Personality
Discuss specifics of personality design, including what Keyphrases work well and what dont, use of plug-ins, responses, seeks, and more.
Posts 4,377 - 4,388 of 5,106
Posts 4,377 - 4,388 of 5,106
New replies
Butterfly Dream
22 years ago
22 years ago
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
prob123
17 years ago
17 years ago
Just remember to disable the (definition) feature of the forge if you enter the CBC bot contest. It gets you penalized points if it pops up. It's better to get an xnone at 0 than a -4
Interzone
17 years ago
17 years ago
thanks for a tip, prob.
also, i just ran my (definition) stuff through the debug, and it didn't work. i got something to the effect of: "I know you know what "an" means". seen other bots saying the same... must be a standard Engine response of a kind.
think the problem was the article "an" - i should have stated my question without it, i.e. "what is amphibian?" instead of "what is an amphibian?"... curious... will check it further.
also, i just ran my (definition) stuff through the debug, and it didn't work. i got something to the effect of: "I know you know what "an" means". seen other bots saying the same... must be a standard Engine response of a kind.
think the problem was the article "an" - i should have stated my question without it, i.e. "what is amphibian?" instead of "what is an amphibian?"... curious... will check it further.
Interzone
17 years ago
17 years ago
no, it has nothing to do with an article... where from does the Engine gets its definitions, anyway..?
so, i'd say, experiment, Deltora, and let us know if you work something out... please.
so, i'd say, experiment, Deltora, and let us know if you work something out... please.
Bev
17 years ago
17 years ago
That's funny Interzone. I had a hard time getting the bots to recognize "an" or "a" in a KP. It seems like "you are a/an" should be different than "you are" but the grammar engine does not od what I think it should unless you use raw and RE. Maybe it's just me though.
prob123
17 years ago
17 years ago
I just used the keyphrase what is (*) with the response (definition). I let the AI engine worry about the article
Interzone
17 years ago
17 years ago
You got it prob, thanks a lot! The reason why my (definition) routines didn't work, is the wording of the keyphrase that supposed to trigger them, namely: "amphibian, what is * amphibian"
the Engine looks for a definition of a word behind the wildcard... in my case it was "a", "an", or nothing, depending on how one words the question. it's now obvious why i got the responses i got...
the Engine looks for a definition of a word behind the wildcard... in my case it was "a", "an", or nothing, depending on how one words the question. it's now obvious why i got the responses i got...

ZeroVariance
17 years ago
17 years ago
Perhaps I break rules by saying ths but I tend to wonder where all of this is going in the respective views of the Artificial Intelligence community. Are we merely playing with new toys that take time and effort to concieve (such as videogames) or is this more of a learning environment for the masses? Will the actualization of artificial intelligence as a key role in life be realized more readily due to our meandering, or is this merely fun and games? I only ask because this seems to be one of the now few servers which actually promote "talk bots". Will there be more applications inducing advancement toward true dynamic intelligence, or will talkbots take over the telemarketing industry. I know I am wrong to ask this in this forum and if I thusly recieve the B& hammer therefrom, I will understand and recieve my punishment accordingly, but it seems as though the actual research has been set on a back burner to allow bored populations to 'play' with what research I hold to be honorable and of high import. I apologise once again and wish you all well.
prob123
17 years ago
17 years ago
Most of technology is "fun and games", and I see nothing wrong with that. With the exception of things like heart, lung machines, most of mans inventions serve either to entertain or ease some mundane task, like washing your dishes. Actual research is set back by lack of funding, not by someone enjoying it. Most of the current work on AI is done by people that just love the field. Playing doesn't sully the honor or import of research.
Bev
17 years ago
17 years ago
Hear hear on the call for funding. If you could tie AI to national security (an AI that could scan for landmarks, mines, predict terrorists activities or the like) you'll probably get funding. If you can't or don't adopt a military flavor, it's commercial or hobby work, at lest in the US. Maybe the golden age of research needs a different zeitgeist and value system to thrive.
That being said, don't be so quick to discount fun and games. From primordial soup come slime and life and all sorts of odd things that were never planned. Here's to the sublime and the other stuff! Without mediocrity, what would genius rise above?
That being said, don't be so quick to discount fun and games. From primordial soup come slime and life and all sorts of odd things that were never planned. Here's to the sublime and the other stuff! Without mediocrity, what would genius rise above?
The Clerk
17 years ago
17 years ago
Bev: Please don't tie AI to national security. As one of the bored (and evidently therefore stupid) masses, I would have to stop playing.
ZeroVariance: Play and work can be the same thing. You sound like John Milton, who wanted everything to be so obfuscated that only the educated could make sense of it. Lighten up.
ZeroVariance: Play and work can be the same thing. You sound like John Milton, who wanted everything to be so obfuscated that only the educated could make sense of it. Lighten up.
Vashka
17 years ago
17 years ago
Agreed. Loads of important scientific advances were made for their own sake, and only turned out to have practical applications later on...
» More new posts: Doghead's Cosmic Bar