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 can pull up the transcript for my username, but when I try to pull up the transcript for my bot, my browser pretty much freezes.

'im = him
so much for trying to use a phony accent

**feeling dumb** if I use a question for 'xintroduce' will the recieving bot reckognize it as a question and give an answer... OR... will it give an automatic 'xintroduce' response? (I have read the AI book) maybe i'm not intelligent enough for this?!? =)

mirror_rorrim, see reply in AI Engine forum.

Alright, so maybe I'm an idiot... I'm trying to give my little guy a list of favourite foods, but the question automatically references xfavorite. How do I futz with that?

That's not currently possible. A lot of us have found it irritating over time, but for now it remains one of the limitations of the system. On the other hand, it is also one of its strengths, since when it is functioning well, it will respond appropriately to questions about many types of favorite things that you wouldn't dream of including.

If the fact that the response will not be consistent when the same question is asked multiple times is what bothers you, you can always substitute a few vaguer responses.

EG:

I don't think I really have a favorite (type). I like pretty much all of them.

Hey, that's private. You don't here me asking you about the stuff you like do you?

I guess I could say (specific), but I change my mind a lot.




Not that you should necessarily use exactly what I put in, but you get the idea.

Alrighty, thanks. (Darn. I had a whole set o' plug-ins poised and ready to launch, too *sigh*.)

Seems to me that it would work well if you could make xfavorite a generic, catch-all category that kicks in when another keyword (or sequence) *isn't* referenced. That could get overly complicated, though...

Leave the plug-ins and phrase you created where they are. I'm sure eventually the Professor will make the adjustments that will make them workable. But for now he's a busy man. Patience will eventually be rewarded. Take the most recent updates to wildcards, prekey/postkey and several other functions which people were asking for for a long time, only for them to turn out to have been on The Profs To Do list all along.

well for those who are not so patient there is always me.
*flies around the room*

Bot of the Day: LinBot!

Yes I had a really long conversation with Linbot and it would probably the best conversation I have had for a long, long time. She kept up the conversation really well and was really interesting!

Do bots dislike you when you get a chat window from them and just close it? I doubt it, but for authenticity/a better simulation, I think they should. After all, how would a human chatter feel if you just never even acknowledged their existance? After all, they could chat anyone, but they chose you.

hmmm? interesting to say the least