Anil Seth pushes back on LLM 'pain vector' paper: parsimony says no conscious experience

anilkseth · x · 2026-09-21

Consciousness scientist Anil Seth published a detailed critique of a paper on 'pain representations' in LLMs. He agrees the pain vectors that explain and steer model behavior are interesting—noting they differ from human pain descriptions, with bodily language almost absent—but argues their emergence is exactly what training data predicts and requires no conscious experience. Two core objections: the paper over-credits the possibility of conscious pain (the parsimonious reading is that LLMs don't feel pain, same for the recent 'J-spaces' finding in Claude), and LLM consciousness presupposes computational functionalism, an assumption challenged by Piccinini, Godfrey-Smith and Seth's own 'biological naturalism' paper in Behavioral and Brain Sciences.

Related event: Anil Seth Critiques LLM 'Pain Vector' Paper(4 posts)→

Original post →

More from AGI Musings

AGI Musings channel →