Jack Clark

website Personal website

core OpenAI core Anthropic

Alignment and RLHF Collective Constitutional AI: Aligning a Language Model with Public Input Alignment and RLHF Constitutional AI: Harmlessness from AI Feedback Alignment and Safety Constitutional Classifiers++: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming Large Language Models Language Models are Few-Shot Learners Alignment and Safety Many-shot Jailbreaking Alignment and Safety Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training Alignment and RLHF Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback