The AI Engine

Some questions:
- Who has good results by using seeks? Are they often 'hit'? What is the longest coherent string of gotos you ever encountered? Do u use it often?

Well, if you have yes/no questions then the yes/no seeks are often (but not always) hit

Here's a double streak. Don't think I've gotten better than that:

Little Mu: kj;';[,kkm
Guest: whatever that kitty is trying to say to me, she obviously wants to say it BAD!
Little Mu: Yup! She's done that to you before, right?
Guest: oh yes!
Little Mu: What can I say? She's an aspiring kitty journalist!

Hhahahahh!!!

That's excellent anticipation on your part Skysaw. In answer to lunar's question, I don't think I've ever buried seeks more than two deep, and I've never had a second triggered. I don't use seeks a lot generally, although I keep meaning to. It seems about the best way of stopping a bot becoming pretty much a Q&A bot, who can give a fairly coherent response to most things, but can't keep the conversation on one track, and never really has any idea what the subject of conversation really is.

ditto.. That's how come SS will give a great answer to the first question, but when a question related to the first one comes up, he has not a clue.

Ooh! Genius streak! Prof, how about... If each bot got X number of memory slots to work with, each memory slot could store a phrase or something, and there was a way to put things in it, like
a) A judge's real name
b) Something the user previously said
c) User's age
d) Anything!
... so it could be recalled like a plugin like "But you said (xmemslot2)" in a different part of the conversation, or "Wait! didn't you say you were (xMemSlot3)? I think you're lying!"

See, we would only use each xMemSlot or whatever it's called for one thing, like age, eye color, whatever, so we could use it in the conversation

How about... You know how you have keyphrases like:
I * did * that
How about (subj) covers the first *, (subj2) takes the second one, and (subj3) takes the subject from the whole phrase or something like that?

How about the "Who is (name)" we used to have?

Heya... I know my question sounds stupid (I'm new to this), but my bot can't seem to recognise either 'hi', 'how are you' or 'see you'. Should I just add them to the keyphrases? Because I tried it once, but someone said "........I want to see you....." and the bot took the 'see you' and ended the chat. Any suggestion on how it should be done?

What's with that honor thing?
What is it for?

Sharakael: 'hi' should be covered by the xhello, but the bots are only programmed to respond to it at the start of the conversation. you should definitely add how are you to your keyphrases. As for 'see you', if you want to keep it then that's up to you. The way to avoid having the conversation ended when someone is using 'see you' in a different context is to have keyphrases that include the phrase see you (i see you) (i want to see you). If you rank them higher than 'see you' on its own, your bot will respond more appropriately.

Bluroses: Honor is an equation that in a bot's case gives a rough indication of development level and in a human's case, how much time and effort they have put in. As for what it's for, that's up for debate. I guess if anything it's a motivational tool. It gives you a goal to strive for. I remember feeling really good when I got my first bot over 1000.