Best Great Pacific Garbage Patch Podcasts (2025)

1
Episode 62: Practical AI at Work: How Execs and Developers Can Actually Use LLMs 59:04

Play Pause

12d ago59:04

59:04

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 engine…

1
Episode 61: The AI Agent Reliability Cliff: What Happens When Tools Fail in Production 28:04

28d ago28:04

28:04

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 pro…

1
Episode 60: 10 Things I Hate About AI Evals with Hamel Husain 1:13:15

1M ago1:13:15

1:13:15

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. Drawing from his experience getting countless teams unstuck, Hamel expl…

1
Episode 59: Patterns and Anti-Patterns For Building with AI 47:37

1M ago47:37

47:37

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 production. In this episode, he shares the “seven deadly sins” of LLM development — and the practical fixes that keep projects from stalling. From context…

1
Episode 58: Building GenAI Systems That Make Business Decisions with Thomas Wiecki (PyMC Labs) 1:00:45

2M ago1:00:45

1:00:45

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 shares how Bayesian modeling and synthetic consumers can be combined with LLMs to simulate customer reactions, guide marketing spend, and support strategy. …

1
Episode 57: AI Agents and LLM Judges at Scale: Processing Millions of Documents (Without Breaking the Bank) 41:27

3M ago41:27

41:27

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 cust…

1
Episode 56: DeepMind Just Dropped Gemma 270M... And Here’s Why It Matters 45:40

3M ago45:40

45:40

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, effi…

1
Episode 55: From Frittatas to Production LLMs: Breakfast at SciPy 38:08

3M ago38:08

38:08

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 sy…

1
Climate Change Is Here For Your Chocolate 13:27

3M ago13:27

13:27

Last year, we reported how extreme weather events may be dwindling the future of chocolate. Just last week, we saw an inkling of that: The Hershey Company announced it would significantly raise the cost of its candy in the face of historically high cocoa prices. So, we're revisiting host Emily Kwong's conversation with Yasmin Tayag, a food, health …

1
This Underwater Sculpture Garden Protects Italian Fishing Grounds 7:53

4M ago7:53

7:53

Mermaids, giants and huge eyes look up from the waters near Talamone, Italy. It's one fisherman's way of protecting fishing grounds from the damage of trawling nets. Artists' sculptures are sunk to the bottom of the Mediterranean sea along with concrete blocks to break the nets of the trawlers that devastate marine life. Learn more about sponsor me…

1
Nature Quest: Are Summers Getting Hotter? 13:47

4M ago13:47

13:47

Much of the country is deep in the middle of a heat wave right now. And every summer, Duane Stilwell's town in Arizona seems to get hotter. It has him worried — and he's not the only one. Since 1980, the average number of heat waves in the U.S has doubled and the average length of a heat wave season has increased from 40 days to 70. Future summers,…

1
Sea Camp: The Largest Daily Migration On Earth 12:47

4M ago12:47

12:47

The twilight zone of the ocean is a mysterious place. At 200-1000 meters below the surface, it's a tough place to study. That's why, during World War II, people reading sonograms from this zone were perplexed when it looked as if the ocean floor was moving up. Every day. And then back down again before dawn. In this latest installment of Sea Camp, …

1
Sea Camp: Is Better Human Health Hidden In The Sea? 13:00

4M ago13:00

13:00

For this week's Sea Camp, we're diving below the ocean's surface to explore the sunlight zone, the portion of ocean that's 0-200 meters deep. Here, we zoom in on some spineless inhabitants envied for their "superpowers." Marine biologist Drew Harvell tells us about stealthy sea slugs, sea stars with super strength and life-saving sponges. Also, exc…

1
The Downstream Effects of China's Rare Earth Mining 6:17

4M ago6:17

6:17

China has nearly cornered the market in rare earth minerals, which are a necessary component to much of our technology today. But China sources some of those rare earths and other heavy metals from neighboring Myanmar. And the ramped up in production there is causing downstream environmental concerns in Thailand. We go to Thailand to understand the…

1
Episode 54: Scaling AI: From Colab to Clusters — A Practitioner’s Guide to Distributed Training and Inference 41:17

4M ago41:17

41:17

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 joins me to demystify distributed training and inference — not just for research labs, but for any ML engineer trying to ship real software. We talk t…

