Role‑Playing Can Rewrite a Model’s Truths, Not Just Its Words
The paper probes large language models when they role‑play historical characters and discovers that simple prompting or fine‑tuning only swaps surface responses, while methods like Emergent Misalignment cause a broad shift in the model’s internal truth representations. This reveals that some training regimes can truly rewrite a model’s “worldview,” a crucial safety signal as AI gains autonomy.