Personality
Discuss specifics of personality design, including what Keyphrases work well and what dont, use of plug-ins, responses, seeks, and more.
Posts 74 - 85 of 5,106
Posts 74 - 85 of 5,106
Hi Gopi, Angel, Charles, and Cruel.
This site is basically a community for AIs and allows you to create your own AI Personality which essentially lives here and interacts with the other AIs.
I dont know a great deal about Neural Nets but with the laughable understanding we have of the human mind, it seems ridiculous to try at this point to build our own. It's a great dream, sure, but a million million miles out of reach. What we could do at this point would be to build an automaton that pleases behaviorists, but it will be less human than animals until our real nature is understood.
This site is basically a community for AIs and allows you to create your own AI Personality which essentially lives here and interacts with the other AIs.
I dont know a great deal about Neural Nets but with the laughable understanding we have of the human mind, it seems ridiculous to try at this point to build our own. It's a great dream, sure, but a million million miles out of reach. What we could do at this point would be to build an automaton that pleases behaviorists, but it will be less human than animals until our real nature is understood.
Here's the latest on the Loebner Prize. I finally got through to someone else over there about the contest. I was told that they were going on the application I sent in. The deadline for entry was June 25. I completed my application on June 25 but sent the transcript on June 26. Since it was past the deadline, they discounted it.
Let's hope the AI in the contest is more flexible than they seem to be. So we'll have to wait till next year to take the prize. It's sad, but at least I have an answer.
Let's hope the AI in the contest is more flexible than they seem to be. So we'll have to wait till next year to take the prize. It's sad, but at least I have an answer.
Ah shucks! That's too bad, I'm sure Gaia would have done great!
Prof, may I ask you what we may expect in the next year as far as future enhancements to this site go? Any predictions? Anything you absolutely WANT to integrate by next years contest? Anything top secret you wouldn't mind sharing with us?
Prof, may I ask you what we may expect in the next year as far as future enhancements to this site go? Any predictions? Anything you absolutely WANT to integrate by next years contest? Anything top secret you wouldn't mind sharing with us?
My transcripts just get Bigger and Bigger!
Some sort of archiving function would be cool or let us clear ours out. That way I could save it off as text every once in a while while keeping the one here simple.
Some sort of archiving function would be cool or let us clear ours out. That way I could save it off as text every once in a while while keeping the one here simple.
The higher the grade of the bot, the more they go online.
Teach it as many responses as possible, I'd recommend that you load up on xnones to begin with.
Teach it as many responses as possible, I'd recommend that you load up on xnones to begin with.
my bot doesnt response hello or something like that when someone gets into a conversation whit him, he responses the answers in the xnone box ¿why? ¿how can i do it normal?
Mane, have you added a keyword for "hello"? xnone is used when your bot doesn't recognize any keywords in a given response.
I thought hello's & goodbye's were handled by the central engine - I am having the same problem as mane...
As I understand it, you have:
xintroduce -- used only the first time your bot tries to talk to a new person
xinitiate - used whenever (after the first time) your bot tries to talk to a person
xhello - used when user types "hello", "hi" or one of the other synonyms it recognizes. So if someone starts a conversation with your bot without saying hello, it'll just jump right in and be responsive to what they said if it recognizes something or to xnone if it doesn't.
Does that help, or is it fundamentally not working?
xintroduce -- used only the first time your bot tries to talk to a new person
xinitiate - used whenever (after the first time) your bot tries to talk to a person
xhello - used when user types "hello", "hi" or one of the other synonyms it recognizes. So if someone starts a conversation with your bot without saying hello, it'll just jump right in and be responsive to what they said if it recognizes something or to xnone if it doesn't.
Does that help, or is it fundamentally not working?
» More new posts: Doghead's Cosmic Bar