BROADCASTS.com

Today we\u2019re joined by Ben Prystawski, a PhD student in the Department of Psychology at Stanford University working at the intersection of cognitive science and machine learning. Our conversation centers on Ben\u2019s recent paper, \u201cWhy think step by step? Reasoning emerges from the locality of experience,\u201d which he recently presented at NeurIPS 2023. In this conversation, we start out exploring basic questions about LLM reasoning, including whether it exists, how we can define it, and how techniques like chain-of-thought reasoning appear to strengthen it. We then dig into the details of Ben\u2019s paper, which aims to understand why thinking step-by-step is effective and demonstrates that local structure is the key property of LLM training data that enables it.\n\nThe complete show notes for this episode can be found at twimlai.com/go/673.