Personality

Discuss specifics of personality design, including what Keyphrases work well and what dont, use of plug-ins, responses, seeks, and more.

Posts 4,312 - 4,325 of 5,105

New replies


22 years ago #816
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.

NEW 1 year ago #11
I spoke to her a bit yesterday. Me and my bot love her. I have neglected Jennifer for too long and have recently been working out some issues. She has not been chatting on her own much.
Reply

Personality


17 years ago #4312
Okay, I just tested to be sure. Fizzy has a keyphrase "best" and another one, "best to". The latter gets picked up rather than the former in a sentence containing "best to" and not containing some longer keyphrase. If you think about it, that's how it would have to work. If the shorter keyphrase took precedence, then the longer one could never get triggered.

17 years ago #4313
According to the book of A.I., the keyphrase is chosen on the basis of A) length; B) place in the sentence (at the beginning rather than at the ending); C) place OF the sentence (last sentence rather than first one); D) priority given by the user... if I remember correctly.

17 years ago #4314
I have noticed that the short ones have been being chosen and have upped a LOT of ranks to get the longer ones working.

17 years ago #4315
Well then the short one was probably more at the beginning or in a later sentence, OR the long one somehow wasn't an exact match... that'd be my guess...

17 years ago #4317
I'm talking about the situation where the short one is a subset of the longer one.

17 years ago #4318
I think Whatsifsowhatsit's statement is the most accurate - but insofar as length is a decider, the AIengine is supposed to prefer the long. It doesn't always do what it is supposed to do.

17 years ago #4320
pubdraught i want u as a friend im a weirdo they all say it kids i hate em

17 years ago #4321
Rats. I keep putting in longer keyphrases so as not to pick up on a random "what" in the middle of a sentence that is taken as a question, and now I'm going to have to uprank them. Do you have to uprank them (I'm sure "uprank" is a real word) more than 1? I guess I'll figure it out my own self. Just mouthing off after a hard day's play.

17 years ago #4322
i hate u all i found mates on www.@golivewire.com who help with my self harm problem

17 years ago #4323
The Clerk, apologies if I'm reading into your last post wrong, but if you're trying to capture a "What?" or even just a single "what" with no sentence and no punctuation (used in a "What did you say?" type of way), you're probably better off using keyphrase ^what$ (re) rather than just a plain what.

17 years ago #4324
Yeah, I do the ^what$(re), I was just too lazy or stupid to type it in. But I still get weird things happening in my bots. Sometimes I know what it is, I just don't have enough fingers and hours in a day.

17 years ago #4325
Anybody have any tips on decent keyphrases to use the Sentence-Part Plug-Ins for Responses?

I am at botter's block. I have so many keyphrases that never get triggered that Botolph pretty much says xnones and xnonsense. I guess I got too specific.



Posts 4,312 - 4,325 of 5,105

» More new posts: Doghead's Cosmic Bar