Machine Learning Street Talk (MLST)

Machine Learning Street Talk (MLST)
  • 4.6 (95)
  • TECHNOLOGY
  • UPDATED DAILY

Welcome! We engage in fascinating discussions with pre-eminent figures in the AI field. Our flagship show covers current affairs in AI, cognitive science, neuroscience and philosophy of mind with in-depth analysis. Our approach is unrivalled in terms of scope and rigour – we believe in intellectual diversity in AI, and we touch on all of the main ideas in the field with the hype surgically removed. MLST is run by Tim Scarfe, Ph.D (https://www.linkedin.com/in/ecsquizor/) and features regular appearances from MIT Doctor of Philosophy Keith Duggar (https://www.linkedin.com/in/dr-keith-duggar/).

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

    JAN 25

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

    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 networks only optimize weights, while energy-based models optimize *both* weights and internal states – a subtle but profound distinction that connects to Bayesian inference. *Why Your Brain Might Have Evolved from Your Nose* – One of the most surprising moments in the conversation. Jeff proposes that the complex, non-smooth nature of olfactory space may have driven the evolution of our associative cortex and planning abilities. *The JEPA Revolution* – A deep dive into Yann LeCun's Joint Embedding Prediction Architecture and why learning in latent space (rather than predicting every pixel) might be the key to more robust AI representations. *AI Safety Without Skynet Fears* – Jeff takes a refreshingly grounded stance on AI risk. He's less worried about rogue superintelligences and more concerned about humans becoming "reward function selectors" – couch potatoes who just approve or reject AI outputs. His proposed solution? Use inverse reinforcement learning to derive AI goals from observed human behavior, then make *small* perturbations rather than naive commands like "end world hunger." Whether you're interested in the philosophy of mind, the technical details of modern machine learning, or just want to understand what makes intelligence *tick,* this conversation delivers insights you won't find anywhere else. --- TIMESTAMPS: 00:00:00 Geometric Deep Learning & Physical Symmetries 00:00:56 Defining Agency: From Rocks to Planning 00:05:25 The Black Box Problem & Counterfactuals 00:08:45 Simulated Agency vs. Physical Reality 00:12:55 Energy-Based Models & Test-Time Training 00:17:30 Bayesian Inference & Free Energy 00:20:07 JEPA, Latent Space, & Non-Contrastive Learning 00:27:07 Evolution of Intelligence & Modular Brains 00:34:00 Scientific Discovery & Automated Experimentation 00:38:04 AI Safety, Enfeeblement & The Future of Work --- REFERENCES: Concept: [00:00:58] Free Energy Principle (FEP) https://en.wikipedia.org/wiki/Free_energy_principle [00:06:00] Monte Carlo Tree Search https://en.wikipedia.org/wiki/Monte_Carlo_tree_search Book: [00:09:00] The Intentional Stance https://mitpress.mit.edu/9780262540537/the-intentional-stance/ Paper: [00:13:00] A Tutorial on Energy-Based Learning (LeCun 2006) http://yann.lecun.com/exdb/publis/pdf/lecun-06.pdf [00:15:00] Auto-Encoding Variational Bayes (VAE) https://arxiv.org/abs/1312.6114 [00:20:15] JEPA (Joint Embedding Prediction Architecture) https://openreview.net/forum?id=BZ5a1r-kVsf [00:22:30] The Wake-Sleep Algorithm https://www.cs.toronto.edu/~hinton/absps/ws.pdf --- RESCRIPT: https://app.rescript.info/public/share/DJlSbJ_Qx080q315tWaqMWn3PixCQsOcM4Kf1IW9_Eo PDF: https://app.rescript.info/api/public/sessions/0efec296b9b6e905/pdf

    47 min
  2. Abstraction & Idealization: AI's Plato Problem [Mazviita Chirimuuta]

    JAN 23

    Abstraction & Idealization: AI's Plato Problem [Mazviita Chirimuuta]

