Reproduce “Automated Adversarial Discovery for Safety Classifiers” 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

Yash Kumar Lal, Preethi Lahoti, Aradhana Sinha, Yao Qin, Ananth Balashankar

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.