Apollo Research
Marius Hobbhahn is a Director and Co-founder at Apollo Research, where Marius is currently involved in starting a new technical AI safety organization based in London. Prior to this, Marius worked as a Research Fellow at Epoch, conducting analysis on important trends in AI and building quantitative models for AI forecasting. In addition, Marius has experience in independent AI safety research, working on various projects. Marius holds a PhD in Machine Learning, a Master of Science in Machine Learning, and Bachelor's degrees in Computer Science and Cognitive Science from the University of Tübingen.
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.