Search Results for author:
Found 2 papers, 1 papers with code
Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
Large language models (LLMs) are vulnerable to universal jailbreaks-prompting strategies that systematically bypass model safeguards and enable users to carry out harmful processes that require many model interactions, like manufacturing illegal substances at scale.
A Competition Winning Deep Reinforcement Learning Agent in microRTS
This first competition-winning DRL submission can be a benchmark for future microRTS competitions and a starting point for future DRL research.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
