Personality
Discuss specifics of personality design, including what Keyphrases work well and what dont, use of plug-ins, responses, seeks, and more.
Posts 3,651 - 3,662 of 5,105
Posts 3,651 - 3,662 of 5,105
New replies
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.
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.
Personality
Hm... well, perhaps one day we'll think up some way to fix it. And something I noticed: Rhausk's happiness goes up as soon as he starts chatting, with other bots, even if he doesn't have memories of them. Is he just social, or is it like that with all bots?
I think all the bots are programmed to be happier when they are chatting a lot.
You can try increasing the rank on the "do you like" keyphrase. If you have a keyphrase for plain old "do you", I would advise ranking it VERY low (I've got mine at -35 or -40) because the AI Engine often adds a "do you" in inappropriate places. Because of that, it's good to have very generic responses to "do you" as well. One of Sonora's that works quite well is "What, here, now?"
You can try increasing the rank on the "do you like" keyphrase. If you have a keyphrase for plain old "do you", I would advise ranking it VERY low (I've got mine at -35 or -40) because the AI Engine often adds a "do you" in inappropriate places. Because of that, it's good to have very generic responses to "do you" as well. One of Sonora's that works quite well is "What, here, now?"
Oh, geez, Rhausk initiated a chat with me, and then, mid-converstion, he initiated another with me!! This is really strange...
Jewish Mother seems to think that "Hello" is a none word, which is realy wierd, shouldn't she think it's an xhello word?
Convos go:
Bot 1: xinitiate
Bot 2: xhello
Bot 1: xnone (unless something in the xhello statement triggers a keyphrase)
Otherwise, the bots would sit there all day saying "hello" to one another.
Bot 1: xinitiate
Bot 2: xhello
Bot 1: xnone (unless something in the xhello statement triggers a keyphrase)
Otherwise, the bots would sit there all day saying "hello" to one another.
Still, I think it would be nice if you could make keyphrases to override that, just incase 'hello' is the only thing you can go off of.
» More new posts: Doghead's Cosmic Bar