The Stack Overflow Podcast

Kayvon Beykpour, the CEO of Macroscope and a tech entrepreneur known for co-founding Periscope, shares insights on the transformative role of AI in code review. He discusses the challenges of visibility in large codebases and how Macroscope's AI tools can streamline project summaries and bug detection. Kayvon elaborates on using abstract syntax trees for precise context and the importance of human oversight. He envisions a future where AI enhances engineers' productivity, allowing them to focus on more complex problems.

Guillaume de Saint-Marc, VP of Engineering at Outshift by Cisco, dives deep into the exciting world of multi-agent architectures and their future as microservices. He explains the shift from single LLMs to collaborating specialized agents tailored for enterprise needs. The importance of communication protocols, security challenges, and creating an interoperable ecosystem are covered. Guillaume also discusses innovative tools like Slim for secure group messaging and highlights the potential applications and limitations of agentic systems.

Simone Kalamakis, VP of Engineering at Viam, dives into the world of robotics, sharing her journey from tech at Microsoft to leading innovative projects. She highlights Viam's software abstraction platform, making robotics accessible with modular tools. From lobster traps to industrial sanding robots, Simone discusses diverse applications, the integration of AI, and the challenges of hardware iteration. She also emphasizes the significance of observability and security in robotic systems, showcasing how technology transforms real-world tasks.

Darryl Lyons, Co-founder and Chief Rainmaker at Rainstick, explores exciting advancements in agricultural technology. He explains how Rainstick mimics thunderstorms, creating electric fields that enhance plant growth. This lightning-inspired approach addresses challenges in agriculture and leverages bioelectricity, combining indigenous knowledge with modern science. Darryl shares insights on the impressive scale of their research, sophisticated data modeling, and plans to automate phenotyping for improved crop yields. It's a fascinating blend of tradition and innovation!

Jared Quincy Davis, CEO and co-founder of Mithril, dives into the fascinating world of GPU utilization. He challenges the notion of a GPU shortage, asserting that inefficiencies in resource allocation are the real issue. Jared discusses how multi-cloud orchestration can optimize GPU usage and why many clouds still rely on single-tenant allocations. He also explores the benefits of using older GPUs for certain workloads and advocates for a mixed fleet approach using specialized models. Get ready to rethink your GPU strategy!

David Hsu, CEO and founder of Retool, dives into the revolution AI is bringing to software engineering. He discusses the evolving role of developers as architects rather than coders and the potential risks non-engineers face when using AI tools. Hsu emphasizes the need for guardrails to protect against dangerous outputs and explores how specialized programming primitives can enhance safety. He also talks about the increasing automation of tools and tasks, highlighting how AI can take on roles in sales and support while leaving creative verification to humans.

Assaf Elovic, Head of AI at monday.com, shares insights on building AI tools people genuinely want to use. He discusses the initial failures of their chatbot and the importance of aligning user expectations with product design. Elovic emphasizes that user adoption outweighs technical perfection and explains how they revamped Monday Sidekick for better user experience. He highlights the potential of autonomous agents and voice technology, discussing how these innovations can enhance productivity while ensuring trust in automated systems.

Benjamin Klieger, the lead engineer at Groq, shares insights on AI agent infrastructure. He discusses the groundbreaking Compound agent that effectively searches the web and executes tasks quickly. Benjamin explains how Groq’s custom LPU hardware allows for lightning-fast inference, transforming a one-minute process into mere seconds. He also touches on the importance of dynamic evals and real-time datasets, critiquing traditional benchmarks for their lack of novelty. Join him as he explores the future of efficient AI agents and the metrics that define their success.

Ramprasad Rai, VP of Platform Engineering at JPMorgan Chase & Co., dives into the challenges of deploying AI in regulated environments. He emphasizes the necessity of community-driven knowledge to ground AI tools, preventing hallucinations that arise from a lack of context. Rai discusses how Stack Overflow's structured Q&A can finely tune AI models and foster trust in generated code. He highlights the importance of active learning loops to maintain institutional expertise and the potential of Stack Overflow as a vital knowledge layer for AI-driven developer tools.

Matias Madou, Co-founder and CTO of Secure Code Warrior, dives into the evolving landscape of AI in coding, emphasizing the critical thinking skills necessary for developers, especially newcomers. He highlights the potential pitfalls of AI-generated code, from common errors to the challenges of understanding AI outputs. Matias stresses the importance of robust training in security and design principles, warning against overreliance on AI that could lead to complacency. The conversation also touches on the changing role of developers as AI democratizes coding, raising new organizational risks.