Vanishing Gradients

Episode 63: Why Gemini 3 Will Change How You Build AI Agents with Ravin Kumar (Google DeepMind)

November 22nd, 2025  |  1 hr 12 secs

ai, genai, machine learning

Gemini 3 is a few days old and the massive leap in performance and model reasoning has big implications for builders: as models begin to self-heal, builders are literally tearing out the functionality their built just months ago: ripping out the defensive coding and reshipping their agent harnesses entirely.

Ravin Kumar (Google DeepMind) joins Hugo to breaks down exactly why the rapid evolution of models like Gemini 3 is changing how we build software. They detail the shift from simple tool calling to building reliable "Agent Harnesses", explore the architectural tradeoffs between deterministic workflows and high-agency systems, the nuance of preventing context rot in massive windows, and why proper evaluation infrastructure is the only way to manage the chaos of autonomous loops.

Episode 62: Practical AI at Work: How Execs and Developers Can Actually Use LLMs

October 31st, 2025  |  59 mins 4 secs

agents, ai, data science, machine learning

Many leaders are trapped between chasing ambitious, ill-defined AI projects and the paralysis of not knowing where to start. Dr. Randall Olson argues that the real opportunity isn't in moonshots, but in the "trillions of dollars of business value" available right now. As co-founder of Wyrd Studios, he bridges the gap between data science, AI engineering, and executive strategy to deliver a practical framework for execution.

Episode 61: The AI Agent Reliability Cliff: What Happens When Tools Fail in Production

October 16th, 2025  |  28 mins 4 secs

agents, ai, machine learning, mlops

Most AI teams find their multi-agent systems devolving into chaos, but ML Engineer Alex Strick van Linschoten argues they are ignoring the production reality. In this episode, he draws on insights from the LLM Ops Database (750+ real-world deployments then; now nearly 1,000!) to systematically measure and engineer constraint, turning unreliable prototypes into robust, enterprise-ready AI.

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 59: Patterns and Anti-Patterns For Building with AI

September 24th, 2025  |  47 mins 37 secs

ai, data science, machine learning

John Berryman has seen what works — and what breaks — when building AI applications. In this episode, he shares the “seven deadly sins” of LLM development and the fixes that keep projects from falling apart. From context management to retrieval debugging, John explains the patterns he’s seen succeed, the mistakes to avoid, and why it helps to think of an LLM as an “AI intern” rather than an all-knowing oracle.

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 55: From Frittatas to Production LLMs: Breakfast at SciPy

August 13th, 2025  |  38 mins 8 secs

data science, generative ai, llm, machine learning, 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 group, and over breakfast at SciPy we explored why AI products break the old rules, what skills different personas bring (and miss), and how to keep systems alive after the launch hype fades.

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.