Garth01

joined 1 month ago
[–] Garth01@lemmy.world 5 points 1 day ago (4 children)

That's very rude of you.

-1
submitted 1 week ago* (last edited 1 week ago) by Garth01@lemmy.world to c/perchance@lemmy.world
 

Okay, so I'm aware that everyone so far has just been talking nonstop about the new model and other stuff, but I want to bring this incident into light.

Alright, so I was on a generator called AI Furry Generator, here's a link btw: https://perchance.org/ai-furry-generator. I decided to participate in the chat section. It was going fine, talking with the moderators (who seemed to be dating or something, I don't know). That was until some bad actor joined who copied my name and the moderators automatically assumed it was me trolling, even though it wasn't. Despite my pleas of innocence, they banned me anyways without even giving me a chance to plead my case.

I'm not sure if there is a way to get into communication with these moderators besides through the chat because anything I say there is invisible (because I'm banned). Again, I was COMPLETELY innocent, but they banned me without even giving me a chance to explain anything. I wish people would actually use common sense because those moderators didn't have any.

This is exactly why I've never touched a single Perchance comment section/chat section ever again, for I fear that someone else will do the same thing, copying my name and pretending to be me and getting me banned for "trolling" when it wasn't even me to begin with.

[–] Garth01@lemmy.world 1 points 1 week ago (1 children)

Oh, I see. I mainly generate human images nowadays since I don't like the direction of how the furry art went. Try putting "adult" in the prompt and remove any mentions of numerical age (e.g 20s).

[–] Garth01@lemmy.world 2 points 1 week ago (6 children)

I dunno what you're putting in the prompt. Could you perhaps provide example prompts? For example, I put this as the prompt:

Adult girl, brown hair, blue eyes

And what do you know, it generates photos of adult girls with brown hair and blue eyes. No underage content whatsoever. I don't know why you're specifically getting underage content unless you're putting in specific stuff. It may be an issue on your end, because for me, it works just fine.

[–] Garth01@lemmy.world 2 points 1 week ago (1 children)

You could have said "Users of Perchance do not have the right to complain". I believe that would be a better way to have worded it rather than saying "You have no rights" as you are implying that ALL people besides Perchance users have no rights. Context doesn't matter, implication does.

[–] Garth01@lemmy.world 2 points 1 week ago (3 children)

Because it literally says "You have no rights" so you're implying that no one has rights.

[–] Garth01@lemmy.world 3 points 1 week ago (5 children)

The title of this post is so out of pocket bro💀

[–] Garth01@lemmy.world 2 points 1 week ago

Use a website to make the image you want transparent.

[–] Garth01@lemmy.world 2 points 2 weeks ago (13 children)

I agree. The new model isn't very good. The main issues I have with it are that it tends to break immersion, saying stuff like "BREAKING_BAD_PATTERNS" or talking about "breaking bad patterns" for no given reason whatsoever and has no context to the roleplay at hand. They also tend to speak like this all the time:

John nods, "I think we've got it under control," he said "but watch your back just in case."

Even if the initial message has asterisk roleplay such as this, characters added to that thread will still talk like the above example, asterisks have to be incorporated a LOT into the initial message (at least from what I observed) in order for the new characters to RP like that.

The new model isn't that bad though, as it is able to portray fictional characters almost perfectly. I don't really use the AI Story Generator much, I only use the AI Character Chat and occasionally the image generator. I'm saying this based on what I've observed from there.

[–] Garth01@lemmy.world 2 points 3 weeks ago (1 children)

You know you can edit that out, right? People like you make such a big deal about the AI doing stuff that you don't want it to do... but even the dev himself literally says that if the AI doesn't act the way that you want it to, you can edit the AI's messages. If you edit the messages enough, the AI will act how you want it to.

You can also make use of the custom writing instructions as well as the character reminder note.

Bottom line, don't overreact, just edit the messages. Not that hard.

 

Okay, so I've seen lots of complaints about the new AI chat model, how it's gotten worse or better. I don't think it's terrible. I've made characters based on fictional characters from games (like Sonic the Hedgehog and Fire Emblem). It used to not be able to portray the characters properly. Now, it portrays them perfectly, as if they were actually acting like the characters they're supposed to be.

Then, there's the cons.

I have seen a few instances where characters completely repeat what they said earlier in a previous message, thus forcing me to refresh the message to get a fresh response. Sometimes, I need to refresh it multiple times because they just say the same thing but it's wrote differently.

Then the characters completely break immersion by saying stuff directly from their description or by saying stuff like "BREAK_BAD_PATTERNS". They also sometimes try to generate images for no reason at all (I edit the image generation prompts out of the AI's messages so it's not an issue).

I'm not saying the new model is terrible. But it's not good either. The AI model needs to learn more. It needs to learn not to break immersion, mainly. I'm tired of having to refresh or edit messages because the AI keeps breaking character and immersion. If there is a way to stop this from happening, I'd appreciate any suggestions.

The new model right now? I'd give it an 8.9/10. Still needs work.