Reproduce “Reasoning as a Weapon: Adaptive Dual-Path Jailbreak Attack on Large Language Models” 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
Shi Lin, Peng Qian, Hongming Yang, Renjie Sun, Dezhang Kong, Xun Wang
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.