Reproduce “Homeopathic Learning: Diluting poisoned fine-tuning data can strengthen its effect” 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

Matt Clarke, Jan Dubiński, James Chua, Simon Schrodi, Owain Evans, Alex Cloud

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