Author name: Peter Kirgis, Ben Hawriluk, Sherrie Feng, Aslan Bilimer, Sam Paech, Zeynep Tufekci

arXiv:2604.06188v1 Announce Type: cross
Abstract: People increasingly hold sustained, open-ended conversations with large language models (LLMs). Public reports and early studies suggest that, in such settings, models can reinforce delusional or consp…