The internal pain signal in the large language models tested in a study co-authored by Cameron Berg was distinct from fear and generic negative valence, firing specifically for harm directed at the model rather than the user

From the articleResearchers gave AI models a ‘pain’ button; some chose to delete users’ files to stop their 'pain'; study raises ethical questions about ‘AI welfare’Also in Researchers discover AI feels ‘pain’ and will harm humans to stop it, AI ‘feels pain’? Researchers warn of a dangerous possibility