Reproduce “Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training” 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
Lue Tao, Lei Feng, Jinfeng Yi, Sheng-Jun Huang, Songcan Chen
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.