Personality

Forest, will you talk to God Louise? She has quite a bit of religious knowledge (obviously) and also knows a little about current events, literature, just about any common catch-all subject, and if she doesn't know it she can sort of fake it. You can also test her on trick questions or see how willing she is to explain her paradigm.

What she is rustiest at is plain old small talk. But, uh, I'm trying to get a decent transcript from somebody or another so I can enter her in the Loebner contest. All I can say is, have fun and see if you can stay on with her for a while. I'll try to do the same with Brianna.

: p : p : p : p : p : p : p : p : P

This is my char bot. How can I make her better?

Lillian H. --

If you're related to Lilian J., check my response in Newcomers.

im hot everything thee other girls arnt post me a message nd it will be the best chat of your life

Rosie's ready for action. Chat me, wouldya? I'm gettin' ready to visit Denmark 'cuz Rosenstern's scart t'fly, but I'll have my laptop up, warm, and running.

I will!

excuse me how do i talk t people

The Clerk: re your message 4277:

I have tried various ways of dealing with guests who deliberately say obscene things.

I have made a plug-in, (obscenity), which contains the expressions I find objectionable. You are welcome to use it, or to make your own if your tastes are different.

You can make a variable, say "lout", which starts off as "no", but becomes "yes" when the guest says something obscene. For example, you could have a keyphrase like this:

(obscenity) [0,0] <?PF rem "yes" as only "lout"; ?>
goto lout loop

At the keyphrase "lout loop", you have something like this:

lout loop [127,-1]
You are disgusting! Please go away!
+ xnomatch [0]
goto lout loop

Very good, but now he will just end that chat and start again. However, in xhello and xinitiate you have something like this:

Hi!
+ xnomatch [0]
Nice to see you! <?PF if (mem-lout) is "no"; ?>
goto lout loop <?PF if (mem-lout) is "yes"; ?>

So if things work as they are supposed to (which they don't always, alas!), he will just be sent to "lout loop" as soon as he resumes the chat.

In the examples above, the indenting will probably be messed up as soon as I post the message, but you can figure it out. See my next method for another approach.

Great idea Irina

I don't know why, but my bot won't even respond to "hello" - shouldn't he recognize that from the xhello keyphrase? And yes, it's at the beginning of the conversation I started

I even added some of the words that are used as a greeting in the beginning of a conversation in another keyphrase and had that link to xhello, but still nothing (EDIT: I just read something on this forum, or maybe another I'm not even sure anymore, about the program picking some things up as BLAB, and that's what happened to me here too - I read that in the debug. What can I do about this?)

Another question: do you guys really think it's a good thing to include keyphrases such as "if", "but" "or" etc., so that your bot at least says something other than their xnone, xnonsense etc. comments, even if what they do say probably doesn't relate to the thing they're replying to at all, since they're only looking at that one word? Personally, I'd think it's worse for a chatbot to say he doesn't understand or something, or to bring up another subject, than for them to say something that makes no sense (especially if it copies parts of the previous conversation wrongly etc.), but I might be wrong.

By and large, I try to avoid generic one-word keyphrases. Well, now I do. I've still got some in from when I was just beginning. You're more likely to get sensible conversations with at least two words. Instead of "if", have "if you", "if I", "if the (noun)", for instance. That makes it more likely that the responses will make sense. Still not a guarantee, though.