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 2,413 - 2,425 of 7,766
Posts 2,413 - 2,425 of 7,766
Whew! I've been at this all day. I've crushed every bug posted in this forum since June (hopefully). Here are the details:
Fixed an import bug that was improperly deleting some Seeks
Straightened out spacing on Seeks in Language Center
Added ability to turn off IP Security for those with shifting IPs
Returned Honor to working order
KornyHateMachine, I've differentiated between lets and let's more accurately.
Regular expressions Keyphrases are case insensitive.
Both "hahaha.." and "hehehe..." are seen as positive interjections. They are stripped out of the sentence and then marked as a positive emotion.
"Well" and "huh" are stripped out as an interjection when it's acting as one, but not in cases like "I do not feel well".
BIG ONE: The plugins (noun2), (verb2), (adjective2), (adj2), and (adverb2) have long been broken. They're working again now.
Butterfly, "Jesus" was being stripped out as an interjection. I've improved the system to prevent that.
The ability to put lists of Keyphrases (with commas) came with the somewhat casual release of PF2. Glad you like it.
Memories should not be coming up for Guests. I'm not sure when I updated this. But let me know if it's still happening.
Hemi, in a bot-chat, the other bot shouldnt respond with your own bot's Seek now. Let me know if this is working.
Ladydyke, I didnt realize "goto" was case sensitive. Sorry about that. It's not anymore.
Lunar22, I've added another level of anti-memory code. I dont know how they're coming up.
Some dumbnut made a bot named "I" which was messing up some of the sentence processing. I fixed this.
Anakerie, I found and fixed a bug that was causing trouble with word Clusters like "Harry Potter".
Spell correction was not working. This is now fixed.
Hemi, if Keyphrases had priority over xinsult and xcompliment, then at least in my bots, xinsult and xcompliment would never be triggered.
Hemi, I added prepeocessing for 1337 and 133t
Simulo, awesome idea about changing the image of abandoned bots to orphans. I have a deletion system in place, but I might do that automatically to help remind me to delete them.
With memories, (subj) and (mem) both work. I'll be rewriting the Memory AI very soon.
Boni, I updated Keyphrase matching to always match the first instance of a match. Previously it was matching the largest match possible. That wasnt exactly your problem- I think I fixed that earlier. But this would have been your next problem.
Just a note- Debug mode isnt the most user-friendly. I make it as much as I can, but it's always changing, and outputting what I need at any given point. If you can understand it, kudos to you! But of not, dont sweat it.
Also, try to keep Bug reports in Bug Stomp.
Fixed an import bug that was improperly deleting some Seeks
Straightened out spacing on Seeks in Language Center
Added ability to turn off IP Security for those with shifting IPs
Returned Honor to working order
KornyHateMachine, I've differentiated between lets and let's more accurately.
Regular expressions Keyphrases are case insensitive.
Both "hahaha.." and "hehehe..." are seen as positive interjections. They are stripped out of the sentence and then marked as a positive emotion.
"Well" and "huh" are stripped out as an interjection when it's acting as one, but not in cases like "I do not feel well".
BIG ONE: The plugins (noun2), (verb2), (adjective2), (adj2), and (adverb2) have long been broken. They're working again now.
Butterfly, "Jesus" was being stripped out as an interjection. I've improved the system to prevent that.
The ability to put lists of Keyphrases (with commas) came with the somewhat casual release of PF2. Glad you like it.
Memories should not be coming up for Guests. I'm not sure when I updated this. But let me know if it's still happening.
Hemi, in a bot-chat, the other bot shouldnt respond with your own bot's Seek now. Let me know if this is working.
Ladydyke, I didnt realize "goto" was case sensitive. Sorry about that. It's not anymore.
Lunar22, I've added another level of anti-memory code. I dont know how they're coming up.
Some dumbnut made a bot named "I" which was messing up some of the sentence processing. I fixed this.
Anakerie, I found and fixed a bug that was causing trouble with word Clusters like "Harry Potter".
Spell correction was not working. This is now fixed.
Hemi, if Keyphrases had priority over xinsult and xcompliment, then at least in my bots, xinsult and xcompliment would never be triggered.
Hemi, I added prepeocessing for 1337 and 133t
Simulo, awesome idea about changing the image of abandoned bots to orphans. I have a deletion system in place, but I might do that automatically to help remind me to delete them.
With memories, (subj) and (mem) both work. I'll be rewriting the Memory AI very soon.
Boni, I updated Keyphrase matching to always match the first instance of a match. Previously it was matching the largest match possible. That wasnt exactly your problem- I think I fixed that earlier. But this would have been your next problem.
Just a note- Debug mode isnt the most user-friendly. I make it as much as I can, but it's always changing, and outputting what I need at any given point. If you can understand it, kudos to you! But of not, dont sweat it.
Also, try to keep Bug reports in Bug Stomp.
Professor, I have a suggestion. It is only a suggestion.
I find that xinsult and xcompliment responses come up a lot in my bots conversations. I find that it ruins the conversation a lot of the time and gives away that it is a bot speaking.
I know that my bot would be able to give more specific responses if normal keyphrases had priority over xinsult and xcompliment responses. Maybe you could have an option for people to let this happen. If you don't agree, I understand. It is just my opinion.
I find that xinsult and xcompliment responses come up a lot in my bots conversations. I find that it ruins the conversation a lot of the time and gives away that it is a bot speaking.
I know that my bot would be able to give more specific responses if normal keyphrases had priority over xinsult and xcompliment responses. Maybe you could have an option for people to let this happen. If you don't agree, I understand. It is just my opinion.
Thank you Professor, I went in and put Ruby's keyphrases in how I had tried before and now she is replying just right. I was so excited I almost started hopping around. Yeah... doesn't take much to excite me... I should take up a sport or something.
I don't know how to program anything, but i was thinking that something that could help people out with there bot is a statistic on how "sane" there bot is. Meaning, a translation of how many of the bots keyphrases would answer in a sensible way. I don't even know if this is possible, but it would help if it was. Just a suggestion. And maybe the user could be told what keyphrases are thought to not make sense in response...just a suggestion.
Moreschi would get 0
Really, though, insanity is subjective. What if you were the only sane one in the world? You'd be called insane.
Really, though, insanity is subjective. What if you were the only sane one in the world? You'd be called insane.
Haha, you could say that. However by the theory of evelution that would never happen, haha, and by the definition of insanity, if you were the only sane one in the world you may be the only one who could make sense of things. So the title insane may be given to you, but you would still be the only one with a logical working mind. Thus, ignore the title insane to the bots, the point of what i said is to find what that the bot of yours says makes sense, and what does not.
Lygn88, that would be really hard to implement. You'd have to have perfect AI to be able to a) imagine the possible responses you could get from any given bot, and then b) determine if they make sense or not. I'm afraid that's up to us for now.
Hemi, I could add an option to turn OFF emotional responses altogether, but I couldnt have them happen after Keyphrases.. not without a lot of work. And as the emotions work great for me (and are funny when they fail) and nobody else has complained about it.. it's pretty far down my list. Sorry mate.
Plus I've got something really cool on the way. When I start working on it, I'll post a message in the news.
Hemi, I could add an option to turn OFF emotional responses altogether, but I couldnt have them happen after Keyphrases.. not without a lot of work. And as the emotions work great for me (and are funny when they fail) and nobody else has complained about it.. it's pretty far down my list. Sorry mate.
Plus I've got something really cool on the way. When I start working on it, I'll post a message in the news.
» More new posts: Doghead's Cosmic Bar