Today we’re 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’s recent paper, “Why think step by step? Reasoning emerges from the locality of experience,” 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’s 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.

🔔 Subscribe to our channel for more great content just like this: https://youtube.com/twimlai?sub_confi...


🗣️ CONNECT WITH US!
===============================
Subscribe to the TWIML AI Podcast: https://twimlai.com/podcast/twimlai/
Join our Slack Community: https://twimlai.com/community/
Subscribe to our newsletter: https://twimlai.com/newsletter/
Want to get in touch? Send us a message: https://twimlai.com/contact/


📖 CHAPTERS
===============================
00:00 - Introduction
04:48 - What is reasoning?
05:10 - Can LLMs reason?
08:55 - Why does chain-of-thought reasoning work?
17:11 - Implications and findings
20:38 - Reasoning in humans
23:20 - Lessons learned
29:05 - Conclusion


🔗 LINKS & RESOURCES
===============================
Why think step by step? Reasoning emerges from the locality of experience - https://arxiv.org/pdf/2304.03843.pdf
STaR: Self-Taught Reasoner - https://arxiv.org/pdf/2203.14465.pdf
Data Distributional Properties Drive Emergent In-Context Learning in Transformers - https://arxiv.org/pdf/2205.05055.pdf


📸 Camera: https://amzn.to/3TQ3zsg
🎙️Microphone: https://amzn.to/3t5zXeV
🚦Lights: https://amzn.to/3TQlX49
🎛️ Audio Interface: https://amzn.to/3TVFAIq
🎚️ Stream Deck: https://amzn.to/3zzm7F5