
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Scaling Up Test-Time Compute with Latent Reasoning with Jonas Geiping - #723
Mar 17, 2025
Jonas Geiping, a research group leader at the Ellis Institute and Max Planck Institute for Intelligent Systems, discusses innovative approaches to AI efficiency. He introduces a novel recurrent depth architecture that enables latent reasoning, allowing models to predict tokens with dynamic compute allocation based on difficulty. Geiping contrasts internal and verbalized reasoning in AI, explores challenges in scaling models, and highlights the architectural advantages that enhance performance in reasoning tasks. His insights pave the way for advancements in machine learning efficiency.
58:38
Episode guests
AI Summary
AI Chapters
Episode notes
Podcast summary created with Snipd AI
Quick takeaways
- The podcast discusses a novel AI architecture that enables models to think in latent space, improving reasoning and performance during evaluation.
- It contrasts traditional RNNs with a recurrent depth strategy that allows flexible layer repetition, decoupling computation from output production for improved scalability.
Deep dives
Divergent Thinking Approaches
Humans often have the capacity to think about problems without immediately verbalizing their solutions. The podcast delves into the concept that people utilize two distinct axes for scaling their computation and reasoning. This duality suggests that individuals do not always process thoughts linearly, but may simultaneously engage in various cognitive processes. The conversation emphasizes that both humans and models can leverage these different methodologies, enabling more flexible approaches to problem-solving.
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.