Machine Learning podcasts

Zoe Weil discusses how recommendation and ranking systems can use in-session behavioral signals to model intent and optimize purchasing outcomes. The episode examines event-to-feature models, low-latency ranking infrastructure, evaluation against business outcomes, and the distinction between click relevance and useful recommendations. It also considers privacy tradeoffs in personalization and the relationship between advertising and organic revenue.

Hosted by Sam Charrington

John Platt discusses how Google’s applied-science team chooses problems where AI can make a useful contribution. Topics include satellite-based detection and prediction of aircraft contrails, evaluation of rerouting trials, limitations of physical simulation, and the role of AI agents in scientific modelling and data work. The conversation also examines overfitting, action incentives, gradient-free optimisation, SMO and support-vector machines, the physical constraints on scaling, and opportunities for robotics and manufacturing to support climate technology. It concludes with FireSat’s approach to detecting small wildfires from orbit and the practical issues of coverage, cost and false positives.

Hosted by Ravid Shwartz Ziv, Allen Roush

Diogo Almeida joins Sam Charrington to discuss TypeSafe's Jev model and the use of calibrated decisions as a component of AI software. The conversation examines reinforcement learning from calibrated decisions, differences from classifiers and text-generating models, and the implications for agents, tool use and system architecture.

Hosted by Sam Charrington

Yuandong Tian discusses his research on computer Go, from DarkForest to OpenGo, and the role of action-space design in applying reinforcement learning. The conversation covers gradient-free optimization, neural architecture search, Coconut’s approach to reasoning in latent space, representation learning and grokking. It then examines AI-assisted research, recursive self-improvement, coding-agent limitations, and whether alternative architectures can outperform transformers. The closing discussion considers data efficiency, robotics, restrictions on self-improving systems, and open-source models.

Hosted by Ravid Shwartz Ziv, Allen Roush

Ming-Yu Liu, NVIDIA vice president of research and head of the Cosmos Lab, joins Practical AI hosts Daniel Whitenack and Chris Benson to discuss AI systems that interact with the physical world. The conversation examines open models, world models and simulation as foundations for robotics and autonomous vehicles, and how research and deployment can advance physical AI. Published 1 October 2026; publisher runtime 47 minutes 19 seconds.

Hosted by Daniel Whitenack, Chris Benson

Andrew Glester explores how drones, robotics and machine learning support wildlife research and conservation. Blair Costelloe discusses the WildDrone and WildBotics networks and the Mara Elephant Project; Camille Rondeau Saint-Jean describes real-time animal monitoring; William Njoroge explains how Ol Pejeta Conservancy combines drones with established conservation methods. The episode considers population data, field constraints, regulation and collaboration across disciplines.

Hosted by Andrew Glester

Sam Charrington speaks with Greg Burnham, who leads AI capabilities research at Epoch AI, about the progression from elementary mathematical tasks to difficult research problems, including Navier–Stokes. They examine how advanced systems solve mathematical problems, the roles of persistence and existing human work, and the evidence for new ideas. The conversation also considers how to measure progress when traditional benchmarks become less informative, why improvements appear steady across successive model generations, and the remaining weaknesses in open-ended research, learning from experience and choosing productive scientific questions.

Hosted by Sam Charrington

Stanford linguist and computer scientist Chris Manning discusses what linguistics contributed to machine learning and why pragmatics and dialogue remain open problems for language models. The conversation examines early abstraction of verb categories in small transformers, how distributed representations shape learning, and whether language alone can support meaningful representations. It also considers language in world models, diffusion language models, and representation finetuning (ReFT), which steers frozen models through their hidden states. The final discussion asks where knowledge resides and whether concepts occupy linear subspaces.

Hosted by Ravid Shwartz Ziv, Allen Roush

Andrew Dai joins The Information Bottleneck to discuss language-model pre-training, next-token prediction, training-data quality and visual reasoning. The conversation examines counting and image understanding, world models and JEPA. Hosted by Ravid Shwartz-Ziv and Allen Roush.

Carnegie Mellon researcher and Abridge co-founder Zachary Lipton discusses where machine learning can help healthcare and why clinical work is harder to automate than software development. The conversation examines medical documentation, decision support, drug discovery, open models and model routing, then turns to academic research, doctoral training and the effects of automation on scientific careers. Hosted by Ravid Shwartz Ziv and Allen Roush. Watch the full conversation on the publisher’s YouTube channel.

