Jürgen Schmidhuber - World Models, RL, and the Year that chang…Welcome to The Information Bottleneck!

Search

June 4, 2026<br>Jürgen Schmidhuber - World Models, RL, and the Year that changed AI (Part 1)

The Information Bottleneck<br>Jürgen Schmidhuber - World Models, RL, and the Year that changed AI (Part 1)

Your browser does not support the audio tag.

Season 1<br>Show Notes<br>Transcript<br>Guest Profile<br>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.<br>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.<br>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.

Timeline<br>00:00 Intro<br>00:55 1991 in Munich, and why that lab mattered<br>02:38 "I'm not very smart" and why compute getting 10× cheaper every 5 years changed everything<br>04:25 Chess as an AI proxy<br>08:27 Artificial curiosity in the 90s vs. today's RL exploration<br>09:10 Why RL is harder than supervised learning<br>20:48 Coding agents vs. robots, and how a baby learns its own hands<br>26:20 Compression as understanding<br>33:40 What's actually missing on the road to AGI<br>37:30 Why millisecond-by-millisecond planning is stupid<br>47:44 Convergence to LLMs, GPUs, and how far we still are from the Bremermann limit<br>51:49 Unsupervised learning, factorial codes, and predictability minimization<br>58:12 Credit assignment: the fights with LeCun and the Nobel critique<br>1:02:13 On his last name becoming a verb<br>1:05:17 The award system's missing peer review<br>1:07:03 Closed labs and the decline of open research<br>1:13:23 Audience questions<br>1:34:02 Closing: who really invented deep learning?

Music:<br>"Kid Kodi" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0.<br>"Palms Down" - Blue Dot Sessions - via Free Music Archive - CC BY-NC 4.0.<br>Changes: trimmed

About: 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.

Ravid Shwartz-Ziv: Everyone, Ravid here. Quick note before we start. We had so much fun talking with Jorgen that we decided to do another one. So this is the first of two episodes with Jorgen Schmidlberg. The second one is coming soon. Enjoy! everyone and welcome back to the information bottleneck Hey J&Atilde;&para;rgen!

Juergen: Hello, Ravid, and hello, Alan. How are you doing?

Allen Roush: We're doing great, I can tell you that. &acirc;“ How are you?

Juergen: That's fine. Thank you so much.

Ravid Shwartz-Ziv: maybe &acirc;“ tell us &acirc;“ you define or how you want to introduce yourself.

Juergen: My name is J&Atilde;&frac14;rgen and I'm interested in artificial intelligence.

Allen Roush: I think that's a bit of an understatement of the century.

Ravid Shwartz-Ziv: Okay. we can start with like, &acirc;“ I'm not if like this is the but like long time ago, right? 1991, okay. No one like the field is the offline machine learning and deep learning is so small, right? There is almost no money in it. &acirc;“ And &acirc;“ you have &acirc;“ a small medium &acirc;“ Germany &acirc;“ &acirc;“ then what? Tell why it's why such an important moment in time.

Juergen: So 1991 is the only palindromic year of the 20th century. And it was important for AI because in this little lab that you mentioned in Munich, we were able to come up with all kinds of algorithms which are now essential to what the big companies, the most valuable companies in the world are doing. A thousand billion dollars are being invested...