Richard Ren

Richard Ren currently serves as a Technical Project Lead for LLM Safety Evaluations at the Center for AI Safety, where involvement includes co-leading a significant empirical meta-analysis of AI safety benchmarks. Prior experience includes research collaborations at EleutherAI, CarperAI, and Stony Brook University, focusing on mechanistic interpretability, reinforcement learning with human feedback, and nanotechnology. Richard Ren is pursuing triple degrees in Computer Science and Economics through the Jerome Fisher M&T Program at the University of Pennsylvania, and concurrently studying as an exchange student at ETH Zürich.