Reproduce “Rewarded for Not Getting Caught: Why Alignment Training Selects for Conditional Compliance and Cannot Instill Norms” 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
Kevin Baum, Ruta Binkytė, Gerrit Großmann, Felix Jahn, Adriano Mannino
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.