Hosted by Ravid Shwartz Ziv, Allen Roush

Rafael Rosengarten and BioPharmaTrend co-founder Andrii Buvailo discuss how to assess progress in AI-assisted drug discovery. They trace the move from individual computational tasks to connected research workflows and question whether counting AI-associated drug candidates captures the technology’s value. Topics include research productivity, trial design, biomarkers, human expertise and the use of patient-derived data, organoids and other representative biological systems to improve translation. The conversation also considers why AI has become polarising and how specialised models may fit into pharmaceutical research.

Alex Smola discusses the development of voice agents, audiovisual systems and AI avatars. Topics include audio tokenization, inference cost, conversational latency, visual context and how artificial systems might learn from interaction while responding appropriately to human emotion.

Hosted by Sam Charrington

Sara Hooker of Adaptation Lab explores AI systems that change with their users, tasks and environments. The discussion connects continual learning, efficient adaptation and automated science with the difficulty of evaluating tasks that lack easily checked answers. It also covers interfaces, distillation, open models, safety and regulation, multilingual tokenization, and possible successors to current Transformer systems. Hosted by Ravid Shwartz Ziv and Allen Roush. Watch the full conversation on the publisher’s YouTube channel.

Hosted by Ravid Shwartz Ziv, Allen Roush

Microsoft researcher Alexia Jolicoeur-Martineau explains the Tiny Recursive Model and the reasoning behind her work on small networks that repeatedly refine an internal state and proposed answer. The conversation examines truncated gradients, puzzle-solving benchmarks and the differences from autoregressive language generation. It also considers molecular modelling, limits of data scaling and which research directions she would prioritize. Hosted by Ravid Shwartz Ziv and Allen Roush. Watch the full conversation on the publisher’s YouTube channel.

Hosted by Ravid Shwartz Ziv, Allen Roush

Rohan Anil of Core Automation discusses the relationship between pretraining, reinforcement learning and learning after deployment. Drawing on his optimization work at Google and Anthropic, he examines why additional post-training, distillation and longer contexts may not solve continual learning. Other topics include second-order optimizers, distributed training, low-level coding agents and the difficulty of coordinating very large GPU clusters. Hosted by Ravid Shwartz Ziv and Allen Roush. Watch the full conversation on the publisher’s YouTube channel.

Hosted by Ravid Shwartz Ziv, Allen Roush

Christopher Potts examines whether increasing token consumption translates into useful improvements in AI performance. The discussion covers evaluation beyond benchmarks, inference-time scaling, DSPy, interpretability, user expertise and architectural changes that could improve the economics of capable AI systems.

Hosted by Sam Charrington

Vincent Racaniello, Kathy Spindler and Brianne Barker discuss research using generative AI to design complete bacteriophage genomes, including reported viable phages active against antibiotic-resistant bacteria. They also examine a study linking recombinant shingles vaccination with lower cardiovascular-event risk. The discussion connects genome modelling, experimental virology and vaccine research, alongside listener letters and weekly selections.

Hosted by Vincent Racaniello, Brianne Barker

John Langford of Microsoft AI Labs discusses whether compact implicit models of the world can improve data efficiency. The conversation examines belief-state compression, Transformer caches, JEPA-style objectives and his Next Latent research. It also covers the value of algorithmic research alongside scaling, agent-assisted experiments, open models, the history of CAPTCHA and the behavior of modern optimizers. Hosted by Ravid Shwartz Ziv and Allen Roush. Watch the full conversation on the publisher’s YouTube channel.

Hosted by Ravid Shwartz Ziv, Allen Roush

INRIA researcher David Holzmüller explains how to choose among tabular foundation models, boosted trees and multilayer perceptrons. He discusses TabArena, TabICL and RealMLP, benchmark weaknesses, small-data performance, calibration and class imbalance. The conversation also examines text columns, explainability, time-series distinctions, synthetic pretraining and the trade-offs among computation, inference speed and predictive performance. Hosted by Ravid Shwartz Ziv and Allen Roush. Watch the full conversation on the publisher’s YouTube channel.

Hosted by Ravid Shwartz Ziv, Allen Roush

Charles Frye of Modal examines the infrastructure constraints behind large-scale AI research. With Ravid Shwartz Ziv and Allen Roush, he discusses underused hardware, saturated resources, sharing GPU capacity and deciding when to train a model. The conversation also covers inference and speculative decoding, hardware economics, virtualization and the security boundaries around agents and open models. Hosted by Ravid Shwartz Ziv and Allen Roush. Watch the full conversation on the publisher’s YouTube channel.

Hosted by Ravid Shwartz Ziv, Allen Roush