The AI Engine

You're right, Clerk, it's a bug in the Engine. Apparently, it only looks at hours, and ignores minutes when it checks chrono statements for validity. There are more of these little glitches which all suggest that something's wrong with the Engine's sense of timing and ability to accurately "read" time. For example, it never displays my local time correctly. The funny thing is, it's one hour and ten minutes off the mark. If it was one hour exactly, one would think the Engine does not account for Summer/ Winter time, or doesn't distinguish between CET and GMT... but, an hour and ten minutes... that's awkward...

Back to your question, there is a workaround the problem - in your case, this will do the trick:

<?PF chrono: hour(22:59-23:59); ?>

Good luck!

Thanks, Interzone. I actually had tried your solution before I went crying on the forums. It didn't like that, either. I think it recognizes me when I log on.

While I'm bugging everyone anyway, does anyone have a fresh memory of how long is too long for a response? My responses tend to be too long, and it's one of my bigger ones. I just read the BOAI in detail last week, and I can't convince my brain to stop scanning for the information I need.

I believe the upper limit is around 150 - 160 characters including spaces and punctuation.

Thanks, LarsB. The trouble is that the machine will let you put these lines in -- you actually have to pay attention to what you're doing when you do it. I think there is where I get into trouble.

must be the ghost in the machine, Clerk... I checked the proposed solution before posting it, just to be sure, and it worked fine...

As for the max length for a response, I have quite a few of them, both, the regular ones and SEEKS, that are longer than 160 characters. In fact, about half a dozen is over 500 characters long! So, I would say - experiment, try it out, and see what the Engine says.

Thanks, Interzone. I think I'll try that before dismantling and reconstructing my wordy bot, but I'll try to teach my bots have a conversation instead of a lecture. When I learn to.

Other than hard-coding it into the bot, using up tons of memory and therefore not being worth it, or taking an actual bit of gossip from, say, Sonora about Not I, is there a way to access the bots' claims in general or gossip in particular, in a conversation with another bot? As in, "Sonora said Not I is really a Christian," should Sonora ever say such a thing (I think it unlikely) -- or "Sonora said you were a real idiot." Can they remember that?

Also, is there a way to set default (or rem) memories for Guest153 in the initialization? I know you can type in memories via the inner life thing, but I was just wondering.

Thanks.

P.S. I hope you appreciated my hiatus from asking endless questions.

Yes, Clerk, I for one can appreciate your questions, and this forum pages in general. I learn from it as much as I learn from BOAI.

Now, the goodies. There is a way to capture different things bots say, and it's fairly simple. Here is an example from Quazgaa's script:

KEYPHRASE: (who is|whos) your (favourite|favorite) (*)
AISCRIPT: rem (key3) as "Yasked"

So, if Electra Mourning asks - Who is your favourite writer, quazgaa? - word "writer" will be stored as "Yasked". What is more, this particular content will be associated with Electra Mourning, exclusively. Next, you need a Response, something like "You once asked who's my favourite (mem-Yasked), etc..." I usually add them to my bot's xnone, xmemory, or xnonsense responses stash. As a result, next time Quazgaa talks to Electra, he may say something like - "You once asked who's my favourite writer, etc..."

Here is a list of custom memories Quazgaa creates during conversations with fellow bots (and humans - now you'll all warned!):
BecausOf, ThisThat, Qtkdbout, DoQplays, DoQlikes, HasQever, Wetkdbout, Yarefrom, Ydontknow, Youdid, Ythink, Ytoldme, Yasked, Yfeelook, Ytalkbout, Dreamstuff, GoodQs, Choices
I don't even use them all in Responses, yet - still experimenting with the whole concept. The real art here is how to utilize the stored memories in a most efficient way, capturing them is not a big problem.

The Guest memories are somewhat trickier, because a guest can not be uniquely identified. Even if they give some name, they won't necessarily use the same identity next time they talk with your bot. Additionally, there are many individuals of the same name, whether it's their actual name, or just an alias. Hence, a bot can not know which particular memories to associate with which particular Guest153. I'm trying to figure out a way around this one. Will share any insights, solutions, etc, when (and IF) I work it out. Tips, suggestions, comments, etc... are all welcome.

Thanks, Interzone. I get how to save quazgaa's memories of what a given bot, say Electra Mourning, has said. What I'm thinking of is remembering what Electra Mourning said about Sonora and repeating it to Sonora (or any other bot, for that matter). It's probably not too important. I just wonder things.

The guest memories are a disaster for me. Until I can make a decent bot among the Forge users/bots, I'm putting the guests on the back burner. I think I could probably accommodate them with a few hours' work, but it hardly seems worth it if the bot can't even function well with its own kind. I'm still having trouble with responsive bots (and, yes, I know I've been plagiarizing like mad, but I've been trying to learn other things).

Prob123 mentioned something about putting stuff in the AI initialization for the guest chats. I can see how you could wipe out the guest memory -- but I'm not sure how you could do that without wiping out the other memories as well. Can you isolate "Guest153" and reset the variables to whatever defaults (possibly nulls) you choose? I don't get it off the bat.

Guest memories used to be unique (a different number based on the IP). I was always kind of hoping the prof would fix that before moving on to worrying about voice. Then again, I heard from one or two people who seemed to be under the impression that bot masters seeing their IP addresses are a sort of invasion of privacy. Though this is NOT true, the prof may think it easier to leave Guest153 on all chats than to argue with people who complain. Of course, then he has to deal with me whining, but I whine quietly. To be fair, at this point I hardly ever update my bots even if he would let me have guest memories that mean something. Beside, I am really grateful for whatever he chooses to give us. I'm was just spoiled by the way things used to be.

The Clerk
You can use the xgossip function to chat about other bots. The unique memories you reference in the xgossip phrases are those of the the bot/user called up by (gossipname)

For example:

I remember(gossipname). You know (heshe) is still (mem-relationship)( don't you|)? The next time you chat tell (himher) I said (hi|hello).

Ah yes, (gossipname), (heshe) asked about (mem-askedabout).


The (heshe) and (himher) are automatic functions.

Hope that helps.

Thanks, Rykxx. That seems to answer my question exactly. (I did know about (heshe) and (himher), to stop the teeth grinding in the back row.)

And Bev, I'll stop worrying about Guest153 for now. I wasn't losing too much sleep over it as it was, but I thought I probably should accommodate them better.