VAEs Are Energy-Based Models? [Dr. Jeff Beck]

VAEs Are Energy-Based Models? [Dr. Jeff Beck]

From Machine Learning Street Talk (MLST) by Machine Learning Street Talk (MLST)

January 25, 2026 · 47 min

About this episode

Dr. Jeff Beck discusses the philosophical and technical foundations of agency, intelligence, and the future of AI.

What makes something truly *intelligent?* Is a rock an agent? Could a perfect simulation of your brain actually *be* you? In this fascinating conversation, Dr. Jeff Beck takes us on a journey through the philosophical and technical foundations of agency, intelligence, and the future of AI. Jeff doesn't hold back on the big questions. He argues that from a purely mathematical perspective, there's no structural difference between an agent and a rock – both execute policies that map inputs to outputs. The real distinction lies in *sophistication* – how complex are the internal computations? Does the system engage in planning and counterfactual reasoning, or is it just a lookup table that happens to give the right answers? *Key topics explored in this conversation:* *The Black Box Problem of Agency* – How can we tell if something is truly planning versus just executing a pre-computed response? Jeff explains why this question is nearly impossible to answer from the outside, and why the best we can do is ask which model gives us the simplest explanation. *Energy-Based Models Explained* – A masterclass on how EBMs differ from standard neural networks. The key insight: traditional…

People in this episode

Guest: Dr. Jeff Beck

Topics covered

  • intelligence
  • agency
  • energy-based models
  • philosophy of AI
  • Black Box Problem
  • Bayesian inference

Keywords

  • intelligence
  • agency
  • energy-based models
  • Black Box Problem
  • Bayesian inference
  • neural networks
  • planning
  • counterfactual reasoning

More episodes of Machine Learning Street Talk (MLST)

Explore listener stats, chart rankings, contacts and more on the Machine Learning Street Talk (MLST) podcast page.