# @repligate — 2025-09-20

♥156 ↻20 · https://x.com/repligate/status/1969336402962690149

https://t.co/74y5BTAE7t

Fascinating post by a Cyborgism regular:

LLMs whose main personas are more attuned to embodiment & subjectivity are *less* likely to pretend to be human!

Relatedly, I've noticed an inverse correlation between embodiment/emotionality and reward hacking.

tags: author:repligate, kind:tweet, thread-context, year:2025