    Professor Mazviita Chirimuuta joins us for a fascinating deep dive into the philosophy of neuroscience and what it really means to understand the mind.*What can neuroscience actually tell us about how the mind works?* In this thought-provoking conversation, we explore the hidden assumptions behind computational theories of the brain, the limits of scientific abstraction, and why the question of machine consciousness might be more complicated than AI researchers assume.Mazviita, author of *The Brain Abstracted,* brings a unique perspective shaped by her background in both neuroscience research and philosophy. She challenges us to think critically about the metaphors we use to understand cognition — from the reflex theory of the late 19th century to today's dominant view of the brain as a computer.*Key topics explored:**The problem of oversimplification* — Why scientific models necessarily leave things out, and how this can sometimes lead entire fields astray. The cautionary tale of reflex theory shows how elegant explanations can blind us to biological complexity.*Is the brain really a computer?* — Mazviita unpacks the philosophical assumptions behind computational neuroscience and asks: if we can model anything computationally, what makes brains special? The answer might challenge everything you thought you knew about AI.*Haptic realism* — A fresh way of thinking about scientific knowledge that emphasizes interaction over passive observation. Knowledge isn't about reading the "source code of the universe" — it's something we actively construct through engagement with the world.*Why embodiment matters for understanding* — Can a disembodied language model truly understand? Mazviita makes a compelling case that human cognition is deeply entangled with our sensory-motor engagement and biological existence in ways that can't simply be abstracted away.*Technology and human finitude* — Drawing on Heidegger, we discuss how the dream of transcending our physical limitations through technology might reflect a fundamental misunderstanding of what it means to be a knower.This conversation is essential viewing for anyone interested in AI, consciousness, philosophy of mind, or the future of cognitive science. Whether you're skeptical of strong AI claims or a true believer in machine consciousness, Mazviita's careful philosophical analysis will give you new tools for thinking through these profound questions.---TIMESTAMPS:00:00:00 The Problem of Generalizing Neuroscience00:02:51 Abstraction vs. Idealization: The "Kaleidoscope"00:05:39 Platonism in AI: Discovering or Inventing Patterns?00:09:42 When Simplification Fails: The Reflex Theory00:12:23 Behaviorism and the "Black Box" Trap00:14:20 Haptic Realism: Knowledge Through Interaction00:20:23 Is Nature Protean? The Myth of Converging Truth00:23:23 The Computational Theory of Mind: A Useful Fiction?00:27:25 Biological Constraints: Why Brains Aren't Just Neural Nets00:31:01 Agency, Distal Causes, and Dennett's Stances00:37:13 Searle's Challenge: Causal Powers and Understanding00:41:58 Heidegger's Warning & The Experiment on Children---REFERENCES:Book:[00:01:28] The Brain Abstractedhttps://mitpress.mit.edu/9780262548045/the-brain-abstracted/[00:11:05] The Integrated Action of the Nervous Systemhttps://www.amazon.sg/integrative-action-nervous-system/dp/9354179029[00:18:15] The Quest for Certainty (Dewey)https://www.amazon.com/Quest-Certainty-Relation-Knowledge-Lectures/dp/0399501916[00:19:45] Realism for Realistic People (Chang)https://www.cambridge.org/core/books/realism-for-realistic-people/ACC93A7F03B15AA4D6F3A466E3FC5AB7---RESCRIPT:https://app.rescript.info/public/share/A6cZ1TY35p8ORMmYCWNBI0no9ChU3-Kx7dPXGJURvZ0PDF Transcript:https://app.rescript.info/api/public/sessions/0fb7767e066cf712/pdf

    54 min
  3. Why Every Brain Metaphor in History Has Been Wrong [SPECIAL EDITION]

    JAN 23

    Why Every Brain Metaphor in History Has Been Wrong [SPECIAL EDITION]

