I really enjoy using AI character chat for roleplaying, but I’ve noticed that after a while, the AI tends to get stuck in a loop or “tunnel vision.” Here’s what I mean:

Repetitive Content (Too Much Romance/NSFW): When I start a session, everything is fine, but over time, the AI’s focus seems to narrow. For example, if there’s any kind of romantic or NSFW moment in the story, the AI eventually latches onto it. After a while, it feels like the AI shifts to making every single message about romance or NSFW content, no matter what I try to do.

Character Obsession with One Goal: Another example is when a character has a specific goal. Initially, it talks about a few different things, which is great. But over time, it seems to focus entirely on that one goal, no matter what the context of the conversation is. For example, one character I interacted with became fixated on “getting more powerful to take over the world,” to the point where every conversation began with, “But first, I have to get more powerful…” It became its catchphrase and made the interaction feel repetitive.

Does anyone else experience this, or have any tips on how to keep the conversation dynamic and balanced?

  • @enthusiasm_headquartersEnglish
    1•2 months ago

    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.