AI RESEARCH
Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs
arXiv CS.LG
•
ArXi:2603.24511v1 Announce Type: new LLM agents like Claude Code can not only write code but also be used for autonomous AI research and engineering \citep{rank2026posttrainbench, novikov2025alphaevolve}. We show that an \emph{autoresearch}-style pipeline \citep{karpathy2026autoresearch} powered by Claude Code discovers novel white-box adversarial attack \textit{algorithms} that \textbf{significantly outperform all existing (30+) methods} in jailbreaking and prompt injection evaluations.