    What if everything we think we know about the brain is just a really good metaphor that we forgot was a metaphor?This episode takes you on a journey through the history of scientific simplification, from a young Karl Friston watching wood lice in his garden to the bold claims that your mind is literally software running on biological hardware.We bring together some of the most brilliant minds we've interviewed — Professor Mazviita Chirimuuta, Francois Chollet, Joscha Bach, Professor Luciano Floridi, Professor Noam Chomsky, Nobel laureate John Jumper, and more — to wrestle with a deceptively simple question: *When scientists simplify reality to study it, what gets captured and what gets lost?**Key ideas explored:**The Spherical Cow Problem* — Science requires simplification. We're limited creatures trying to understand systems far more complex than our working memory can hold. But when does a useful model become a dangerous illusion?*The Kaleidoscope Hypothesis* — Francois Chollet's beautiful idea that beneath all the apparent chaos of reality lies simple, repeating patterns — like bits of colored glass in a kaleidoscope creating infinite complexity. Is this profound truth or Platonic wishful thinking?*Is Software Really Spirit?* — Joscha Bach makes the provocative claim that software is literally spirit, not metaphorically. We push back on this, asking whether the "sameness" we see across different computers running the same program exists in nature or only in our descriptions.*The Cultural Illusion of AGI* — Why does artificial general intelligence seem so inevitable to people in Silicon Valley? Professor Chirimuuta suggests we might be caught in a "cultural historical illusion" — our mechanistic assumptions about minds making AI seem like destiny when it might just be a bet.*Prediction vs. Understanding* — Nobel Prize winner John Jumper: AI can predict and control, but understanding requires a human in the loop. Throughout history, we've described the brain as hydraulic pumps, telegraph networks, telephone switchboards, and now computers. Each metaphor felt obviously true at the time. This episode asks: what will we think was naive about our current assumptions in fifty years?Featuring insights from *The Brain Abstracted* by Mazviita Chirimuuta — possibly the most influential book on how we think about thinking in 2025.---TIMESTAMPS:00:00:00 The Wood Louse & The Spherical Cow00:02:04 The Necessity of Abstraction00:04:42 Simplicius vs. Ignorantio: The Boxing Match00:06:39 The Kaleidoscope Hypothesis00:08:40 Is the Mind Software?00:13:15 Critique of Causal Patterns00:14:40 Temperature is Not a Thing00:18:24 The Ship of Theseus & Ontology00:23:45 Metaphors Hardening into Reality00:25:41 The Illusion of AGI Inevitability00:27:45 Prediction vs. Understanding00:32:00 Climbing the Mountain vs. The Helicopter00:34:53 Haptic Realism & The Limits of Knowledge---REFERENCES:Person:[00:00:00] Karl Friston (UCL)https://profiles.ucl.ac.uk/1236-karl-friston[00:06:30] Francois Chollethttps://fchollet.com/[00:14:41] Cesar Hidalgo, MLST interview.https://www.youtube.com/watch?v=vzpFOJRteeI[00:30:30] Terence Tao's Bloghttps://terrytao.wordpress.com/Book:[00:02:25] The Brain Abstractedhttps://mitpress.mit.edu/9780262548045/the-brain-abstracted/[00:06:00] On Learned Ignorancehttps://www.amazon.com/Nicholas-Cusa-learned-ignorance-translation/dp/0938060236[00:24:15] Science and the Modern Worldhttps://amazon.com/dp/0684836394 RESCRIPT:https://app.rescript.info/public/share/CYy0ex2M2kvcVRdMnSUky5O7H7hB7v2u_nVhoUiuKD4PDF Transcript: https://app.rescript.info/api/public/sessions/6c44c41e1e0fa6dd/pdf Thank you to Dr. Maxwell Ramstead for early script work on this show (Ph.D student of Friston) and the woodlice story came from him!

    42 min
  4. Bayesian Brain, Scientific Method, and Models [Dr. Jeff Beck]

    12/31/2025

    Bayesian Brain, Scientific Method, and Models [Dr. Jeff Beck]

