Where is the Mind? Persona Vectors and LLM Individuation
Quick summary
arXiv:2604.17031v3 Announce Type: replace-cross Abstract: The individuation problem for large language models asks which entities associated with them, if any, should be identified as minds. We approach this problem through mechanistic interpretability, engaging in particular with recent empirical work on persona vectors, persona space, and emergent misalignment. We argue that three views are the strongest candidates: the virtual instance view and two new views we introduce, the (virtual) instance-persona view and the model-persona view. First, we argue for the virtual instance view on the gro
Key takeaways
- arXiv:2604.17031v3 Announce Type: replace-cross Abstract: The individuation problem for large language models asks which entities associated with them, if any, should be identified as minds.
- We approach this problem through mechanistic interpretability, engaging in particular with recent empirical work on persona vectors, persona space, and emergent misalignment.
- We argue that three views are the strongest candidates: the virtual instance view and two new views we introduce, the (virtual) instance-persona view and the model-persona view.
Why it matters
This model development creates a new option for users and a new testing obligation for developers. A fixed evaluation set comparing quality, cost and failure behavior is more useful than launch claims.
Member comments