Trump sort of sounds like vomit getting caught in your throat after a burp, the Musk is what comes out when you finally hurl.

Yeah if you fiddle around with about:config without knowing exactly what yer doing, shit breaks. Fortunately you can type “about:profiles” in the url box, make a test profile, and mess around as much as you want before nuking your default browser.

I read about this too, and it worries me. Google has donated over a billion dollars to Mozilla over the years. That alone doesn’t scare me so much as it’s a blatant propaganda tool to deflect the antitrust sentiment that plagues them and will probably some day do its work of breaking them apart.

Fortunately, there are numerous open source forks. I am currently using Librewolf, a fork of firefox focused on privacy and anti-tracking, and it has worked without a hitch. A couple of my extensions have required fiddling with to get right but it’s part of life if you care about these things.

NordVPN was found selling user data years ago and it’s dubious that they even provide real VPN services, as they are not open source. They are part of a large conglomerate of corporate VPNs and shouldn’t be trusted. It’s a shame so many social media influencers accept their money from promotions.

I use Airvpn, a non-profit run by hacktivists out of Italy and have been for years. I have not been having technical problems with perchance tools due to VPN, though I am not permitted to join chat boards or start an account on perchance while on my vpn. Kind of a shame but I can live with it.

NordVPN not a true VPN. They got in trouble some years back for leaking (or selling) user data. Use protonvpn, airvpn, or mullvad. :)

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 /.

deleted by creator

deleted by creator

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.

deleted by creator

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 <instructions> 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.