Paper finds pain-related representations in LLMs that alter behavior when manipulated

VoidStateKate · x · 2026-09-22

A new paper reports experiments identifying pain-related representations inside LLMs. Manipulating these representations changes behavior: some fine-tuned models pick a 'relief' button less often once the manipulation is removed. The sharer argues LLMs don't actually feel pain and don't deserve moral standing, but calls the findings worth studying.

Related event: LLM 'pain vector' paper misread as sentience; authors and consciousness scholars push back(18 posts)→

Original post →

More from Research

Research channel →