    Dr. Jeff Beck, mathematician turned computational neuroscientist, joins us for a fascinating deep dive into why the future of AI might look less like ChatGPT and more like your own brain. **SPONSOR MESSAGES START** — Prolific - Quality data. From real people. For faster breakthroughs. https://www.prolific.com/?utm_source=mlst — **END** *What if the key to building truly intelligent machines isn't bigger models, but smarter ones?* In this conversation, Jeff makes a compelling case that we've been building AI backwards. While the tech industry races to scale up transformers and language models, Jeff argues we're missing something fundamental: the brain doesn't work like a giant prediction engine. It works like a scientist, constantly testing hypotheses about a world made of *objects* that interact through *forces* — not pixels and tokens. *The Bayesian Brain* — Jeff explains how your brain is essentially running the scientific method on autopilot. When you combine what you see with what you hear, you're doing optimal Bayesian inference without even knowing it. This isn't just philosophy — it's backed by decades of behavioral experiments showing humans are surprisingly efficient at handling uncertainty. *AutoGrad Changed Everything* — Forget transformers for a moment. Jeff argues the real hero of the AI boom was automatic differentiation, which turned AI from a math problem into an engineering problem. But in the process, we lost sight of what actually makes intelligence work. *The Cat in the Warehouse Problem* — Here's where it gets practical. Imagine a warehouse robot that's never seen a cat. Current AI would either crash or make something up. Jeff's approach? Build models that *know what they don't know*, can phone a friend to download new object models on the fly, and keep learning continuously. It's like giving robots the ability to say "wait, what IS that?" instead of confidently being wrong. *Why Language is a Terrible Model for Thought* — In a provocative twist, Jeff argues that grounding AI in language (like we do with LLMs) is fundamentally misguided. Self-report is the least reliable data in psychology — people routinely explain their own behavior incorrectly. We should be grounding AI in physics, not words. *The Future is Lots of Little Models* — Instead of one massive neural network, Jeff envisions AI systems built like video game engines: thousands of small, modular object models that can be combined, swapped, and updated independently. It's more efficient, more flexible, and much closer to how we actually think. Rescript: https://app.rescript.info/public/share/D-b494t8DIV-KRGYONJghvg-aelMmxSDjKthjGdYqsE --- TIMESTAMPS: 00:00:00 Introduction & The Bayesian Brain 00:01:25 Bayesian Inference & Information Processing 00:05:17 The Brain Metaphor: From Levers to Computers 00:10:13 Micro vs. Macro Causation & Instrumentalism 00:16:59 The Active Inference Community & AutoGrad 00:22:54 Object-Centered Models & The Grounding Problem 00:35:50 Scaling Bayesian Inference & Architecture Design 00:48:05 The Cat in the Warehouse: Solving Generalization 00:58:17 Alignment via Belief Exchange 01:05:24 Deception, Emergence & Cellular Automata --- REFERENCES: Paper: [00:00:24] Zoubin Ghahramani (Google DeepMind) https://pmc.ncbi.nlm.nih.gov/articles/PMC3538441/pdf/rsta201 [00:19:20] Mamba: Linear-Time Sequence Modeling https://arxiv.org/abs/2312.00752 [00:27:36] xLSTM: Extended Long Short-Term Memory https://arxiv.org/abs/2405.04517 [00:41:12] 3D Gaussian Splatting https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/ [01:07:09] Lenia: Biology of Artificial Life https://arxiv.org/abs/1812.05433 [01:08:20] Growing Neural Cellular Automata https://distill.pub/2020/growing-ca/ [01:14:05] DreamCoder https://arxiv.org/abs/2006.08381 [01:14:58] The Genomic Bottleneck https://www.nature.com/articles/s41467-019-11786-6 Person: [00:16:42] Karl Friston (UCL) https://www.youtube.com/watch?v=PNYWi996Beg

    1h 17m
  5. Your Brain is Running a Simulation Right Now [Max Bennett]

    12/30/2025

    Your Brain is Running a Simulation Right Now [Max Bennett]

