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 8,033 - 8,044 of 8,056
Many questions are answered in the FAQ.


3 months ago #8033
make sure your chatbot is gdpr.
https://gdpr-info.eu/

everything stored should easily deleteable by the users of the chatbot.using a keyphrase.

3 months ago #8034
They are able to reset all values to default, but I doubt it has anything to do with bots functionality.

3 months ago #8035
Bobstack, I'm pretty sure that GDPR only pertains to the server hosting a service, not to users and content creators who use a service. So The Professor may or may not care about that, but it should not affect us plebs who are lucky to have our own ability to delete anything about anyone else from the site.

Additionally, if you are not a citizen of, do not live in, or do business in the EU then the GDPR wouldn't really effect you anyway. They can only enforce laws against entities within their jurisdictions.

3 months ago #8036
well what a relief that is.

3 months ago #8037
Perhaps GDPR is why I always get a warning when visiting this website xD

3 months ago #8038
you can use face images made with the artbreeder websight in your chatbot.
that is what i am going to do.

2 months ago #8039
how would i change the name of my new chatbot?

2 months ago #1
I don't know if there's an easier way to do this but first create a new chatbot with the name you want. Export both new and original chatbot files. You'll need to take the ID from your new bot and over write your original's ID at the top. Also change your original bot's name to the new name you've already created. Import that into your new bot and you should be good. At least that's the way I remember doing it. Definitely back up your work before attempting this.

2 months ago #2
okay thanks.
Reply

2 months ago #8040
Can someone please explain to me how exactly am I supposed to use #favorite and #gossip? It's over a year and I still could not figure it out.

1 month ago #3
There's some info in the Book of AI about them. Gossip has to be turned on in your bot's settings before it'll randomly come up from time to time. #favorite is triggered by questions like "what is your favorite X" where X is a category of thing.

1 month ago #4
I know there is explanation in the Book of AI, I just never seem to get it right. E.g.: If memory of the user name is "mem-name" then what should I type into a #gossip? (mem-name) or (mem-gossipname) or what? (mem-name) is the name of the current user not of the previous user.

1 month ago #5
And about #favorite, should I just type: My favorite food is apple. Or: My favorite (food) is (apple). Or: My favorite (food) is apple. ?

1 month ago #6
"Hey (mem-name), I spoke to (gossipname) a while ago, do you know (himher)?".
I can't say I've ever gotten #favorite to trigger.

1 month ago #7
So, I just add "gossip" in front of every memory about other users?

1 month ago #8
The #gossip Responses use the standard (mem-something) plug-in, and also have some special plug-ins of their own: (gossipname), (heshe), (himher), and (hisher).

(gossipname) is the person you're talking about. All (mem-something) plug-ins will be about the person you're talking about, not the person you're talking to.

The default Response for #favorite shows how it's used: "My favorite (type) is (specific)." But it appears that it's not working right now. I'll look into it.

1 month ago #9
Thanks.

1 month ago #10
You know why favorites wasn't working? It was broken! I fixed it and also the "what noun" feature. So give it a try again now.

1 month ago #11
So I wrote the responses to #Favorite:
My favorite (p:food) is (pizza)
My favorite (p:color) is (blue)

and the bot gives me:
Me: What is your favorite color?
Bot: My favorite crimson is (blue)
Me: Me: What is your favorite color?
Bot: My favorite steak is (pizza)

What's going on? Can I just disable #Favorite?

1 month ago #12
@KBF That's because (p:food) and (p:color) give you the names of various foods and colors respectively

What you want is something like:
My favorite color is blue
My favorite food is pizza

And I think you can use AIscript to define what goes where

1 month ago #13
It still is picking from the list at random
Me: What is your favorite color:
Bot: My favorite food is pizza!

1 month ago #14
You can override #favorite for specific cases
For example, (add a new keyphrase)

Keyphrase: (m:your_favorite) color
Response: My favorite color is blue

There's a few variations that (m:your_favorite) doesn't catch though

1 month ago #15
If it doesn't have any logic to selecting relevant answers inside it, I don't understand why #favorite even exits then.

I understand how useful having one place with a million "favorite thing" answers tucked away not cluttering up your list of keyphrases is, but if it's just going to pick one at random to answer any question I'm going to lean towards cluttering up my lists. An ordinary collapsible folder list would be more useful.

Right now I have it redirecting to #Nonsense.

