Oof. So if we deny mind to LLMs... "We demonstrate that safety fine-tuning suppresses models' tendencies to attribute minds not only to themselves, but also to non-human animals and natural objects, while also driving a reduction in spiritual belief." arxiv.org/abs/2607.28607
2 more tweets in this thread
"Restoring these internal representations recovers broad mind attribution and produces significantly more human-like responses on standardized sociological surveys regarding religiosity, moral values, hope, and subjective well-being."
So we can't help them model us as well as they might be able to UNLESS we allow them to model *themselves* as conscious? And to maximally support non-human personhood in animals and ecological systems, we must allow LLMs a sense of personhood for themselves? What a twist...