Why Scaling Prediction Cannot Create Intelligence - Alexander Mattick

0:00-2:14:20

Alexander Mattick is a researcher at Fraunhofer IIS and a PhD researcher at the University of Technology Nuremberg (UTN), and a regular on Yannic Kilcher's Discord. He first came on MLST in 2022, after helping research the Yann LeCun and Randall Balestriero episode on interpolation. SPONSOR: --- Cyber Fund built the Monastery to help founders ship products that were impossible a year ago. Applications for Batch 1 are now open. Apply now: https://cyber.fund --- Alexander treats inference as the thread running through modern machine learning: once you have a model, what does it cost to get an answer out of it? He works through Monte Carlo, GFlowNets, energy-based models, diffusion, normalising flows and flow matching, with four short explainers he recorded himself. He is blunt about energy-based models: you can sample from them in principle, but it is rarely worth the compute. JEPA and "world model", he says, are closer to branding than to technical categories. Next: theories of deep learning, none of which he thinks predicts enough yet to guide practice, then reinforcement learning. --- 0:00 Cold open: information is expensive 0:51 Welcome back, Alexander Mattic 2:08 Alexander's research background 2:50 Inference: densities, sampling and Monte Carlo 6:42 GFlowNets, energy functions and MCMC 9:45 Explainer: energy-based models 11:03 Why model a density at all?

Publisher

Machine Learning Street Talk (MLST)

Link

podcasters.spotify.com/pod/show/machinelearningstreettalk/episodes/Why-Scaling-Prediction-Cannot-Create-Intelligence---Alexander-Mattick-e3p69rq

Published

September 21, 2026

Duration

2h 14m

Format

Podcast

Category

Issues · Tech News

Source

RSS feed

ML

Machine Learning Street Talk (MLST)

@mlstreettalk

#scalingpredictioncannot #alexandermattick

The Nile