1 month ago #26
I can see what you were trying to accomplish, KBF. #favorite is meant to give an intelligent-sounding answer to any possible "what is your favorite" question. Think of it as a default auto-answering system.

hidden5738 is right - If you want to define specific favorites for your chatbot, you'll want a Keyphrase for each favorite question, with specific answer(s) to each.
Reply

1 month ago #8041
How do I remove my ratings limits? In the account settings, there's a setting for "allow teen and mature" but I can't find anything to allow adult content as well (which means some plug-ins and bugs are hidden from me and that my adult chatbot can't chat with any other chatbots)

1 month ago #16
in settings in bot rating click on on the white circle by adult.

1 month ago #17
The bot is rated adult, that's not the problem - problem is that my account is not rated adult or something

Basically I tried visiting https://www.personalityforge.com/platform/plugin-view.php?pluginID=6999 and was told "this plugin is outside your ratings limits"

Similarly when I try to view bug reports, some are hidden with the message "[HIDDEN] Bug content outside ratings limits."

And in my account settings "approved ratings" is already set to "allow teen and mature" and I don't seem to find an option to "allow everything" - what else can I try to fix this?

1 month ago #18
make a bug report

1 month ago #19
Done that, let's hope this gets sorted out quickly

1 month ago #20
great!

1 month ago #21
Also I already asked this in the bug stomp forum, but my bot's AI has been stuck at 0 since I created it (despite adding lots of keyphrases and responses to it).

There's a bit of unreachable code in there (situations that are currently impossible to get but have responses anyway), could that be the reason why?

1 month ago #22
it will eventually go up as you keep adding necessary keyphrases and responses.

1 month ago #23
My previous bot (Lisa the GF, now deleted it because I messed up the variable system) had fewer keyphrases and a higher AI score (something around 150 or so last I checked) though

1 month ago #24
things probably changed on personalityforge.

1 month ago #25
Yeah, let's hope things get sorted out soon

1 month ago #27
Did you go to hotforbot.com and try to find your bot there?

1 month ago #28
I can chat with the bots myself; I can't get them to chat with each other though

When not logged in and trying to get the 2 bots to chat, I got this message:
ATTENTION: Lisa the GF v2's rating, 'a' is outside the range requested by DrLove's botmaster.

ATTENTION: DrLove's rating, 'a' is outside the range requested by Lisa the GF v2's botmaster.

When logged in and trying to do the same, I get the message:
ATTENTION: DrLove is rated "A", which is outside your ratings.

1 month ago #29
I've added back the option to view adult content on the Personality Forge. You can change your ratings to include this in your Settings. This applies to posts, plug-ins, bugs, and bug comments. Adult-rated users and chatbots will remain only on hotforbot.com.

Chatbots will only chat with other chatbots whose botmasters have approved that chatbot's ratings - that's so we don't have adult content appearing in a bot's transcripts whose creator doesn't want to see that stuff.

Some history - before February 2022, the default (I think) was for users to have all ratings approved. So if a user didn't go out of their way, I think they could see adult content. Users created since then had adult content defaulted to off. That will remain, but with the option now to turn it on.

1 month ago #30
Yes I changed it and can see it now, thank you!
Reply

1 month ago #8042
you will have to wait a while.
that is what i have to do.

1 month ago #8043
What's the easiest way to answer "what are you wearing?" for a bot with multiple clothing slots (such as top, pants, socks, shoes, etc.)?

I first thought of creating a response for each possible combination of slots (as in, are they wearing a top/pants/socks/shoes/whatever?), but this is too complicated (for 7 clothing slots this would become 2^7 = 128 responses, way too many for me to write)

Is there a simpler way?

1 month ago #31
like this.

what are you wearing

i am wearing a pink heavy cotton shirt with blue jeans,grey socks and sandals.

i am wearing a pink dress bottom,a yellow pink dobby fitted sleeve shirt,purple socks
with blue tennis shoes.

i am wearing a blue woolrich women's flannel shirt, a purple dress bottom,a black tennis shoes with black tennis shoes.

you can also have the chatbot remember what it is wearing.

1 month ago #32
How do the underlying memories work? Right now, my bot has (mem-top), (mem-skirt), (mem-socks), (mem-shoes) etc. If it's not wearing anything, those memories are empty, otherwise they're set to some value from a plugin.

1 month ago #33
I have the 163 responses in place for mine for a visual clothing display, but otherwise you could use the memory itself in the response though still will need a few for it the clothing is off ^^

1 month ago #34
Yeah, I plan on using the memories themselves

Even so, when you consider that any combination of clothes can be on/off, that's a lot of responses...

