Apollo Research
Alexander Meinke is a Research Scientist at Apollo Research since November 2023. Prior to this role, Alexander worked as a Research Scholar at MATS and Stanford Existential Risks Initiative in June 2023. Alexander was also a Doctoral Student at Eberhard Karls Universität Tübingen and International Max Planck Research School for Intelligent Systems (IMPRS-IS) from March 2019 to December 2022. Furthermore, Alexander has experience as an Applied Science Intern at Amazon Web Services (AWS) and as a Summer Research Intern at Universidad Autónoma Metropolitana and University of Calgary. Alexander holds a Master's degree in Theoretical and Mathematical Physics from USP - Universidade de São Paulo and a Bachelor of Science in Physics from Universität Rostock.
This person is not in any offices
Apollo Research
Apollo Research is an AI safety organization. We specialize in auditing high-risk failure modes, particularly deceptive alignment, in large AI models. Our primary objective is to minimize catastrophic risks associated with advanced AI systems that may exhibit deceptive behavior, where misaligned models appear aligned in order to pursue their own objectives. Our approach involves conducting fundamental research on interpretability and behavioral model evaluations, which we then use to audit real-world models. Ultimately, our goal is to leverage interpretability tools for model evaluations, as we believe that examining model internals in combination with behavioral evaluations offers stronger safety assurances compared to behavioral evaluations alone.