Episode Details

Today's papers: - Neural posterior estimation of the neutrino direction in IceCube using transformer-encoded normalizing flows on the sphere: https://arxiv.org/abs/2604.19846v1 - Location Not Found: Exposing Implicit Local and Global Biases in Multilingual LLMs: https://arxiv.org/abs/2604.19292v1 - Large Language Models Exhibit Normative Conformity: https://arxiv.org/abs/2604.19301v1 - Design Rules for Extreme-Edge Scientific Computing on AI Engines: https://arxiv.org/abs/2604.19106v1 - Auditing and Controlling AI Agent Actions in Spreadsheets: https://arxiv.org/abs/2604.20070v1 This podcast is from Colin Davis (colin-davis.com) using Claude & Elevenlabs.