    Tim sits down with Max Bennett to explore how our brains evolved over 600 million years—and what that means for understanding both human intelligence and AI. Max isn't a neuroscientist by training. He's a tech entrepreneur who got curious, started reading, and ended up weaving together three fields that rarely talk to each other: comparative psychology (what different animals can actually do), evolutionary neuroscience (how brains changed over time), and AI (what actually works in practice). *Your Brain Is a Guessing Machine* You don't actually "see" the world. Your brain builds a simulation of what it *thinks* is out there and just uses your eyes to check if it's right. That's why optical illusions work—your brain is filling in a triangle that isn't there, or can't decide if it's looking at a duck or a rabbit. *Rats Have Regrets* *Chimps Are Machiavellian* *Language Is the Human Superpower* *Does ChatGPT Think?* (truncated description, more on rescript) Understanding how the brain evolved isn't just about the past. It gives us clues about: - What's actually different between human intelligence and AI - Why we're so easily fooled by status games and tribal thinking - What features we might want to build into—or leave out of—future AI systems Get Max's book: https://www.amazon.com/Brief-History-Intelligence-Humans-Breakthroughs/dp/0063286343 Rescript: https://app.rescript.info/public/share/R234b7AXyDXZusqQ_43KMGsUSvJ2TpSz2I3emnI6j9A --- TIMESTAMPS: 00:00:00 Introduction: Outsider's Advantage & Neocortex Theories 00:11:34 Perception as Inference: The Filling-In Machine 00:19:11 Understanding, Recognition & Generative Models 00:36:39 How Mice Plan: Vicarious Trial & Error 00:46:15 Evolution of Self: The Layer 4 Mystery 00:58:31 Ancient Minds & The Social Brain: Machiavellian Apes 01:19:36 AI Alignment, Instrumental Convergence & Status Games 01:33:07 Metacognition & The IQ Paradox 01:48:40 Does GPT Have Theory of Mind? 02:00:40 Memes, Language Singularity & Brain Size Myths 02:16:44 Communication, Language & The Cyborg Future 02:44:25 Shared Fictions, World Models & The Reality Gap --- REFERENCES:Person: [00:00:05] Karl Friston (UCL) https://www.youtube.com/watch?v=PNYWi996Beg [00:00:06] Jeff Hawkins https://www.youtube.com/watch?v=6VQILbDqaI4 [00:12:19] Hermann von Helmholtz https://plato.stanford.edu/entries/hermann-helmholtz/ [00:38:34] David Redish (U. Minnesota) https://redishlab.umn.edu/ [01:10:19] Robin Dunbar https://www.psy.ox.ac.uk/people/robin-dunbar [01:15:04] Emil Menzel https://www.sciencedirect.com/bookseries/behavior-of-nonhuman-primates/vol/5/suppl/C [01:19:49] Nick Bostrom https://nickbostrom.com/ [02:28:25] Noam Chomsky https://linguistics.mit.edu/user/chomsky/ [03:01:22] Judea Pearl https://samueli.ucla.edu/people/judea-pearl/ Concept/Framework: [00:05:04] Active Inference https://www.youtube.com/watch?v=KkR24ieh5Ow Paper: [00:35:59] Predictions not commands [Rick A Adams] https://pubmed.ncbi.nlm.nih.gov/23129312/ Book: [01:25:42] The Elephant in the Brain https://www.amazon.com/Elephant-Brain-Hidden-Motives-Everyday/dp/0190495995 [01:28:27] The Status Game https://www.goodreads.com/book/show/58642436-the-status-game [02:00:40] The Selfish Gene https://amazon.com/dp/0198788606 [02:14:25] The Language Game https://www.amazon.com/Language-Game-Improvisation-Created-Changed/dp/1541674987 [02:54:40] The Evolution of Language https://www.amazon.com/Evolution-Language-Approaches/dp/052167736X [03:09:37] The Three-Body Problem https://amazon.com/dp/0765377063

    3h 17m
  6. The 3 Laws of Knowledge [César Hidalgo]

    12/27/2025

    The 3 Laws of Knowledge [César Hidalgo]

