Topic: coding agents

Dimitris Papailiopoulos of Microsoft Research and the University of Wisconsin discusses how coding agents change scientific research. The conversation covers small arithmetic transformers, symbolic mathematical reasoning, interacting agents, and the role of human judgment and verification. It also examines diversity in machine-generated ideas, benchmark and harness overfitting, persistent agent errors, continual learning, world models, and where information theory helps explain AI. Hosted by Ravid Shwartz Ziv and Allen Roush; the full conversation is available on the publisher's YouTube channe

Alexandre Pesant discusses the capabilities and limits of coding agents and development through natural-language intent. Topics include context engineering, changes between workflow-based and agentic architectures, scaling challenges, evaluations and interface design. The conversation examines how model improvements influence practical software-development tools.