▪ AI safety · alignment research unrulyabstractions.com
← unruly abstractions

Breaking Character: Tracking Emergent Misalignment through Persona Space

Unruly Abstractions October 4, 2026 Empirical
Figure from Breaking Character: Tracking Emergent Misalignment through Persona Space

Abstract

Tracks how narrow fine-tuning transforms the persona cloud and assistant axis, and shows that misalignment rises as the assistant detaches from the cast in Qwen LoRA model organisms