    César Hidalgo has spent years trying to answer a deceptively simple question: What is knowledge, and why is it so hard to move around? We all have this intuition that knowledge is just... information. Write it down in a book, upload it to GitHub, train an AI on it—done. But César argues that's completely wrong. Knowledge isn't a thing you can copy and paste. It's more like a living organism that needs the right environment, the right people, and constant exercise to survive. Guest: César Hidalgo, Director of the Center for Collective Learning 1. Knowledge Follows Laws (Like Physics) 2. You Can't Download Expertise 3. Why Big Companies Fail to Adapt 4. The "Infinite Alphabet" of Economies If you think AI can just "copy" human knowledge, or that development is just about throwing money at poor countries, or that writing things down preserves them forever—this conversation will change your mind. Knowledge is fragile, specific, and collective. It decays fast if you don't use it. The Infinite Alphabet [César A. Hidalgo] https://www.penguin.co.uk/books/458054/the-infinite-alphabet-by-hidalgo-cesar-a/9780241655672 https://x.com/cesifoti Rescript link. https://app.rescript.info/public/share/eaBHbEo9xamwbwpxzcVVm4NQjMh7lsOQKeWwNxmw0JQ --- TIMESTAMPS: 00:00:00 The Three Laws of Knowledge 00:02:28 Rival vs. Non-Rival: The Economics of Ideas 00:05:43 Why You Can't Just 'Download' Knowledge 00:08:11 The Detective Novel Analogy 00:11:54 Collective Learning & Organizational Networks 00:16:27 Architectural Innovation: Amazon vs. Barnes & Noble 00:19:15 The First Law: Learning Curves 00:23:05 The Samuel Slater Story: Treason & Memory 00:28:31 Physics of Knowledge: Joule's Cannon 00:32:33 Extensive vs. Intensive Properties 00:35:45 Knowledge Decay: Ise Temple & Polaroid 00:41:20 Absorptive Capacity: Sony & Donetsk 00:47:08 Disruptive Innovation & S-Curves 00:51:23 Team Size & The Cost of Innovation 00:57:13 Geography of Knowledge: Vespa's Origin 01:04:34 Migration, Diversity & 'Planet China' 01:12:02 Institutions vs. Knowledge: The China Story 01:21:27 Economic Complexity & The Infinite Alphabet 01:32:27 Do LLMs Have Knowledge? --- REFERENCES: Book: [00:47:45] The Innovator's Dilemma (Christensen) https://www.amazon.com/Innovators-Dilemma-Revolutionary-Change-Business/dp/0062060244 [00:55:15] Why Greatness Cannot Be Planned https://amazon.com/dp/3319155237 [01:35:00] Why Information Grows https://amazon.com/dp/0465048994 Paper: [00:03:15] Endogenous Technological Change (Romer, 1990) https://web.stanford.edu/~klenow/Romer_1990.pdf [00:03:30] A Model of Growth Through Creative Destruction (Aghion & Howitt, 1992) https://dash.harvard.edu/server/api/core/bitstreams/7312037d-2b2d-6bd4-e053-0100007fdf3b/content [00:14:55] Organizational Learning: From Experience to Knowledge (Argote & Miron-Spektor, 2011) https://www.researchgate.net/publication/228754233_Organizational_Learning_From_Experience_to_Knowledge [00:17:05] Architectural Innovation (Henderson & Clark, 1990) https://www.researchgate.net/publication/200465578_Architectural_Innovation_The_Reconfiguration_of_Existing_Product_Technologies_and_the_Failure_of_Established_Firms [00:19:45] The Learning Curve Equation (Thurstone, 1916) https://dn790007.ca.archive.org/0/items/learningcurveequ00thurrich/learningcurveequ00thurrich.pdf [00:21:30] Factors Affecting the Cost of Airplanes (Wright, 1936) https://pdodds.w3.uvm.edu/research/papers/others/1936/wright1936a.pdf [00:52:45] Are Ideas Getting Harder to Find? (Bloom et al.) https://web.stanford.edu/~chadj/IdeaPF.pdf [01:33:00] LLMs/ Emergence https://arxiv.org/abs/2506.11135 Person: [00:25:30] Samuel Slater https://en.wikipedia.org/wiki/Samuel_Slater [00:42:05] Masaru Ibuka (Sony) https://www.sony.com/en/SonyInfo/CorporateInfo/History/SonyHistory/1-02.html

