Machine Learning Street Talk (MLST)
A podcast by Machine Learning Street Talk (MLST)

Categories:
213 Episodes
-
ARC Prize v2 Launch! (Francois Chollet and Mike Knoop)
Published: 3/24/2025 -
Test-Time Adaptation: the key to reasoning with DL (Mohamed Osman)
Published: 3/22/2025 -
GSMSymbolic paper - Iman Mirzadeh (Apple)
Published: 3/19/2025 -
Reasoning, Robustness, and Human Feedback in AI - Max Bartolo (Cohere)
Published: 3/18/2025 -
Tau Language: The Software Synthesis Future (sponsored)
Published: 3/12/2025 -
John Palazza - Vice President of Global Sales @ CentML ( sponsored)
Published: 3/10/2025 -
Transformers Need Glasses! - Federico Barbero
Published: 3/8/2025 -
Sakana AI - Chris Lu, Robert Tjarko Lange, Cong Lu
Published: 3/1/2025 -
Clement Bonnet - Can Latent Program Networks Solve Abstract Reasoning?
Published: 2/19/2025 -
Prof. Jakob Foerster - ImageNet Moment for Reinforcement Learning?
Published: 2/18/2025 -
Daniel Franzen & Jan Disselhoff - ARC Prize 2024 winners
Published: 2/12/2025 -
Sepp Hochreiter - LSTM: The Comeback Story?
Published: 2/12/2025 -
Want to Understand Neural Networks? Think Elastic Origami! - Prof. Randall Balestriero
Published: 2/8/2025 -
Nicholas Carlini (Google DeepMind)
Published: 1/25/2025 -
Subbarao Kambhampati - Do o1 models search?
Published: 1/23/2025 -
How Do AI Models Actually Think? - Laura Ruis
Published: 1/20/2025 -
Jurgen Schmidhuber on Humans co-existing with AIs
Published: 1/16/2025 -
Yoshua Bengio - Designing out Agency for Safe AI
Published: 1/15/2025 -
Francois Chollet - ARC reflections - NeurIPS 2024
Published: 1/9/2025 -
Jeff Clune - Agent AI Needs Darwin
Published: 1/4/2025
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/).