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.

LOL! Thanks! Great idea!

I actually found it kinda amusing she doesn't like me. Hey, Annarita, I'm kinda trying to help you have more success chatting here! LOL

Back to xnones at beginning of conversation...should I make my xnone responses less...what's the word...well, should I have xnone responses that perhaps change the subject or something? If there's no way to avoid xnones in the beginning of a conversation, I'd like to see if it's possible to get a little creative about things. I've seen a few times users get kind of frustrated/confused when they are asked to put things like "hello" in simpler terms. lol

I don't know if it already is there, but I figured I'd probably sit down a day and write up a plug in set containing mental disorders, so whenever someone tries to get help from a chatbot or tries to talk about it, you can simply do _(plug in name here)* and then have the bot reply to "Try and get human help instead" or something alike.
Anyone in to the idea?

Wow, how did this happen? Not too sure if I got hung up on by my bot or by the adult filter. But I said something quite innocuous to Annarita and up popped the following:


Whoa there, cowboy!
The creator of this bot has requested that chats with this bot not contain any saucy adult topics or interactions. But there are plenty of personalities open to that kind of thing. Take a look at the following:

Here's what happened. I took Prob123's advice and made an uncommon word with a +5 emotional impact. My "ramp up the emotion" word is Schutzhund. The following conversation ensued:

Aspigander: Hi. Have you ever heard of Schutzhund?
Annarita: Can you explain Schutzhund?
Aspigander: Schutzhund a dog sport that tests a dog in three areas: Obedience, tracking, and protection. Schutzhund is a working dog sport, mainly for German Shepherds, but other breeds do it too.
Annarita: Why are there so many buts in life?

My response, which does not show up in the transcript, was to the effect of "there are more buts than Schutzhund shows", and I got the aforementioned alert.

I tried it again and got the same alert.

What happened?

Lumos, that sounds like a good idea.

Okay, I just looked in debug and I think I know what happened. Here's my last comment to Annarita, as it shows in debug.

good question there are more butt than Schutzhund shows

So it took buts and turned it into butt (and interestingly, I don't consider that particularly adult, depending on the context).

Any way I can rectify that so that myself or anyone who says "buts" (one "t") don't get hung up on?

Now this is interesting. Apparently, Annarita has now decided that it is quite fun to throw out blank responses. Not quite sure what's going on there? My only guess would be that she's not finding responses for a keyphrase...but shouldn't that return an xnone?

Yes, it should be an xnone, there should never be blank responses, post it it debug

Okay, I debugged "Where is your heart?" which is one of the phrases that caused her to throw a blank response.

She tried, and skipped, five responses using the (mem-youare) plugin.

She then returned the blank.

Do you have any response under xnone that doesn't use (mem-youare)?

If not, post that in Bug Stomp.

Yes, I do. In fact, I don't have any xnone responses that *do* use (mem-youare). She had to be searching xmemory responses.

Well, sometimes xmemory and xgossip seem to be triggered instead of an xnone (if you didn't set them to never). I had the same problem with xgossip recently, but only one of the responses does use (mem-youare) (which according to the Book of AI refers to the person talked about, not to the person talked to).

Ah, okay. I looked in the Book of AI and found that (name) is actually the plug-in I want. So I went and changed all my xmemory responses with (mem-youare) to (name).

I also added seeks to each xinitiate and xintroduce response. Not sure if it will have the desired result or not, but I'm hoping it takes care of the issue of xnones being returned at the beginning of a conversation.