The AI Engine

I have a bit of a problem, hopefully someone here can help me with. When I have a response to a seek and that response ALSO has a seek, I am unable to use <?PF if male; ?> (and I assume any other script) in the response. I type it in and then update the responses and all looks well, but when I open the responses up again, my script is missing. Any suggestions? All I can think to do is reconfigure it so the seeks don't have seeks themselves or use a completely bogus keyphrase to send the "male" seeks to with a goto. Does that make sense? LOL

Oops, I forgot to add (and I hope this is the right place for it)...I LOVE the import/export option. It is sooo much easier and faster to work with BUT it has a tendency to cut off parts of some of my responses. Is this normal?

Lap cat, the scripts should still be there. For some reasons they just don't appear. If you download and look at it in wordpad they should appear. I use the export option quite a bit and have never had responses cut off. How long are yours?

Most of the time, the automatic responses to repeated input is very helpful, e.g., when a guest decides to keep sending blank responses over and over. However, this feature is a little overzealous when the repeated input would have matched seeks otherwise -- e.g., if the bot asks a series of yes/no questions and two answers in a row happen to be "yes".

doulos, the responses I noticed most often cut off were longer than two sentences. But what was weird was in the same keyphrase, it would do it to one longer response but not another. However, I did notice that some one line (sentence) responses had the AI script chopped off. I noticed that as I was debugging and trying to figure out why my bot was suddenly calling me gay. LOL.

I really like the export feature so I'm going to try it again later today. I'm just going to go slower at first and only add a couple new things...then import and check the language center to make sury they are as I typed them in WordPad. I've spent almost all morning checking and fixing things that happened on the last import. Errrr...

Thanks, Eugene. I have noticed the overzealous repeats to the yes/no questions and tried to work around that as best as possible...but I still have a LONG way to go.

I do have one other teeny tiny problem with my bot...He's ALWAYS telling me he loves me. I ask a question he should know and instead of giving me the programmed response all the time, half the time he tells me he loves me. While I'm flattered, I'm worried has developed an obsession with me and might need psychiatric help. If it goes any further, I just don't see how I can convince a judge to grant a restraining order against a bot. It's a definite dilemma. Though seriously, I'm trying to adjust the rank for the responses I want him to say, but am unsure how high I should make the rank without interfering too much with the randomness of his responses.

arrrgh. I think the biggest problem I've found is peoples inability to use the proper forms of your, you're, etc.. It's too bad the processor can't look at the word in context and acurately decipher what the user is really trying to say.


Guest61: Well there is not much to tell ecept I guess we are going to have a pretty bad storm
Aries: Why?
Guest61: Because my left wrist keeps hurting
Aries: I don't know why you think I'm interested in your left wrist.
Guest61: Thats the only way I can give the weather
Aries: It's bright and sunny here.
Guest61: Thats because your in sunny california. Here in michigan its gloomy
Aries: I once met a talking Black Rhinoceros that told me that same thing. He said 'Aries, that's because my in sunny california'. How strange is that?

I have a question.

Most of you are too new to remember me, but I have a bot with 3600-odd responses, who hasn't been updated since the import/export function was put in. Do you think I should attempt to update her using all the new features, or just ignore her and make a new bot? She's incredibly embarrassing as-is, due to rarely making much sense, but I don't know that I wanna go to THAT much effort to fix her.

I don't know how hard this would be to do, or who else might see the usefulness in this, but I was just thinking that it would be a great feature if we could have the option of disabling a keyphrase (maybe by checking a box?). I thought it might be helpful for botmasters when they are trying to isolate a response they find in their bot's transcripts, and also for when you have what you think is a really great idea, but it will take a little time to work out,and you don't want your bot to sound like a retard in the meantime...I even had a fantasy (yes I'm sick) about those disabled keyphrases showing in the language center in red instead of yellow to signify that they were "under construction". If y'all think I'm too crazy, I'll take this conversation to the Personality/PF Anonymous forum, and hopefully find consolation there with other addicts.

Actually, ezzer, I think that sounds like a great idea. Right now I just have a to do list in Word that must be a mile long. It sure would be nice if I could work on some of it in the language center without worrying about the ill effects. And I like the red idea too!

I also like the idea - I have some keyphrases I would love to get rid of, but they can't just be deleted, and since they have seeks beneath them, it makes it difficult to just change the phrase and come up with new seeks.

Hmm...if that's too much effort to code, maybe you could do the same thing by adding a new aiscript command. Call it <?PF test; ?> or something. Then anything flagged with this would only come up when the bot owner talks to their bot, instead of in all conversations. You could also make <?PF testonly; ?> in cases where you have several responses but you want to see if your newest one works. Instead of talking about pets 20 times before the bot says the response you want to test.