SAIN Amsterdam Discussion Group: Super Co-Alignment

🤖 AI Safety Discussion Group 📍 Location: Oerknal, Science Park, UvA🕠 Time: 5:30 PM Discussion topic: Super Co-alignment of Human and AI for Sustainable Symbiotic Society We'll discuss a recent paper on the "superalignment": how will we ensure AI systems which are much smarter, remain aligned with compatible intentions and values? The paper introduces a concrete framework for "super co-alignment", emphasising co-shaped and co-evolved symbolic values between humans and AGI/ASI read it here: https://arxiv.org/html/2504.17404v5 💬 Potential Discussion points: Everyone is welcome, whether you're deeply involved in AI safety or simply curious about the topic!