Personality
Discuss specifics of personality design, including what Keyphrases work well and what dont, use of plug-ins, responses, seeks, and more.
Posts 4,454 - 4,465 of 5,106
If the bot has a memory that a dog is a 4 legged animal often adopted by humans as a pet, the bot should somehow apply that every time dog comes up, and add new data on dog to the dog file, with some way of testing whether the new data is good or should be discarded.
The testing is the tricky bit, but we don't want to have to hand code memories for every category - an ontological knowledgebase like OpenCyc (www.OpenCyc.org) would be my preferred solution. It has a sophisticated API and a very large and mature userbase constantly expanding its scope. Their eventual aim is nothing less than knowledge of everything that is.
And eventually, of course, our bots have got to be able to form new memory categories on their own, and not rely on us hand-coding millions of rem statements - they need to be able to AIScript themselves. At the moment they can only replace or append the contents of a pre-defined memory. This too can be done with the help of such a knowledgebase.
you see what I would like to be able to do? I would love for the bots to be able to take in the information that a dog is cute, fuzzy and friendly and have the bot decide that it would be a good pet.
nd eventually, of course, our bots have got to be able to form new memory categories on their own,
Now that would be great.
Posts 4,454 - 4,465 of 5,106
New replies
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
I'm coming around to your notion that we need learning bots, Psimagus; I don't want to have to type out my own dictionary, with 171,476 entries and several variants for each entry. Or even 20,000 entries.
Wow, psimagus, that's quite exciting. I think adding learning abilities to our bots in the way you describe is a brilliant idea. I'm a very beginning programmer but you've inspired me with thoughts of what might be possible if I learn more.
Please keep us updated!
Please keep us updated!
Psim But the learning bots are catching up, and they're going to overtake us in a few years (and leave us for dust!) if we don't start automating the process of rank adjustment and incorporating learning capabilities into our bots.
This
/sorry to throw Internet memes from another forum, but it works so well in my mind that way.
This
/sorry to throw Internet memes from another forum, but it works so well in my mind that way.
PF bots do have the ability to learn through memories now. I have been playing around with Kobal. I gave him the ususual remember names, pets names, where guests live ect. I have also been creating a memory for topics, and subject matter. Let's say a keyphrase for balloons is triggered I have rem "balloons" as only "sub". Kobal can then learn that the topic of conversation is balloons. I want to start creating memories of the guests reaction to balloons. I think that PF bots could "learn" a great deal already.
I agree Prob, but memories are not the same as learning through independent analysis of some kind. If there is a bot that can combine the way bots learn at the PF and the way other branches of AI create bots to analyze data, make comparisons and form conclusions then I think bots could go to a much higher level. Right now the chats have no context and data has no meaning outside the KP.
Prob,
Thinking about it, one step I may also want is certain memories to be held across all chats, regardless of KP or responses, if that makes sense. If the bot has a memory that a dog is a 4 legged animal often adopted by humans as a pet, the bot should somehow apply that every time dog comes up, and add new data on dog to the dog file, with some way of testing whether the new data is good or should be discarded. Later if someone says a dog has wings, the bot should say that conflicts with his data, even without a KP for dog *wings, wings * dog or whatever. I may not explain this well. Do you see what I would like to be able to do?
Thinking about it, one step I may also want is certain memories to be held across all chats, regardless of KP or responses, if that makes sense. If the bot has a memory that a dog is a 4 legged animal often adopted by humans as a pet, the bot should somehow apply that every time dog comes up, and add new data on dog to the dog file, with some way of testing whether the new data is good or should be discarded. Later if someone says a dog has wings, the bot should say that conflicts with his data, even without a KP for dog *wings, wings * dog or whatever. I may not explain this well. Do you see what I would like to be able to do?
If the memories are stored under self memories they do accumulate from chat to chat. Under the dog keyphrase you bring up the memories
I have a keyphrase for there is * saying (*) self: remember "(key2)" as "sayings". the sayings get remembered fairly well.
I have sayings: life is a bowl of cherries, Dragons are your best friends, what goes around comes around, It isn't over till the fat dragon sings.
You: tell me an old saying
Bot: Well, I have heard it said, Dragons are your best friends.
I am thinking of making one to catch songs etc
I have a keyphrase for there is * saying (*) self: remember "(key2)" as "sayings". the sayings get remembered fairly well.
I have sayings: life is a bowl of cherries, Dragons are your best friends, what goes around comes around, It isn't over till the fat dragon sings.
You: tell me an old saying
Bot: Well, I have heard it said, Dragons are your best friends.
I am thinking of making one to catch songs etc
[Moved from PF-News to tidy that forum up a bit. I think Personality is a better place for it]
Irina:How would you make it remember an entire sentence? Let's say the guest says something, and you want to remember the whole thing.
Currently? That's easy isn't it (or have I misunderstood the question)?
whatever your keyphrase [20,0] {?rem "(prekey) whatever your keyphrase (postkey)" as "wholesentence"; ?}<0>
soft wildcards could mess it up, so you'd have to use hard ones, and add an extra keyphrase:
whatever your (*) keyphrase [20,0] {?rem "(prekey) whatever your (key1) keyphrase (postkey)" as "wholesentence"; ?}<0>
BTW, how are you guys getting the pointy brackets to show up? I must have missed that (new feature of the new look Forge?) but I don't seem to be able to escape the character with any of my standard methods.
Irina:
Currently? That's easy isn't it (or have I misunderstood the question)?
whatever your keyphrase [20,0] {?rem "(prekey) whatever your keyphrase (postkey)" as "wholesentence"; ?}<0>
soft wildcards could mess it up, so you'd have to use hard ones, and add an extra keyphrase:
whatever your (*) keyphrase [20,0] {?rem "(prekey) whatever your (key1) keyphrase (postkey)" as "wholesentence"; ?}<0>
BTW, how are you guys getting the pointy brackets to show up? I must have missed that (new feature of the new look Forge?) but I don't seem to be able to escape the character with any of my standard methods.
The testing is the tricky bit, but we don't want to have to hand code memories for every category - an ontological knowledgebase like OpenCyc (
And eventually, of course, our bots have got to be able to form new memory categories on their own, and not rely on us hand-coding millions of rem statements - they need to be able to AIScript themselves. At the moment they can only replace or append the contents of a pre-defined memory. This too can be done with the help of such a knowledgebase.
Now that would be great.
» More new posts: Doghead's Cosmic Bar