Reproduce “Generative AI User Experience: Developing Human--AI Epistemic Partnership” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Xiaoming Zhai
The authors propose the Human–AI Epistemic Partnership Theory (HAEPT), a framework for examining how people decide what to trust in AI, how thinking is divided, and who is responsible. It describes these expectations as revisable epistemic, agency, and accountability contracts. CLAIS and ArgueAgent illustrate contrasting configurations, but the theory remains unvalidated and the examples do not establish causal effects.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.