Software Engineering podcasts

Diogo Almeida joins Sam Charrington to discuss TypeSafe's Jev model and the use of calibrated decisions as a component of AI software. The conversation examines reinforcement learning from calibrated decisions, differences from classifiers and text-generating models, and the implications for agents, tool use and system architecture.

Hosted by Sam Charrington

Nick Kuhn joins Daniel Whitenack and Chris Benson to discuss deploying AI agents alongside conventional enterprise applications. Topics include agent build packs, MCP gateways, shared memory, identity, sandboxing and lessons from platform engineering.

Hosted by Daniel Whitenack, Chris Benson

Demetrios Brinkmann and Chris Benson discuss agents that operate computers and interact with software. They examine MCP, agent harnesses, interactions between agents, emerging commerce workflows and the practical challenges of using these tools in enterprise environments.

Hosted by Chris Benson

Chetan Gupta joins Daniel Whitenack and Chris Benson to discuss the importance of system architecture when moving AI into enterprise use. The conversation connects industrial and physical AI with deployment, governance and sovereignty, considering how organizations can make practical design choices.

Hosted by Daniel Whitenack, Chris Benson

Angie Jones discusses the shared infrastructure needed for practical AI agents, including interoperability and open standards. The conversation covers MCP, agent-to-agent communication and Goose, asking how common foundations can make tools easier to connect and reduce fragmentation as organizations adopt agent systems.

Hosted by Chris Benson

Chris Benson and Daniel Whitenack separate the roles of models, agents and the software harnesses that run them. They discuss architectural choices for multi-agent systems, practical deployment considerations, and how openness and dependency on particular vendors influence the systems developers can build.

Hosted by Chris Benson, Daniel Whitenack

PufferAI researcher Joseph Suarez argues that implementation and simulation bottlenecks have constrained reinforcement learning as much as algorithm choice. He discusses the design of useful simulators, CPU and GPU trade-offs, faster training pipelines and open-source research tools. The conversation ranges from game environments to potential applications in scientific simulation and biological modelling. Hosted by Ravid Shwartz Ziv and Allen Roush. Watch the full conversation on the publisher’s YouTube channel.

Hosted by Ravid Shwartz Ziv, Allen Roush

Berkeley professor Ion Stoica discusses how research software becomes useful infrastructure and, sometimes, a company. The conversation draws on systems projects and companies associated with his laboratory to examine adoption, maintenance and the role of students. It also covers the complexity of the AI software stack, GPU utilization, coding agents in distributed systems, reward design and regulating outcomes. Hosted by Ravid Shwartz Ziv and Allen Roush. Watch the full conversation on the publisher’s YouTube channel.

Hosted by Ravid Shwartz Ziv, Allen Roush

NVIDIA researcher Jean-Francois Puget discusses evaluating agent skills and distinguishing real improvements from benchmark overfitting. Drawing on Kaggle competitions, he emphasizes validation that separates development feedback from final evaluation. The episode also considers coding agents, multi-agent software development, model-release claims and his team’s approach to the ARC-AGI competition. Hosted by Ravid Shwartz Ziv and Allen Roush. Watch the full conversation on the publisher’s YouTube channel.

Hosted by Ravid Shwartz Ziv, Allen Roush

Hamza Tahir discusses how experience with MLOps can inform more reliable agent systems. The conversation covers workflow execution, replayability and observability, including the design of agent harnesses and how ZenML's Kitaru approaches the practical work of running agents in production.

Hosted by Daniel Whitenack

Fireworks AI co-founder Benny Chen explains the infrastructure required to serve machine-learning models at scale, from GPU procurement and kernels to runtimes and request routing. He discusses power constraints, hardware utilization, mixture-of-experts models, quantization, reinforcement-learning efficiency and speculative decoding. The conversation also covers distributed training across data centres, sparse autoencoders, the constraints on open-source interpretability research, and the relationship between open models and compute availability. Hosted by Ravid Shwartz Ziv and Allen Roush; the full conversation is available on YouTube.

Hosted by Ravid Shwartz Ziv, Allen Roush

Devvret Rishi discusses how agents with access to tools and external systems change the security requirements of generative AI applications. He examines the limitations of static controls and the need for runtime policies, observability and recovery mechanisms as agent workflows become more capable.

Hosted by Sam Charrington

Alex Bowcut draws lessons from building an AI system for tax-law research. He explains why retrieval still matters with long-context models, how chunking and combined retrieval methods affect results, and why reliable citations and feedback from domain experts are central to evaluating a specialized application.

Hosted by Sam Charrington