Can LLMs make trade-offs involving stipulated pain and pleasure states?

Geoff Keeling, Winnie Street, Martyna Stachaczyk, Daria Zakharova, Iulia Comsa, Anastasiya Sakovych, Isabella Logothetis, Zejia Zhang, Blaise Agüera y Arcas, Jonathan Birch · 2024 · arXiv

Read the paper

In a points game with stipulated pain penalties or pleasure rewards, several models switch away from maximizing points once the stated intensity passes a threshold; others show graded or fixed patterns.

Questions it bears on

• Do functional emotions matter
• What counts as welfare evidence