Jürgen Schmidhuber - World Models, RL, and the Year that changed AI (Part 1)

In this episode, we host Jürgen Schmidhuber - the man, the legend, one of the godfathers of modern AI. His lab worked out many ideas behind today’s systems (LSTM, world models, artificial curiosity, Transformer variants, and even GAN-style setups) decades before they became fashionable, and he’s just as well known for making sure people remember who did what first. This is the first of two conversations with him.We go back to his lab in the early 90s and ask how one small group came up with so many of the ideas that are now being scaled to a thousand billion dollars, back when compute was ten million times more expensive. A lot of the episode comes down to one distinction he keeps making: prediction vs. decision-making. His take is that LLMs are very good prediction machines that imitate the web, but that’s only half the problem. To actually act in the world, you need a controller that uses a world model to plan. He talks about his 1990 work on world models and artificial curiosity, where the controller gets rewarded for running experiments that improve its own model (an adversarial setup years before GANs), why planning millisecond by millisecond doesn’t scale, and why you need sub-goals instead.We also talk about compression as the core of understanding, from falling apples to Kepler to Einstein, and why we still don’t have a robot that can do what a plumber does, even though the AI behind the screen keeps getting better. Then the conversation moves to credit assignment: how “to Schmidhuber” became a verb, what he thinks is broken about the award system, and a long exchange on PMAX vs. JEPA. He ends on the real origins of deep learning and a prediction about self-replicating machines in space.Timeline00:00  Intro00:55  1991 in Munich, and why that lab mattered02:38  "I'm not very smart"  and why compute getting 10× cheaper every 5 years changed everything04:25  Chess as an AI proxy08:27  Artificial curiosity in the 90s vs. today's RL exploration09:10  Why RL is harder than supervised learning20:48  Coding agents vs. robots, and how a baby learns its own hands26:20  Compression as understanding33:40  What's actually missing on the road to AGI37:30  Why millisecond-by-millisecond planning is stupid47:44  Convergence to LLMs, GPUs, and how far we still are from the Bremermann limit51:49  Unsupervised learning, factorial codes, and predictability minimization58:12  Credit assignment: the fights with LeCun and the Nobel critique1:02:13  On his last name becoming a verb1:05:17  The award system's missing peer review1:07:03  Closed labs and the decline of open research1:13:23  Audience questions1:34:02  Closing: who really invented deep learning?Music:"Kid Kodi" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0."Palms Down" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0.Changes: trimmedAbout: The Information Bottleneck is hosted by Ravid Shwartz-Ziv and Allen Roush, featuring in-depth conversations with leading AI researchers about the ideas shaping the future of machine learning.