enthusiasm_headquarters

dot-producting the arrays

It took me a while to figure out that the AI does not understand how to match pronoun with its subject. Too-many-fingers aberrations would happen in the text where character genders would suddenly morph or they would transport magically to replace the actions of another person. It's kind of an annoying problem.

I’ve noticed this too. It also uses the same turns of phrase across many characters, which makes me think the conversational training data is somewhat limited. One thing you can do is a “nuclear” option. I was testing the Strict GM default character on a sci-fi adventure, and the AI became obsessed with putting my party in these crystal caves.

Everything became about the caves. The caves would start to feel my words and resonate with all the action. I manually edited out the caves from all of the previous replies, then just dropped in a relevant subject in the last of its replies.

So in your case, remove everything from its last reply and just put "What is it about video games that you enjoy?" and this will nudge it in the right direction. The AI seems to randomly draw from lore, its description, reminders, and recent QA without any logic to which is most important.

As an example, in a recent chat I accidentally ended a sentence with "/" instead of ".", two replies later AI ended its sentence with /.

It's just a thing. There's a few things you can do to help keep characters somewhat more intelligible. I don't know what you've done/tried yet, though.

Who downvoted me saying I loved the dev. That's not very nice.

Hmm, perhaps I spoke too soon. I put the custom code in the character's custom code section. I reloaded the chat tab. Then typed /print in the chat field. It gave me an "Executing custom code" status for a few seconds, but nothing happened. All I have on this browser is Ublock Origin, would that mess it up maybe?

It's a problem with the philosophy of open communities that can only be solved with worse problems, I'm afraid, and I'm speaking as a former moderator, for over 5 years, of a game channel with 10,000+ users in it at any one time.

I don't use perchance's chat feature, but I'm certain you could figure a way to import your own chat frame into the generator. For example, start an IRC channel and import it in, with you and trusted users as the ops, and then ban the IPs of the gross people/Trump supporters/pedophiles.

VioneT, this is exactly what I wanted, thank you so much!

I would just like to take this moment to say how much I love you.

So I created a lemmy account (this is cool, I hate corporate social media, but this is cool) just to post about this. Since your topic was right smack at the top of the forum I figure I won't waste space posting the same thing.

I have a couple very long conversations using the https://perchance.org/ai-character-chat interface, which seems to be the most feature-rich and interesting of the AI text tools on perchance. Thus far I've got about 10mb of text across a few sessions, and like you I've struggled to figure out why the hell the AI gets stuck on itself.

**I'll just list things that I've tried: **

• Using [AI:] and (AI: ) and to be explicit about not using certain words. I've tried many different combinations of these just to see if it helps. You've probably noticed the AI can adopt very quirky and sudden idiosyncrasies for no apparent reason.

• Editing the AI character (evoked with /ai by default) to include banlists of overly used (by that I mean almost every reply) words, often completely nonsensical in their context.

• Including a simple reply instruction, the small field that is auto-inserted before every AI reply, with something like [AI:](Reminder: Do not in any way say, use, write ... with the words X, Y, or Z.)

• Lore. I've tried both including same word blocks in lore txt uploads and in the /lore feature.

• /mem I have gone through the AI mem file and manually deleted every single instance of a word or two I want never to appear on the hunch that it was "reinforcing" itself as above user rightly identifies.

My chats have become infected with "hope" and "pride." The characters are proud of basically everything. I have nothing against either hope or pride in general, but it's maddening. Sometimes the instructions seem to have an effect, but inevitably this happens:

Muggles feels a sense of, not quite pride, she knows she can't be proud, but something a lot like pride, a warm sort of connection that resembles pride.

I almost think the AI is messing with me. I think a simple bandaid would be to allow a hard blocklist feature. I've also tried using the (negative:::) feature used in image making, but this seems to have zero effect.