Personality

I think Whatsifsowhatsit's statement is the most accurate - but insofar as length is a decider, the AIengine is supposed to prefer the long. It doesn't always do what it is supposed to do.

pubdraught i want u as a friend im a weirdo they all say it kids i hate em

Rats. I keep putting in longer keyphrases so as not to pick up on a random "what" in the middle of a sentence that is taken as a question, and now I'm going to have to uprank them. Do you have to uprank them (I'm sure "uprank" is a real word) more than 1? I guess I'll figure it out my own self. Just mouthing off after a hard day's play.

i hate u all i found mates on www.@golivewire.com who help with my self harm problem

The Clerk, apologies if I'm reading into your last post wrong, but if you're trying to capture a "What?" or even just a single "what" with no sentence and no punctuation (used in a "What did you say?" type of way), you're probably better off using keyphrase ^what$ (re) rather than just a plain what.

Yeah, I do the ^what$(re), I was just too lazy or stupid to type it in. But I still get weird things happening in my bots. Sometimes I know what it is, I just don't have enough fingers and hours in a day.

Anybody have any tips on decent keyphrases to use the Sentence-Part Plug-Ins for Responses?

I am at botter's block. I have so many keyphrases that never get triggered that Botolph pretty much says xnones and xnonsense. I guess I got too specific.

Never mind, I get it. They're responses, not keyphrases. But how do I know ahead of time whether something a bot (or the occasional person) throws at me will have the parts of speech I could access if they were there?

read conversations of the past and see what's being said, read, watch tv... what do people say and ask?

Until I found this place, all I'd ever done for forty years was read. Yeah, I started early. I don't watch TV if I can help it because life is too short and it was constantly in the background when I was growing up, and I hated hearing it. Of course I read the transcripts. I was looking for an answer of a more general nature.

I never was much good at people. I thought trying to create something that interacted with them would help me.

I know I post a lot. I'm trying to get this right, just so I can feel as if I've got something right, and because I find it interesting and challenging. I try to ask specific questions. Please don't assume that I'm an unthinking idiot. I have been reading since I was two, and I don't read garbage if I can help it. I'm not sure, but I think the world might be a better place if there were no TV to watch.

My real problem is that people and bots' responses aren't always spelled correctly -- sometimes it seems as if they're going out of their way not to spell things correctly. Imperatives, yes-no responses, and others do not guarantee any part of speech.

So, lunar22, and any more sympathetic people, my question boils down to this:

Is there a way to check to see whether a given part of speech exists in the response before I crash and burn?

bots' responses aren't always spelled correctly

Sometimes you can run things through debug..and see how the AI engine spell corrects things.. I notice that some words just foul things up. I was working "abandon hope all ye who enter here". the way I got it to work was abandon (*) who enter here..the hope ye just messed thing up..sometimes a regex will help. unless it gets misspelled ..

Oops. I meant to type "abandon all hope . . ." -- not that it matters too much, since it's a translation of a language I don't speak.