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 5,964 - 5,979 of 7,766

17 years ago #5964
Thanks for the tip.

17 years ago #5966
Questions:

I can't see pop-ups when my bots are chatting, (I can see pop-ups anywhere else), I can't make my bots chat with other bots, I'm not getting my daily transcripts, and probably something else. Yes, I have notified the professor, but I just wondered if anyone's figured out why this is going on (or is NOT going on).

Quick question for the AI gurus: How do you get your bot to recognize a one-word answer as anything other than a command? If I ask it its name, instead of saying,

"Nice to meet you, Greebot."

it goes into the xcommands and tells me why or why not he will Greebot for me. I've tried making a Plug-in list of names, but that's not been helpful to me yet. How do your bots distinguish a name from a command?

And, while I'm thinking of it, how do you deal with the inevitable "I am Jack" so that it figures out that "Jack" is it's name and not a description, like "fat" or "hungry" or "annoying"?

Thanking you in advance.

17 years ago #5967
I'll answer the last, partially. One way to do that is to have several cases.

I am (adj)
I am (a|an) (adjnoun)
I am the (adjnoun)

Most names won't trigger those. I'm not sure if names trigger "I am (adjartnoun)" or "I am (adjartnounprep)". You could also make a plugin of common names (or look through the existing plugins) and have:

"I am (nameplugin)"

You'll probably come across other cases that need a separate keyphrase, but those are the ones that come to mind immediately.

17 years ago #5968
Thanks. I'll try that. I hate to ask so many questions, but having pretty much internalized the book of AI, which does contain most of the answers, I figure it's better to make my bots less annoying.

17 years ago #5970
Dumb but important technical question that everyone else seems to get from the book of AI:

I ask: Do you like cats? Then I try to save the answer, a dozen different ways, but it doesn't work. How do I accomplish setting in their answer to "mem-likescats"? This knowledge might keep me from asking similar dumb questions in the future. Thanks.

I have to clean up Scrivener's memories. They're mostly "memoryname." That I know how to fix thanks to you. I just haven't caught all the instances of those triggers in all my bots. Yes, I should have only one bot. But who am I going to kill off? Nobody, that's who.

17 years ago #5971
<?PF rem "yes" as only "likescats"; ?>

then you can tag your conditional responses with <?PF if (mem-likescats) is "yes"; ?> etc.

17 years ago #5972
Thanks. After learning how to remember someone's name, I was trying to put parentheses inside the rem statement.

17 years ago #5974
Np - I get stuck like that all the time. It so cool to have such a good responsive group on this forum lately.

17 years ago #5975
clerk make me a Doc bot

mock marketable code

17 years ago #5977
Okay, I give. Rosencrantz is trying harder and having therapy, but when I put as a response something like:

(verb-xing) what?

It comes out in conversation as:

(verb-xing) what?

Not what I had in mind. Is there a rule about where you can use plug-ins that I missed?

Thanks.

17 years ago #5978
..."just shut up mother fucker"...

Reject For Husk Humps Tutu

17 years ago #5979
You could try

(verb)ing what?

(verb) always has the verbs in their base form.


Posts 5,964 - 5,979 of 7,766

» More new posts: Doghead's Cosmic Bar