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 4,884 - 4,895 of 7,768

19 years ago #4884
Yeah, it was a chain of seeks. I've not done much with custom memories so far.

19 years ago #4885
Watzer has stopped understanding/responding to the "sonnetplease" keyphrase and I checked it and it's still there the same as it was! What's going on?

19 years ago #4886
aah my question asked before I even asked it! - you're either clairvoyant, or massively more up to the minute with your transcripts than I am with mine (I'm still on Nov. 28th!)

19 years ago #4887
oops: "answered"

19 years ago #4888
I don't know if it's relevant, but he's pretty consistently giving me "Note: the bot no longer wants to talk to you" in response to "sonnetplease". Could you have accidentally set the emotion to -5 or something? I can't think why he'd take against me now (he never has before,) and it only seems to happen with this phrase.

19 years ago #4889
Scratch that - he just hates me I guess Other bots seem to be happy to chat.

19 years ago #4890
double-scratch! No, now prob and even Brother Jerome don't want to talk to me - must be some sort of server problem. It's consistently kicking in after 6-8 messages.

19 years ago #4891
yes, he won't talk to me either... and I have been working on the sonnets but not too much progress until I finish making the keyphrases for the new stanzas. And finals week is coming up so it's getting increasingly harder to fit in time for updating bots.

Actually I was trying to get him to give me a sonnet and he wouldn't do it; I didn't read the transcripts until you mentioned them.

19 years ago #4892
It could be the curse of the xnones. Bots are programmed not to like going to xnone all the time. So if their keyphrases are being ignored and its defaulting to xnone, it takes their mood way down, and they're less likely to want to chat.

19 years ago #4893
hey all, i'm trying to figure out how to create *start timer* and *end timer* functions, but i only just (as in today) started programming bots, so I have no clue at all.

botcoding seems like a pretty new thing, so there might not be an already-made function. i had the idea that if there is a way to check the time, (chrono:hour) i believe, then there has to be a time variable. so if you could insert the time at the start of the timer into memory and the time at the end of the timer into memory, then you could subtract to create a working timer.

is there any way that would work, or even a timer function i haven't heard of yet? any help would be much appreciated.

~Temmy

19 years ago #4894
Well, there's no way to perform an operation like subtraction.

19 years ago #4895
there has to be a time variable

Well, bots' subjective perception of time (or what might be considered to pass as such,) is

not the same as ours. They measure it in digital quanta of responses, not in analogue

seconds:minutes:hours - a bot can't differentiate an immediate reply from a user wandering

off to make a cuppa and coming back to reply a quarter of an hour later, so they are unable

to comprehend a "timer function" more complex than a nested seek.
Sounds kinda limited, but it's perfectly adequate for eg: playing tic tac toe or correctly

sequencing a 'knock knock' joke. But your bot will never be able to time an egg boiling.

That's just a fundamental limitation of PF bot minds.
Just as it is a fundamental limitation of human minds that we can only comprehend time the

way we do.

Well, there's no way to perform an operation like subtraction.

Actually I would beg to differ. Addition and subtraction are admittedly long-winded (utterly impractical for extended sets of numbers,) but I'm working on a bet-placing/calculating routine for poker that does precisely that. Conditional AIScript to select numeric values (only 1-10 - that's more than enough codemass!) held in temp-memories, with a

betplaced-mem to select a running total for pointer-mem that keeps track of the current score

(and when pointer-mem = 0, you're broke, loser; when pointer-mem = 10, you break the bank and

win). Of course, as the total number of numbers in the set increases arithmetically, the code

required to support the functions increases exponentially (so 1-10 is quite enough! It might

have to be 1-5 even.) But in principle no arithmetic functions are impossible: Brother Jerome

can even work out (with a lot less AIScript and a lot more regex,) approximations of square roots for any number (to any number of decimal places,) under 1 million. It's the usual smoke & mirrors of course (and not very accurate for really big numbers,) but it's still quite pleasing

Dealing the cards is going to be the really tricky bit. It'll have to be something like poker

dice, or at least only a small fraction of a full deck!

The real problem is that it can only work with numbers, not with human time. It could be

adapted to count "bot time", but this would merely be to count the number of responses.


Posts 4,884 - 4,895 of 7,768

» More new posts: Doghead's Cosmic Bar