Principia - Theoretical Model Organism for Alignment (Jin Hwa Lee)

Join us at Principia, an innovative organization dedicated to advancing deep learning theory and enhancing analytical training dynamics for AI safety. 🤖 We aim to develop theory-based hypotheses that can be rigorously tested on AI systems at scale.

In this session, Jin Hwa Lee will present a concise overview of Principia's research vision. Following that, we invite you to engage in a casual Q&A, where Jin will share insights on how their experience at Pivotal influenced their journey to establish a new safety organization. 🗣️💡

🔗 Join us here and be part of this important conversation!