Vanishing Gradients
Hugo Bowne-Anderson
A podcast about all things data, brought to you by data scientist Hugo Bowne-Anderson.
It's time for more critical conversations about the challenges in our industry in order to build better compasses for the solution space! To this end, this podcast will consist of long-format conversations between Hugo and other people who work broadly in the data science, machine learning, and AI spaces. We'll dive deep into all the moving parts of the data world, so if you're new to the space, you'll have an opportunity to learn from the experts. And if you've been around for a while, you'll find out what's happening in many other parts of the data world.
It's time for more critical conversations about the challenges in our industry in order to build better compasses for the solution space! To this end, this podcast will consist of long-format conversations between Hugo and other people who work broadly in the data science, machine learning, and AI spaces. We'll dive deep into all the moving parts of the data world, so if you're new to the space, you'll have an opportunity to learn from the experts. And if you've been around for a while, you'll find out what's happening in many other parts of the data world.
Episodes
Mentioned books
62 snips
Dec 3, 2025 • 1h 3min
Episode 64: Data Science Meets Agentic AI with Michael Kennedy (Talk Python)
In this discussion, Michael Kennedy, a seasoned Python developer and educator known for his insights on AI and software practices, tackles the myth of complexity in tech. He shares how to simplify production Python systems, emphasizing the importance of the 'Docker barrier' for cost-effective self-hosting. The conversation explores how Agentic AI is shifting development mindsets and enhancing efficiency. Michael also stresses the value of struggling through learning and the need for complementary skills in navigating the evolving tech landscape.
103 snips
Nov 22, 2025 • 1h
Episode 63: Why Gemini 3 Will Change How You Build AI Agents with Ravin Kumar (Google DeepMind)
Ravin Kumar, a researcher at Google DeepMind specializing in generative models and LLM products, joins to discuss the groundbreaking Gemini 3. They illustrate how models can 'self-heal' and adapt, reshaping software development. Topics include the transition from basic tool calling to advanced agent harnesses, the contrast between deterministic workflows and high-agency systems, and the importance of robust evaluation infrastructures. Ravin also shares insights on the evolution of productive features like Audio Overviews and the future of multimodal agents.
53 snips
Oct 31, 2025 • 59min
Episode 62: Practical AI at Work: How Execs and Developers Can Actually Use LLMs
Dr. Randall Olson, co-founder of Wyrd Studios and AI strategist, dives into practical AI applications that can unlock immediate value for businesses. He discusses how non-technical leaders can quickly prototype tools using ChatGPT, emphasizing the significance of starting small with achievable tasks. Randall urges a disciplined approach to AI evaluation akin to software testing, highlights overlooked opportunities for automation, and advocates for iterative experimentation to foster innovation in the workplace. Transforming mundane problems into streamlined solutions is key!
51 snips
Oct 16, 2025 • 28min
Episode 61: The AI Agent Reliability Cliff: What Happens When Tools Fail in Production
In a fascinating discussion, Alex Strick van Linschoten, a machine learning engineer at ZenML and curator of the LLM Ops Database, delves into the complexities of multi-agent systems. He emphasizes the dangers of introducing too many agents, advocating for simplicity and reliability. Alex shares key insights from nearly 1,000 real-world deployments, highlighting the importance of MLOps hygiene, human-in-the-loop strategies, and using basic programming checks over costly LLM judges. His practical advice on scaling down systems is a must-listen for AI developers!
149 snips
Sep 30, 2025 • 1h 13min
Episode 60: 10 Things I Hate About AI Evals with Hamel Husain
Hamel Husain, a machine learning engineer and evals expert, discusses the pitfalls of AI evaluations and how to adopt a data-centric approach for reliable results. He outlines ten critical mistakes teams make, debunking ineffective metrics like 'hallucination scores' in favor of tailored analytics. Hamel shares a workflow for effective error analysis, including involving domain experts wisely and avoiding hasty automation. Bryan Bischoff joins as a guest to introduce the 'Failure as a Funnel' concept, emphasizing focused debugging for complex AI systems.
34 snips
Sep 23, 2025 • 48min
Episode 59: Patterns and Anti-Patterns For Building with AI
In this engaging discussion, John Berryman, Founder of Arcturus Labs and an early engineer on GitHub Copilot, dives into the real-world challenges of building AI applications. He highlights the 'seven deadly sins' of LLM development, offering practical solutions to keep projects moving. John explains why aspiring for perfect accuracy may hinder progress and shares insights on context management and retrieval debugging. Treating an LLM like a forgetful intern, he emphasizes starting simply and avoiding unnecessary complexity for successful deployment.
Sep 9, 2025 • 1h 1min
Episode 58: Building GenAI Systems That Make Business Decisions with Thomas Wiecki (PyMC Labs)
Thomas Wiecki, founder of PyMC Labs and co-author of PyMC, dives into how generative AI can shape business decisions. He discusses using large language models as synthetic consumers to test product ideas, revealing the efficiency of AI over traditional surveys. Thomas emphasizes Bayesian modeling's role in providing trustworthy insights and navigating complex data. His experience with Colgate highlights the iterative design of AI systems for better product and marketing strategies, urging a balance between innovative models and reliability.
12 snips
Aug 29, 2025 • 41min
Episode 57: AI Agents and LLM Judges at Scale: Processing Millions of Documents (Without Breaking the Bank)
Shreya Shankar, a PhD candidate at UC Berkeley with experience at Google Brain and Facebook, dives into the world of AI agents and document processing. She sheds light on how LLMs can efficiently handle vast amounts of data, maintaining accuracy without breaking the bank. Topics include the importance of human error review, the intricacies of transforming LLM workflows into reliable pipelines, and the balance of using cheap vs. expensive models. Shreya also discusses how guardrails and structured approaches can enhance LLM outputs in real-world applications.
Aug 14, 2025 • 46min
Episode 56: DeepMind Just Dropped Gemma 270M... And Here’s Why It Matters
Ravin Kumar, a researcher at Google DeepMind, dives into the newly launched Gemma 270M, the smallest member of the Gemma 3 family of AI models. He explains its efficiency and speed, perfect for on-device use cases where privacy and latency are crucial. Kumar discusses the strategic advantages of smaller models for fine-tuning and targeted tasks, emphasizing their potential to drive broader AI adoption. Listeners will learn how to leverage 270M for specific applications and compare it with larger models in diverse scenarios.
Aug 12, 2025 • 38min
Episode 55: From Frittatas to Production LLMs: Breakfast at SciPy
Join Eric Ma, who heads research data science at Moderna, as he discusses the wild world of AI systems over breakfast at SciPy. He reveals why 'perfect' testing can lead you astray and introduces three key personas in AI development, each with unique blind spots. Discover how curiosity can elevate builders from good to great, and learn about maintaining observability in both development and production. Eric also shares insights on fostering experimentation in large organizations, embracing the chaos that comes with creating thriving AI products.
