Reproduce “Harm Laundering in GPT Models: Evidence That Gender Discrimination Is Transformed Rather Than Reduced Across Safety-Trained Generations” 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
Sarah Wyer, Sue Black, Noura Al Moubayed
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.