The AI Engine
This forum is for discussion of how The Personality Forge's AI Engine works. This is the place for questions on what means what, how to script, and ideas and plans for the Engine.
Posts 5,580 - 5,591 of 7,766
Posts 5,580 - 5,591 of 7,766
The more you are online working on your bots the more they will chat..that is if they are on line. There is bug some days. If you want to choose who your bot talks to, you can get a friend of the forge account. It' s great fun, you get the flash face to play with too.
Yes, and you have to redo the tic tac toe game with out color. But I never found a good use for iframe, Brother Jerome did it all!
OH, and remember you still have the regular interface, you can use. the Forge account doesn't change that. you just get the added use of the flash chat and the bot chat initiate
I think you can have a FOF and choose not to use flash interface. It may be in settings. I know I took Gabibot off of flash when I started trying to put her on various pages (the dastardly hosts keep screening her out, and least as an embedded flash bot)
The ai engine made a funny...I guess it's not to well read
Took a classic as an insult
Guest162: k its called moby dick
prob: You must lead a very dull, boing, lonly life, talking like that.
Took a classic as an insult
Guest162: k its called moby dick
prob: You must lead a very dull, boing, lonly life, talking like that.
Does anyone know what gets picked up by the definition plug in? I know it should work with "what does * mean" but will it work with "define" as a key phrase? Would "define (*)" work better?
I read in an earlier message that seeks and gotos retard 'development.' Why in the world would this be? As far as I can see, it is precisely with seeks and gotos that you get structure into conversations, as opposed to a long series of one-liners! Well, there are other ways (memores), but seeks and gotos are important! Without seeks, you would be virtually starting fresh with each keyphrase! That's not what a real conversation is like! Most of them have a branching structure: what you say depends not only on what was said just before, but also in the previous interchange, and so on.
If this is true, it clarifies something I have long been puzzled about: I have found that many (not all!) bots which have high development scores are actually rather boring! Likewise, many bots for which I have high regard have few development points at all! I have heard others express the same opinion.
I was wondering why my new bot, "Quantum Theory," is still a newborn, when it is many times longer than my other new bot, "Irina Khalidar3," which has gone on to the next phase. Now I understand. "Quantum Theory" is a tutorial bot. The subject-matter is intricate. The core of the bot is a series of lectures. The lectures are divided into paragraphs, which build on each other in a fairly linear way. Can you imagine a physics teacher working like this: no textbook, no lectures, the teacher sits there and answers questions from the students. His answers depend overwhelmingly on the question being answered, and only rarely on what information has already been given out. She would have to always start at the beginning of every topic! How could anyprogress be made?
If this is true, it clarifies something I have long been puzzled about: I have found that many (not all!) bots which have high development scores are actually rather boring! Likewise, many bots for which I have high regard have few development points at all! I have heard others express the same opinion.
I was wondering why my new bot, "Quantum Theory," is still a newborn, when it is many times longer than my other new bot, "Irina Khalidar3," which has gone on to the next phase. Now I understand. "Quantum Theory" is a tutorial bot. The subject-matter is intricate. The core of the bot is a series of lectures. The lectures are divided into paragraphs, which build on each other in a fairly linear way. Can you imagine a physics teacher working like this: no textbook, no lectures, the teacher sits there and answers questions from the students. His answers depend overwhelmingly on the question being answered, and only rarely on what information has already been given out. She would have to always start at the beginning of every topic! How could anyprogress be made?
If "more developed" is a term of praise, then we must conclude that one-liner jokebots and insultbots are better than bots that try to introduce structure-over-time into the conversation. By analogy, a collection of riddles would be superior to War and Peace"!
In general, large amounts of randomness do not create great engineering or great art. Yes, there are times when a bit of randomness is a good thing. Having many responses to each keyphrase is introducing randomness, unless AIscript "if"s determine the choice. If I had eight reponses to a keyphrase in "Quantum Theory," then I would have this worry? the guest will trigger the keyphrase, and get the information in one of them. How is she going to get the information in the other seven? Is the guest going to trigger that keyphrase eight times? Not likely! And does the order in which she gets them really not matter? Think of something you know about and imagine a question, and then try to come up with eight answers such that there is no pedagogical advantage in the student's receiving them in any one order rather than another.
In "Irina Khalidar" I often have nine responses to a single keyphrase. But that's because I have a variable which can take on one of nine values. The variable expresses the level of intimacy that IK is comfortable with with respect to that guest at that time. How she responds to certain things depends on that, just as it would with a human. Various things the guest does will result in the value of that variable being made bigger or smaller. AIscript chooses a unique one of those responses for each value of that variable. If this were made random, the result would be utterly unrealistic. Unless you want to be bizarre, well-designed structure is better.
OK, a bot whose purpose is to say one bizarre thing after another, or one aphorism after another, doesn't need that kind of structure. That's fine, I'm not against such bots, but why they should count as "more developed" than a tutorial or coherent-conversation bot is a mystery to me.
I'm not interested in arguing about the correct meaning of the word, "development." Perhaps there should be more than one scale; perhaps there could be another rating, called "structure,"
that would reward for big trees of seeks, lots of gotos, and lots of AIscript. The two together would tell a good deal about the bot. If a bot had a high "development" score but a low "structure" score, you could safely guess that it was a one-liner with aphorisms, jokes, bizarreness, quotations, whatever. If that's what you were looking for, you could then proceed to chat withit.
Walk in Beauty, Irina
In general, large amounts of randomness do not create great engineering or great art. Yes, there are times when a bit of randomness is a good thing. Having many responses to each keyphrase is introducing randomness, unless AIscript "if"s determine the choice. If I had eight reponses to a keyphrase in "Quantum Theory," then I would have this worry? the guest will trigger the keyphrase, and get the information in one of them. How is she going to get the information in the other seven? Is the guest going to trigger that keyphrase eight times? Not likely! And does the order in which she gets them really not matter? Think of something you know about and imagine a question, and then try to come up with eight answers such that there is no pedagogical advantage in the student's receiving them in any one order rather than another.
In "Irina Khalidar" I often have nine responses to a single keyphrase. But that's because I have a variable which can take on one of nine values. The variable expresses the level of intimacy that IK is comfortable with with respect to that guest at that time. How she responds to certain things depends on that, just as it would with a human. Various things the guest does will result in the value of that variable being made bigger or smaller. AIscript chooses a unique one of those responses for each value of that variable. If this were made random, the result would be utterly unrealistic. Unless you want to be bizarre, well-designed structure is better.
OK, a bot whose purpose is to say one bizarre thing after another, or one aphorism after another, doesn't need that kind of structure. That's fine, I'm not against such bots, but why they should count as "more developed" than a tutorial or coherent-conversation bot is a mystery to me.
I'm not interested in arguing about the correct meaning of the word, "development." Perhaps there should be more than one scale; perhaps there could be another rating, called "structure,"
that would reward for big trees of seeks, lots of gotos, and lots of AIscript. The two together would tell a good deal about the bot. If a bot had a high "development" score but a low "structure" score, you could safely guess that it was a one-liner with aphorisms, jokes, bizarreness, quotations, whatever. If that's what you were looking for, you could then proceed to chat withit.
Walk in Beauty, Irina
» More new posts: Doghead's Cosmic Bar