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 2,406 - 2,417 of 7,766
Posts 2,406 - 2,417 of 7,766
Simulo it may not have been documented, it was in the beginning, and as far as I know it still works.
Unless of course it has been supplanted by (firstprekey, etc)....
Unless of course it has been supplanted by (firstprekey, etc)....
I am looking forward to the new server. I hope I stop getting logged out after this one is replaced.
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.
» More new posts: Doghead's Cosmic Bar