Ep. #6, Why AI Needs to Argue with Itself with James Evans

On episode 14 of Data Renegades, CL Kao speaks with Hannes Mühleisen, co-creator of DuckDB, about building databases that people actually want to use. Hannes explains how conversations with frustrated statisticians shaped DuckDB’s architecture and why useful software sometimes requires abandoning your own assumptions. They explore DuckLake, the Quack client-server protocol, and how a focus on human usability is paying off as AI agents begin choosing their own tools.

On episode 6 of Lab Notes, Amir Zohrenejad speaks with James Evans about the surprising finding that reasoning models simulate a society rather than a single brain. They dig into sycophancy and why users trust AI less but perform better when it has a point of view, the Computational Life experiments that evolved self-replicating programs from a primordial soup of code, and James’s argument that diverse novel ideas are about to become the scarcest resource on the planet.

On episode 45 of Open Source Ready, Brian Douglas and John McBride speak with Dotta about Paperclip, an open-source platform for managing teams of AI agents. They explore what happens when agents produce more work than humans can review, why permissions need to extend beyond a separate computer, and how engineering judgment changes when writing code becomes easier.

On episode 13 of Third Loop, the Progressive Delivery team speaks with Jennifer Riggins about why faster code doesn’t automatically mean better software. They explore how AI exposes organizational bottlenecks, why psychological safety matters, and what Spotify’s growing feature set reveals about user value. Jennifer makes the case for smaller experiments, stronger feedback loops, and keeping people at the center of delivery.

On episode 60 of Generationship, Rachel Chalmers speaks with Vasanth Mohan of SambaNova about when faster AI agents actually mean better work. They explore why token consumption and code volume are poor substitutes for business value, how inference latency interrupts productive workflows, and why engineering taste still matters. Sometimes the most valuable thing an engineer can produce is less code.

On episode 44 of Open Source Ready, Brian Douglas and John McBride sit down with Mikyo King to explore why an agent can fail even when its model gets things right. They discuss observing the full agent workflow, using evaluations to uncover unexpected behavior, and testing whether skills actually improve results. Along the way, Mikyo shares how Arize approaches open source collaboration as coding agents reshape the contribution process.

On episode 12 of Third Loop, the Progressive Delivery team speaks with Steph Hippo, Platform Engineering Director at Honeycomb, about what happens when AI accelerates development beyond the pace humans can absorb. They explore safe defaults, evolving code reviews, and the feedback loops that help teams understand what they ship. Steph makes the case for reinvesting saved time in better decisions, software quality, and human connection.

On episode 59 of Generationship, Rachel Chalmers speaks with Emily Long and Alex Zenla, co-founders of Edera, about rethinking the foundations of cloud and AI security. They explain how an IoT side project became an approach to workload isolation built around Xen and Rust, and why AI agents are making stronger security boundaries increasingly urgent. Along the way, they discuss complementary leadership skills, fundraising lessons, and the value of questioning the industry’s technical assumptions.

In episode 5 of Lab Notes, Amir Zohrenejad speaks with Aoden Teo, co-founder and CEO of Miso Labs, about what it will take for voice AI to become truly humanlike. They explore the limitations of today's speech-to-text and text-to-speech pipelines, the promise of full-duplex speech models, and the technical challenges around audio tokenization, turn-taking, emotion, reasoning, and real-time inference.

On episode 11 of Third Loop, the Progressive Delivery team sits down with Chad Fowler to explore regenerative software and what architecture looks like when AI makes code cheap enough to continually replace. They discuss Phoenix Architecture, Pace Layers, observability, architectural constraints, and why the system itself, rather than any individual implementation, may become the real asset in an AI-native future.