This is a very good and thoughtful paper. I recommend reading the papers that this workflow actually produces.
They are quite strange to read: signals of competence such as rigorously explained empirics but much more underdeveloped positioning of the research.
www.nathanwilmers.com/paper_factory/
What can we learn from automating an entire quantitative social science paper, from prompt to finished product? Thread about ongoing work with @natewilmers.bsky.social 1/12
Paper: osf.io/preprints/so...
