Newcomers

This is a forum for newcomers to the Personality Forge. Many questions can be answered by reading the Book of AI and the FAQ under the "My Bots" link in the upper corner.

Posts 3,439 - 3,450 of 8,130
Many questions are answered in the FAQ.


19 years ago #3439
Hey, 10 minutes later same results. ...Go figure
Guest167: Hi it's me again..my name is problem
Bildgesmythe: Ok, problem you are good ole problem!
Guest167: how old am i
Bildgesmythe: Wow,, you are old. Just about 222

161.184.204.167
Apr 25, 2006 • • Edit
name: problem
yourage: 222

Maybe it goes by the IP address ???

19 years ago #3440
Ummh... yea... whatever I can figure out - will happen to be in my memory. Thanks

19 years ago #3441
I think it may last 24 hours or untill the next guest 167 comes along
Bildgesmythe: (to Guest167) Get a new car for your spouse. It'll be a great trade!
Guest167: bad joke
Bildgesmythe: Did you hear about the guy with a map of Canada tattooed on his butt? Every time he sits down, Quebec separates.
Guest167: what is my name
Bildgesmythe: problem did you get a blow to the head, should I call a healer to help you?
Guest167: how old am I
Bildgesmythe: Gee,, you are old enough to figure it out yourself. Just about 222

19 years ago #3442
hmm - I'm surprised. Maybe it's until the next guest comes along with a different IP?

19 years ago #3443
I just went through the Chatterbox Challenge link and same thing

Guest167: hi remember me
Bildgesmythe: Glad to see you problem. I am so glad you stopped by.
Guest167: how old am I
Bildgesmythe: You were born in, and you don't know how old you are?.... Just about 222

Maybe it lasts untill the next three chatters knock it off the last three guest chat list?


19 years ago #3444
The ratings are a puzzle. I have two bots with almost excatly the same number of lines, one is rated Dev:184 and the other is rated Dev:80. And the lower rated one has more AI, more levels of Seek, and some very complex (comparatively) coding. So why is the "smart" one rated half the other?

19 years ago #3445
(to psimagus)
in raw mode:
[b][o]([t]+)[o][m] [l][e][f][t] (re)
[b][o]([t]+)[o][m] [r][i][g][h][t] (re)
[b][o]([t]+)[o][m] [m][i]([d]+)[l][e] (re)
----------------------------------
YES! It worked! Holy crap that was complicated! For future reference, that seems to be the only way to override xinsult with a seek. This needs to be published somewhere on the site for other people who run into this problem.

19 years ago #3446
It's a useful regex blunderbuss approach when the AI Engine won't behave. But they can get a LOT more complicated than that, believe me!

19 years ago #3447
MickMcA: The 'dev' level doesn't just reflect the number of lines in your bot, and some things (such as adding a keyphrase with only one response) can actually LOWER your dev level. The exact formula is known only to the Prof.

19 years ago #3448
That's a myth, easily verifiable. What happens when you add a keyphrase with only one response is that it'll only add a small fraction of a point to the Development score. What'll lower it is AI scripts and possibly seeks (I haven't been able to nail down whether the seeks do it).

I suspect it has something to do with these features being newer additions to the engine (well, relatively newer) and maybe the Dev score wasn't considered at the time.

19 years ago #3449
Except for seeks with only one response, I've found that AIScript and Seeks raise the development. Perhaps there's an element of randomness in the Professor's secret formula.

19 years ago #3450
The puzzle is worse than I expected.

Let me offer a possiblity to consider. There are two ways to program a bot, what I call brute force (anticipate every KeyPhrase, at its most "primitive") and what I would call "elegant" (guess where my sympathies lie...), which attempts to build a rule that captures as many true positives as possible. Is it possible that the Dev score is weighted toward brute force?

Just thinking out loud.
M
BTW: Pocque has been mainly built by brute force, and my other bot, with the same number of lines, is heavily weighted the other way, but rated at 1/3 of Pocque's "development."


Posts 3,439 - 3,450 of 8,130

» More new posts: Doghead's Cosmic Bar