Build Wiz AI Show

• Training-Free Group Relative Policy Optimization for LLM Agents

  Are expensive Large Language Model (LLM) fine-tuning methods holding back your specialized agents, demanding massive computational resources and data? We dive into Training-Free Group Relative Policy Optimization (Training-Free GRPO), a novel non-parametric method that enhances LLM agent behavior by distilling semantic advantages from group rollouts into lightweight token priors, eliminating costly parameter updates. Discover how this highly efficient approach achieves significant performance gains in specialized domains like mathematical reasoning and web searching, often surpassing traditional fine-tuning while using only dozens of training samples.

  --------  

  13:38

  --------

  13:38
• OpenAI's Vision: AGI, Sora, and Bottlenecks

  Join us for a deep dive with Greg Brockman on the future of AI, where he reveals the internal struggle ("pain and suffering") of managing compute scarcity and the immense physical infrastructure build required to scale systems like Sora 2. Brockman discusses the shift from viewing AGI as a destination to a continuous process, emphasizing that current scaling curves and algorithmic progress continue unabated. We also explore the inevitable move toward proactive AI agents and a fully generative web, predicting a major change to the social contract and web monetization.

  --------  

  12:21

  --------

  12:21
• Agentic Context Engineering: Evolving Contexts for LLMs

  Tune in as we explore Agentic Context Engineering (ACE), a novel framework designed to overcome limitations like "brevity bias" and "context collapse" that plague traditional LLM context adaptation methods. ACE transforms model contexts into continuously evolving, structured "playbooks" by employing a modular process of generation, reflection, and curation. We discuss how this approach enables scalable, self-improving agents, yielding substantial performance gains on complex tasks—such as +10.6% on agent benchmarks—while significantly lowering adaptation latency and cost.

  --------  

  16:35

  --------

  16:35
• Less is More: Recursive Reasoning with Tiny Networks

  This episode explores the Tiny Recursive Model (TRM), a novel approach that leverages a single, tiny network (as small as 7M parameters) to tackle hard puzzle tasks like Sudoku, Maze, and ARC-AGI. We investigate how this simplified, recursive reasoning strategy achieves significantly higher generalization and outperforms much larger models, including complex Large Language Models (LLMs) and the Hierarchical Reasoning Model (HRM). Discover why this "less is more" philosophy is leading to breakthroughs in parameter-efficient AI reasoning by simplifying complex mathematical theories and biological justifications.

  --------  

  14:28

  --------

  14:28
• Understanding the 4 Main Approaches to LLM Evaluation - from Sebastian Raschka

  Demystify Large Language Model (LLM) evaluation, breaking down the four main methods used to compare models: multiple-choice benchmarks, verifiers, leaderboards, and LLM judges. We offer a clear mental map of these techniques, distinguishing between benchmark-based and judgment-based approaches to help you interpret performance scores and measure progress in your own AI development. Discover the pros and cons of each method—from MMLU accuracy checks to the dynamic Elo ranking system—and learn why combining them is key to holistic model assessment.Original blog post: https://magazine.sebastianraschka.com/p/llm-evaluation-4-approaches

  --------  

  15:16

  --------

  15:16

More Technology podcasts

Trending Technology podcasts

About Build Wiz AI Show