This is a known “bug” that was seen for long, even from the times of Llama, and one of the reasons why Llama was axed as it did exactly this but more often that the current model. The current one still does it, at the time of release it was rare, but I guess it has become often after several updates. I still find it rare, but the most characters I had at the same time in the current model was five and I find this a rare occurrence, but that is my own experience.

There is a way to dampen this though, which worked in Llama partially. Keep in mind, this is just a “dampen”, as I suspect that due to the way LLMs work, every model in existence would fall to this.

When writing the descriptions of the characters, use three dashes (—) to separate each character. For example:

---
# Character A
<Your description here>
---
# Character B
<Your description here>
---
# Character C
<Your description here>

This is not a fix, but should help it making more rare. Hope this helps though.

More context, or example could be better to see whats wrong and what the AI is being confused with. Hopefully the 3 characters you have arent 2000 word essays each right ?

As the way i format stuff for the overview, the AI doesnt seem to have issues with identifying who is who, but i also write with way more grounded expectations that with the tiny token window of Perchance. And its not even that different from what you have, only slightly more…meta.

And so on, this can extend to other characters, but again, i dont try to write essays on theology and philosophy with them.