Podcast Episodes

Episode 59: Patterns and Anti-Patterns For Building with AI

John Berryman (Arcturus Labs; early GitHub Copilot engineer; co-author of Relevant Search and Prompt Engineering for LLMs) has spent years figuring out what makes AI applications actually work in pro…

Published on 11 hours ago

Episode 58: Building GenAI Systems That Make Business Decisions with Thomas Wiecki (PyMC Labs)

While most conversations about generative AI focus on chatbots, Thomas Wiecki (PyMC Labs, PyMC) has been building systems that help companies make actual business decisions. In this episode, he share…

Published on 2 weeks ago

Episode 57: AI Agents and LLM Judges at Scale: Processing Millions of Documents (Without Breaking the Bank)

While many people talk about “agents,” Shreya Shankar (UC Berkeley) has been building the systems that make them reliable. In this episode, she shares how AI agents and LLM judges can be used to proc…

Published on 3 weeks, 4 days ago

Episode 56: DeepMind Just Dropped Gemma 270M... And Here’s Why It Matters

While much of the AI world chases ever-larger models, Ravin Kumar (Google DeepMind) and his team build across the size spectrum, from billions of parameters down to this week’s release: Gemma 270M, t…

Published on 1 month, 1 week ago

Episode 55: From Frittatas to Production LLMs: Breakfast at SciPy

Traditional software expects 100% passing tests. In LLM-powered systems, that’s not just unrealistic — it’s a feature, not a bug. Eric Ma leads research data science in Moderna’s data science and AI …

Published on 1 month, 1 week ago

Episode 54: Scaling AI: From Colab to Clusters — A Practitioner’s Guide to Distributed Training and Inference

Season 1

Colab is cozy. But production won’t fit on a single GPU.
Zach Mueller leads Accelerate at Hugging Face and spends his days helping people go from solo scripts to scalable systems. In this episode, he…

Published on 2 months ago

Episode 53: Human-Seeded Evals & Self-Tuning Agents: Samuel Colvin on Shipping Reliable LLMs

Season 1

Demos are easy; durability is hard. Samuel Colvin has spent a decade building guardrails in Python (first with Pydantic, now with Logfire), and he’s convinced most LLM failures have nothing to do wit…

Published on 2 months, 2 weeks ago

Episode 52: Why Most LLM Products Break at Retrieval (And How to Fix Them)

Season 1

Most LLM-powered features do not break at the model. They break at the context. So how do you retrieve the right information to get useful results, even under vague or messy user queries?

In this epi…

Published on 2 months, 3 weeks ago

Episode 51: Why We Built an MCP Server and What Broke First

Season 1

What does it take to actually ship LLM-powered features, and what breaks when you connect them to real production data?

In this episode, we hear from Philip Carter — then a Principal PM at Honeycomb …

Published on 2 months, 4 weeks ago

Episode 50: A Field Guide to Rapidly Improving AI Products -- With Hamel Husain

Season 1

If we want AI systems that actually work, we need to get much better at evaluating them, not just building more pipelines, agents, and frameworks.

In this episode, Hugo talks with Hamel Hussain (ex-A…

Published on 3 months, 1 week ago