Alex Mallen

Alex Mallen is a member of technical staff at Redwood Research, a nonprofit AI safety and security research organization, where he works on AI control, monitoring, and interpretability. He previously conducted research on language model interpretability and alignment at EleutherAI and at the University of Washington's H2 Lab. He is known for research and writing on reward hacking, AI control, deceptive alignment, and score-seeking behavior in AI systems, as well as co-authoring work on representation engineering and eliciting latent knowledge.