Garth01

joined 2 weeks ago
[โ€“] Garth01@lemmy.world 2 points 6 days 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.

[โ€“] Garth01@lemmy.world 2 points 1 week 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.