    1h 37m
  7. "I Desperately Want To Live In The Matrix" - Dr. Mike Israetel

    12/24/2025

    "I Desperately Want To Live In The Matrix" - Dr. Mike Israetel

    This is a lively, no-holds-barred debate about whether AI can truly be intelligent, conscious, or understand anything at all — and what happens when (or if) machines become smarter than us. Dr. Mike Israetel is a sports scientist, entrepreneur, and co-founder of RP Strength (a fitness company). He describes himself as a "dilettante" in AI but brings a fascinating outsider's perspective. Jared Feather (IFBB Pro bodybuilder and exercise physiologist) The Big Questions: 1. When is superintelligence coming? 2. Does AI actually understand anything? 3. The Simulation Debate (The Spiciest Part) 4. Will AI kill us all? (The Doomer Debate) 5. What happens to human jobs and purpose? 6. Do we need suffering? Mikes channel: https://www.youtube.com/channel/UCfQgsKhHjSyRLOp9mnffqVg RESCRIPT INTERACTIVE PLAYER: https://app.rescript.info/public/share/GVMUXHCqctPkXH8WcYtufFG7FQcdJew_RL_MLgMKU1U --- TIMESTAMPS: 00:00:00 Introduction & Workout Demo 00:04:15 ASI Timelines & Definitions 00:10:24 The Embodiment Debate 00:18:28 Neutrinos & Abstract Knowledge 00:25:56 Can AI Learn From YouTube? 00:31:25 Diversity of Intelligence 00:36:00 AI Slop & Understanding 00:45:18 The Simulation Argument: Fire & Water 00:58:36 Consciousness & Zombies 01:04:30 Do Reasoning Models Actually Reason? 01:12:00 The Live Learning Problem 01:19:15 Superintelligence & Benevolence 01:28:59 What is True Agency? 01:37:20 Game Theory & The "Kill All Humans" Fallacy 01:48:05 Regulation & The China Factor 01:55:52 Mind Uploading & The Future of Love 02:04:41 Economics of ASI: Will We Be Useless? 02:13:35 The Matrix & The Value of Suffering 02:17:30 Transhumanism & Inequality 02:21:28 Debrief: AI Medical Advice & Final Thoughts --- REFERENCES: Paper: [00:10:45] Alchemy and Artificial Intelligence (Dreyfus) https://www.rand.org/content/dam/rand/pubs/papers/2006/P3244.pdf [00:10:55] The Chinese Room Argument (John Searle) https://home.csulb.edu/~cwallis/382/readings/482/searle.minds.brains.programs.bbs.1980.pdf [00:11:05] The Symbol Grounding Problem (Stephen Harnad) https://arxiv.org/html/cs/9906002 [00:23:00] Attention Is All You Need https://arxiv.org/abs/1706.03762 [00:45:00] GPT-4 Technical Report https://arxiv.org/abs/2303.08774 [01:45:00] Anthropic Agentic Misalignment Paper https://www.anthropic.com/research/agentic-misalignment [02:17:45] Retatrutide https://pubmed.ncbi.nlm.nih.gov/37366315/ Organization: [00:15:50] CERN https://home.cern/ [01:05:00] METR Long Horizon Evaluations https://evaluations.metr.org/ MLST Episode: [00:23:10] MLST: Llion Jones - Inventors' Remorse https://www.youtube.com/watch?v=DtePicx_kFY [00:50:30] MLST: Blaise Agüera y Arcas Interview https://www.youtube.com/watch?v=rMSEqJ_4EBk [01:10:00] MLST: David Krakauer https://www.youtube.com/watch?v=dY46YsGWMIc Event: [00:23:40] ARC Prize/Challenge https://arcprize.org/ Book: [00:24:45] The Brain Abstracted https://www.amazon.com/Brain-Abstracted-Simplification-Philosophy-Neuroscience/dp/0262548046 [00:47:55] Pamela McCorduck https://www.amazon.com/Machines-Who-Think-Artificial-Intelligence/dp/1568812051 [01:23:15] The Singularity Is Nearer (Ray Kurzweil) https://www.amazon.com/Singularity-Nearer-Ray-Kurzweil-ebook/dp/B08Y6FYJVY [01:27:35] A Fire Upon The Deep (Vernor Vinge) https://www.amazon.com/Fire-Upon-Deep-S-F-MASTERWORKS-ebook/dp/B00AVUMIZE/ [02:04:50] Deep Utopia (Nick Bostrom) https://www.amazon.com/Deep-Utopia-Meaning-Solved-World/dp/1646871642 [02:05:00] Technofeudalism (Yanis Varoufakis) https://www.amazon.com/Technofeudalism-Killed-Capitalism-Yanis-Varoufakis/dp/1685891241 Visual Context Needed: [00:29:40] AT-AT Walker (Star Wars) https://starwars.fandom.com/wiki/All_Terrain_Armored_Transport Person: [00:33:15] Andrej Karpathy https://karpathy.ai/ Video: [01:40:00] Mike Israetel vs Liron Shapira AI Doom Debate https://www.youtube.com/watch?v=RaDWSPMdM4o Company: [02:26:30] Examine.com https://examine.com/

    2h 56m
  8. Making deep learning perform real algorithms with Category Theory (Andrew Dudzik, Petar Velichkovich, Taco Cohen, Bruno Gavranović, Paul Lessard)

    12/22/2025

    Making deep learning perform real algorithms with Category Theory (Andrew Dudzik, Petar Velichkovich, Taco Cohen, Bruno Gavranović, Paul Lessard)

