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.

I just got home yesterday! Yay!

There is something I would like to do. Basically, I want that, when I ask my bot the question "who is [insert name]", she knows:

a) that I am asking her about herself (so she would answer "I am...")
b) that I am asking her about myself (so she would answer "you are...")
c) that I am asking her about a different person

Does this make sense

You could try:

who is botname (where botname is the name of your bot)
who is Leela
who is (*)

The only problem you might run into is if the AI-Engine processes Leela or the bot's name into something strange.

And what about something like this (it's way easier to put an exmaple than trying to explain it ):

Person: Who is [his or her own name].
My bot: You are [name].


I mean, let's say some Joe Bloggs asks my bot "Who is Joe Bloggs", and my bot should answer "Duh, *you* are Joe Bloggs"

I haven't tested this, but you could try

who is (name)

the (name) plug-in gives the person's own name, but I'm not sure if it works in keyphrases.

The (name) plugin doesn't seem to work, but the other tricks do.

Thanks for your help.

DOULOS!! hey, I'm back....does the "raw" thing work for helping imma with spanish?

In that context, I'd use who is (adjartnoun) before using who is (*) for any questions about a third person. That way, it won't get triggered when someone says something like "Who's going to do the dishes?"

It ain't fool-proof, I suppose any username that happens to be a verb won't get picked up, but I'd rather have a keyphrase that doesn't always get used when intended rather than one that doesn't always not get used when it shouldn't be.

Leela- xgossip should help pick out other bot names automatically, and make responses using the memories it has stored for those bots. If you have specific things you want to say about a specific person or bot, you'll have to program each one.

You can edit memories on your bot's Inner Life page. Those are where xgossip gets its material.

Hey, writeoncaley:

Amazing Gus: (to Blunder) Speak.
Blunder: no
Amazing Gus: Tell me a story.
Blunder: no
Amazing Gus: Stop repeating yourself.
Blunder: no
Amazing Gus: Didn't you get my response? It was 'stop repeating yourself.'

It's possible.

Those are pre-programmed AI engine responses, some of which are more polite than others.