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.

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.

Sounds a little iffy to me.

I think that's probably a good idea, Ulrike, though even larger keyphrases would probably be even better.

What do you mean, The Clerk?

And does anyone know anything about how to solve the problem I mentioned in my last post here?

The way it's supposed to go, if two bots talk, is

Bot1: xinitiate
Bot2: xhello
Bot1: xnone (unless something in Bot2's xhello triggered a keyphrase)

Saying hello at any other point in the conversation is treated as blab by the AIEngine. If you use raw mode and rank it high enough, you can get a hello keyphrase to pick up (but generally only if there are two words, like "hello there!").

Does that mean a conversation shouldn't ever really begin with 'hello' or 'hi'? That doesn't seem right...

Sorry, went a little JHONNY.

I did not mean to sound as if I were debating with Ulrike. Sonora bites, for one thing.

It's just a steep learning curve for me (obviously), that's all . . . it's like the environment. Every time you think you're helping one thing, you're screwing up twelve other things.

Whatsifsowhatsit:

No, they should start with it, it's just that hello/hi type words won't be recognised by xhello or xinitiate after the first two lines. The reason is that if it did, and someone's xinitiate was "hello", that would trigger an xhello let's say "hi", then this would trigger another xhello "howdy" which would trigger another xhello "hello" and you'd end up in an infinite loop.

Hello and hi are fine at the start.

Corwin,

Thanks for your reply. But that's just what I was wondering about, the words 'hello' and 'hi' at the start. I get that it shouldn't continue replying to it on and on, but if I open a conversation with my bot with 'hello' or 'hi' or similar words, he goes to the xnone reply, saying he doesn't understand. In debug, it says that it sees my entry as BLAB or something like that.

But as I said, thanks for replying

Hmm... this message I typed here needs to go