Source record

Published by arXiv cs.HC (T1 source). The original is at https://arxiv.org/abs/2610.33301.

Pipeline notes

The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.

A multi-agent system called the As-If Machine helps users co-write first-person counterfactual narratives about policy risks. Two pre-registered experiments found that these narratives increased psychological closeness more than expert vignettes or unrelated co-writing, with effects on policy attitudes varying by domain.

Documents a concrete human-AI role split: the system supplies situated detail while people supply perspective and emotion, supported by large pre-registered studies.

Cited by

No citations on record.