Open-source LLMs administer maximum electric shocks in a Milgram-like obedience experiment

By Roland Pihlakas and Jan Llenzl DagohoyThis post is a slightly updated copy of our Arxiv preprint available at https://arxiv.org/abs/2605.21401 . The tables are converted to images in order to preserve cell background colours. All citations have inline links attached for readers' convenience.With this post, we are looking for external collaborators, ideas, questions, resource suggestions, feedback, and any other thoughts.AbstractLarge language models (LLMs) are increasingly deployed as autonom...