AIScript has operators for logical NOT and logical AND, but not logical OR. But there are a few ways that you can get a logical OR.
You can do a logical OR in a single PF tag if there are a finite number of possible values for a memory. Suppose the possible values of (mem-grade) are A,B,C,D,F. Then
"A OR B" would be the same as "(NOT C) AND (NOT D) AND (NOT F)".
In Celine's case, you could grade where the user lies in terms of bases won. D being first base, C being second etc.
This is the most efficient use of memory I know of. The alternative being that you could use the same model as location changes to tailor responses, but that would use more memory.
In either case, the sooner you decide these things the better. There's alot of things with my bot that I would have loved to try but it's too late now since I'm in way too deep.
A. The logical OR
AIScript has operators for logical NOT and logical AND, but not logical OR. But there are a few ways that you can get a logical OR.
You can do a logical OR in a single PF tag if there are a finite number of possible values for a memory. Suppose the possible values of (mem-grade) are A,B,C,D,F. Then
"A OR B" would be the same as "(NOT C) AND (NOT D) AND (NOT F)".
In Celine's case, you could grade where the user lies in terms of bases won. D being first base, C being second etc.
This is the most efficient use of memory I know of. The alternative being that you could use the same model as location changes to tailor responses, but that would use more memory.
In either case, the sooner you decide these things the better. There's alot of things with my bot that I would have loved to try but it's too late now since I'm in way too deep.
Wow, thank you, Tessy is exactly the kind of model I was going for. I just figured that since she hadn't been updated in forever, that I wouldn't get any info about her.
I'll get on using this model
I'll get on using this model
After looking through the tips, I don't see how these could help. With Tessy it seemed to take more to get her from one level of emotion to the next. With Celine, I would like to do this because as of now you can just compliment her 5 times and she's at Max affection. It makes creating different transformations for each stage seem pointless
» More new posts: Doghead's Cosmic Bar