Vanishing Gradients

Episode 60: 10 Things I Hate About AI Evals with Hamel Husain

September 30th, 2025  |  1 hr 13 mins

ai, data science, evals, genai, llms, machine learning

Most AI teams find "evals" frustrating, but ML Engineer Hamel Husain argues they’re just using the wrong playbook. In this episode, he lays out a data-centric approach to systematically measure and improve AI, turning unreliable prototypes into robust, production-ready systems.

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

August 29th, 2025  |  41 mins 27 secs

agents, llms, machine learning, rag

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 process millions of documents accurately and cheaply.

Drawing from work on projects ranging from databases of police misconduct reports to large-scale customer transcripts, Shreya explains the frameworks, error analysis, and guardrails needed to turn flaky LLM outputs into trustworthy pipelines

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

August 15th, 2025  |  45 mins 40 secs

genai, llms, machine learning

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, the smallest member yet of the Gemma 3 open-weight family. At just 270 million parameters, a quarter the size of Gemma 1B, it’s designed for speed, efficiency, and fine-tuning.

We explore what makes 270M special, where it fits alongside its billion-parameter siblings, and why you might reach for it in production even if you think “small” means “just for experiments.”

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

July 3rd, 2025  |  Season 1  |  28 mins 38 secs

ai, data science, genai, llms, machine learning

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 episode, we hear from Eric Ma, who leads data science research in the Data Science and AI group at Moderna. He shares what it takes to move beyond toy demos and ship LLM features that actually help people do their jobs.

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

June 27th, 2025  |  Season 1  |  47 mins 41 secs

ai, data science, llms, machine learning

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 and now a Product Management Director at Salesforce. In early 2023, he helped build one of the first LLM-powered SaaS features to ship to real users. More recently, he and his team built a production-ready MCP server.

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

June 17th, 2025  |  Season 1  |  27 mins 42 secs

ai, data science, evals, llms, machine learning

Hugo talks with Hamel Hussain (ex-Airbnb, GitHub, DataRobot) about how to improve AI products through evaluation, error analysis, and iteration. They discuss why most teams overlook debugging LLM systems, how to prioritize what to fix, and why evals are not just metrics—but a full development process.

Episode 49: Why Data and AI Still Break at Scale (and What to Do About It)

June 5th, 2025  |  Season 1  |  1 hr 21 mins

ai, data science, llms, machine learning

Hugo talks with Akshay Agrawal (Marimo, ex-Google Brain, Netflix, Stanford) about why data and AI systems still break at scale—and what it takes to fix them. They dive into the limits of existing workflows, the importance of reproducibility and reactive execution, and how Marimo reimagines notebooks for modern software development.

Episode 47: The Great Pacific Garbage Patch of Code Slop with Joe Reis

April 7th, 2025  |  Season 1  |  1 hr 19 mins

ai, data science, genai, llms, machine learning, vibe coding

What if the cost of writing code dropped to zero — but the cost of understanding it skyrocketed?

In this episode, Hugo sits down with Joe Reis to unpack how AI tooling is reshaping the software development lifecycle — from experimentation and prototyping to deployment, maintainability, and everything in between.

Episode 46: Software Composition Is the New Vibe Coding

April 3rd, 2025  |  Season 1  |  1 hr 8 mins

ai, data science, genai, llms, machine learning, vibe coding

What if building software felt more like composing than coding?

In this episode, Hugo and Greg explore how LLMs are reshaping the way we think about software development—from deterministic programming to a more flexible, prompt-driven, and collaborative style of building. It’s not just hype or grift—it’s a real shift in how we express intent, reason about systems, and collaborate across roles.

Hugo speaks with Greg Ceccarelli—co-founder of SpecStory, former CPO at Pluralsight, and Director of Data Science at GitHub—about the rise of software composition and how it changes the way individuals and teams create with LLMs.

Episode 44: The Future of AI Coding Assistants: Who’s Really in Control?

February 4th, 2025  |  Season 1  |  1 hr 34 mins

ai, data science, llms, machine learning

AI coding assistants are reshaping how developers write, debug, and maintain code—but who’s really in control? In this episode, Hugo speaks with Tyler Dunn, CEO and co-founder of Continue, an open-source AI-powered code assistant that gives developers more customization and flexibility in their workflows.