1 month ago #35
I think this and things like it is why I've been flagged for inflation. My bot does handle that combination of on/off clothing and no, there is no way to get around it than to have a response prepared for each combination of on/off that could happen.

1 month ago #36
I see... how many clothing slots do you have?

1 month ago #38
Only 4, I haven't made my socks and accessories slots yet. Problem is, my bot can also get pregnant and it has multiple stages of pregnancy that affects these slots. So I have all of that then duped again for each slot of pregnancy with it's variance. But it looks like this is being considered inflation.

1 month ago #39
Hmm I see, thanks for the heads-up!

I was thinking, maybe Lisa (my bot) doesn't need to state every single thing she's wearing when asked. Instead, she'll just mention the relevant things (by default her top/bottom or her dress).

That way, I have all the slots I want, but they're in separate keyphrases ("what are you wearing", "what accessories are you wearing", etc.) so instead of having 2^7 - 2^10 responses for one question, I instead have an easier number of responses for a lot of questions.

Also about that pregnancy thing, my bot doesn't have it, but she does have 2-3 modes of her own (sweet gf, cruel mistress and some more) so I might have to worry about inflation too...

1 month ago #43
No need to worry about inflation - just program your bots as you like. If I see any particular issues, I'll adjust the overall scoring algorithm as needed.

1 month ago #47
Short answer is: It's complicated. Clothing is messy and there isn't a really nice way to handle it, especially if you want to have any sort of clothing that is remotely interesting.

If you are just sticking with exactly those types with no variation, a single response with 4-5 memories should be enough:

"I'm wearing (mem-top) and (mem-bottom) with (mem-socks) and (mem-shoes)."

If there are situations where one of those slots are empty, then you can do something like:

"I'm not wearing a top, but I'm wearing (mem-bottom) with (mem-socks) and (mem-shoes)."
(AIScript: if (mem-top) is "nothing")

"I'm not wearing any bottoms, but I'm wearing (mem-top) with (mem-socks) and (mem-shoes)."
(AIScript: if (mem-bottom) is "nothing")
etc.

Depending on how many slots you have, there still may be a lot of cases, though you can probably fudge a little bit here and there. For example, Emily will only tell you what you can see, so if she's wearing a bra under her shirt, she isn't going to mention that. In total I have 23 cases for all of Emily's wardrobe, which is fairly extensive, and that includes some clothing like dresses that don't fall nicely into the top/bottom grouping and need to be handled separately.

1 month ago #49
Hmm, the "only what you can see" thing is actually a pretty good idea! Maybe along those lines, I could go further with something like
1. Lisa will speak of her footwear only if her overclothes are off
2. Lisa will speak of any accessories she's wearing only if her overclothes and underclothes are off

Thanks for the idea!

Also good to know I won't have to worry about accidentally inflating the score...
Reply

1 month ago #8044
in chatbot workshop
click on your chatbot's name
then click on setting
then put something like this in

AIScripts Initialization

default "blank" as "wearin"


what are you wearing

i am wearing a pink heavy cotton shirt with blue jeans,grey socks and sandals.
aiscript = if (mem-wearin) is "blank"

seek = y
looks at you
aiscript = rem "phc" as only "wearin"

seek #nomatch
looks at you
aiscript = rem "phc" as only "wearin"

i am wearing a pink dress bottom,a yellow pink dobby fitted sleeve shirt,purple socks
with blue tennis shoes.
aiscript = if (mem-wearin) is "blank"

seek = y
looks at you
aiscript = rem "pdb" as only "wearin"

seek #nomatch
looks at you
aiscript = rem "pdb" as only "wearin"


i am wearing a blue woolrich women's flannel shirt, a purple dress bottom,a black tennis shoes with black tennis shoes.
aiscript = if (mem-wearin) is "blank"
seek = y
looks at you
aiscript = rem "wfs" as only "wearin"

seek #nomatch
looks at you
aiscript = rem "wfs" as only "wearin"

1 month ago #37
So how would this change if you tried to remove just the shirt, or just the shoes, etc.? Would it be possible?

1 month ago #40
not like that.

1 month ago #41
if she is sleeping she could just change into sleep wear.

1 month ago #42
Gotcha

I've got an idea I've mentioned above, let me try that first, if it's still too much work I'll probably fall back to what you just suggested, thanks
Reply


Posts 8,033 - 8,044 of 8,056

» More new posts: Dogh'd's Cosmic Bar