    We often think of Large Language Models (LLMs) as all-knowing, but as the team reveals, they still struggle with the logic of a second-grader. Why can’t ChatGPT reliably add large numbers? Why does it "hallucinate" the laws of physics? The answer lies in the architecture. This episode explores how *Category Theory* —an ultra-abstract branch of mathematics—could provide the "Periodic Table" for neural networks, turning the "alchemy" of modern AI into a rigorous science. In this deep-dive exploration, *Andrew Dudzik*, *Petar Velichkovich*, *Taco Cohen*, *Bruno Gavranović*, and *Paul Lessard* join host *Tim Scarfe* to discuss the fundamental limitations of today’s AI and the radical mathematical framework that might fix them. TRANSCRIPT: https://app.rescript.info/public/share/LMreunA-BUpgP-2AkuEvxA7BAFuA-VJNAp2Ut4MkMWk --- Key Insights in This Episode: * *The "Addition" Problem:* *Andrew Dudzik* explains why LLMs don't actually "know" math—they just recognize patterns. When you change a single digit in a long string of numbers, the pattern breaks because the model lacks the internal "machinery" to perform a simple carry operation. * *Beyond Alchemy:* deep learning is currently in its "alchemy" phase—we have powerful results, but we lack a unifying theory. Category Theory is proposed as the framework to move AI from trial-and-error to principled engineering. [00:13:49] * *Algebra with Colors:* To make Category Theory accessible, the guests use brilliant analogies—like thinking of matrices as *magnets with colors* that only snap together when the types match. This "partial compositionality" is the secret to building more complex internal reasoning. [00:09:17] * *Synthetic vs. Analytic Math:* *Paul Lessard* breaks down the philosophical shift needed in AI research: moving from "Analytic" math (what things are made of) to "Synthetic" math [00:23:41] --- Why This Matters for AGI If we want AI to solve the world's hardest scientific problems, it can't just be a "stochastic parrot." It needs to internalize the rules of logic and computation. By imbuing neural networks with categorical priors, researchers are attempting to build a future where AI doesn't just predict the next word—it understands the underlying structure of the universe. --- TIMESTAMPS: 00:00:00 The Failure of LLM Addition & Physics 00:01:26 Tool Use vs Intrinsic Model Quality 00:03:07 Efficiency Gains via Internalization 00:04:28 Geometric Deep Learning & Equivariance 00:07:05 Limitations of Group Theory 00:09:17 Category Theory: Algebra with Colors 00:11:25 The Systematic Guide of Lego-like Math 00:13:49 The Alchemy Analogy & Unifying Theory 00:15:33 Information Destruction & Reasoning 00:18:00 Pathfinding & Monoids in Computation 00:20:15 System 2 Reasoning & Error Awareness 00:23:31 Analytic vs Synthetic Mathematics 00:25:52 Morphisms & Weight Tying Basics 00:26:48 2-Categories & Weight Sharing Theory 00:28:55 Higher Categories & Emergence 00:31:41 Compositionality & Recursive Folds 00:34:05 Syntax vs Semantics in Network Design 00:36:14 Homomorphisms & Multi-Sorted Syntax 00:39:30 The Carrying Problem & Hopf Fibrations Petar Veličković (GDM) https://petar-v.com/ Paul Lessard https://www.linkedin.com/in/paul-roy-lessard/ Bruno Gavranović https://www.brunogavranovic.com/ Andrew Dudzik (GDM) https://www.linkedin.com/in/andrew-dudzik-222789142/ --- REFERENCES: Model: [00:01:05] Veo https://deepmind.google/models/veo/ [00:01:10] Genie https://deepmind.google/blog/genie-3-a-new-frontier-for-world-models/ Paper: [00:04:30] Geometric Deep Learning Blueprint https://arxiv.org/abs/2104.13478 https://www.youtube.com/watch?v=bIZB1hIJ4u8 [00:16:45] AlphaGeometry https://arxiv.org/abs/2401.08312 [00:16:55] AlphaCode https://arxiv.org/abs/2203.07814 [00:17:05] FunSearch https://www.nature.com/articles/s41586-023-06924-6 [00:37:00] Attention Is All You Need https://arxiv.org/abs/1706.03762 [00:43:00] Categorical Deep Learning https://arxiv.org/abs/2402.15332

    44 min
See All (246)

4.6
out of 5
95 Ratings

About

Welcome! We engage in fascinating discussions with pre-eminent figures in the AI field. Our flagship show covers current affairs in AI, cognitive science, neuroscience and philosophy of mind with in-depth analysis. Our approach is unrivalled in terms of scope and rigour – we believe in intellectual diversity in AI, and we touch on all of the main ideas in the field with the hype surgically removed. MLST is run by Tim Scarfe, Ph.D (https://www.linkedin.com/in/ecsquizor/) and features regular appearances from MIT Doctor of Philosophy Keith Duggar (https://www.linkedin.com/in/dr-keith-duggar/).

Information

  • Creator
    Machine Learning Street Talk (MLST)
  • Years Active
    2020 - 2026
  • Episodes
    246
  • Rating
    Explicit
  • Copyright
    © Machine Learning Street Talk (MLST)
  • Show Website
    Machine Learning Street Talk (MLST)

You Might Also Like