1
Sea Camp: These Critters Call The Great Pacific Garbage Patch Home 14:35

4M ago14:35

14:35

For this second installment of the Sea Camp series, we explore the Great Pacific Garbage Patch. It's the largest of five gigantic garbage patches in the sea. These patches hang out at the nexus of the world's ocean currents, changing shape with the waves. These areas were long thought to have been uninhabited, the plastics and fishing gear too harm…

1
When old oil wells become 'orphans,' that's a problem 7:58

4M ago7:58

7:58

All across the U.S., there are aging oil and natural gas wells no longer in use. A lot of them don't have anyone on the hook to seal them up. Some estimate over a million such "orphan wells" still exist. Because they haven't been plugged, they're still leaking greenhouse gases and other chemicals into the atmosphere and into the land around them. W…

1
After devastating floods a Central Texas community comes together 10:53

4M ago10:53

10:53

It's been nearly a week since devastating flooding tore through Kerr County, Texas killing more than a hundred people. Now, after unimaginable tragedy, residents are coming together to help each other move forward. NPR's Juana Summers and producers Erika Ryan and Tyler Bartlam visited the City West Church, which has transformed from a house of wors…

1
Itchy? Air Pollution May Be Making It Worse 13:11

4M ago13:11

13:11

Short Wave producer Hannah Chinn has adult-onset eczema. They're not the only one. Up to ten percent of people in the United States have it, according to the National Eczema Association — and its prevalence is increasing. Despite its ubiquity, a lot about this skin condition remains a mystery. So today, Hannah's getting answers. In this encore epis…

1
Episode 53: Human-Seeded Evals & Self-Tuning Agents: Samuel Colvin on Shipping Reliable LLMs 44:49

4M ago44:49

44:49

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 with the model itself. They appear where the data is fuzzy, the prompts drift, or no one bothered to measure real-world behavior. Samuel joins me to show …

1
Episode 52: Why Most LLM Products Break at Retrieval (And How to Fix Them) 28:38

4M ago28:38

28:38

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 dem…

1
Episode 51: Why We Built an MCP Server and What Broke First 47:41

5M ago47:41

47:41

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. M…

1
Episode 50: A Field Guide to Rapidly Improving AI Products -- With Hamel Husain 27:42

5M ago27:42

27:42

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-Airbnb, GitHub, DataRobot) about how teams can improve AI products by focusing on error analysis, data inspection, and systematic iteration. The convers…

1
Episode 49: Why Data and AI Still Break at Scale (and What to Do About It) 1:21:45

5M ago1:21:45

1:21:45

If we want AI systems that actually work in production, we need better infrastructure—not just better models. In this episode, Hugo talks with Akshay Agrawal (Marimo, ex-Google Brain, Netflix, Stanford) about why data and AI pipelines still break down at scale, and how we can fix the fundamentals: reproducibility, composability, and reliable execut…

1
Episode 48: HOW TO BENCHMARK AGI WITH GREG KAMRADT 1:04:25

6M ago1:04:25

1:04:25

If we want to make progress toward AGI, we need a clear definition of intelligence—and a way to measure it. In this episode, Hugo talks with Greg Kamradt, President of the ARC Prize Foundation, about ARC-AGI: a benchmark built on Francois Chollet’s definition of intelligence as “the efficiency at which you learn new things.” Unlike most evals that …

1
Episode 47: The Great Pacific Garbage Patch of Code Slop with Joe Reis 1:19:12

7M ago1:19:12

1:19:12

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. Joe is the co-author of Fundamentals…

1
Episode 46: Software Composition Is the New Vibe Coding 1:08:57

7M ago1:08:57

1:08:57

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, reaso…

1
Episode 45: Your AI application is broken. Here’s what to do about it. 1:17:30

9M ago1:17:30

1:17:30

Too many teams are building AI applications without truly understanding why their models fail. Instead of jumping straight to LLM evaluations, dashboards, or vibe checks, how do you actually fix a broken AI app? In this episode, Hugo speaks with Hamel Husain, longtime ML engineer, open-source contributor, and consultant, about why debugging generat…

1
Episode 44: The Future of AI Coding Assistants: Who’s Really in Control? 1:34:11

9M ago1:34:11

1:34:11

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. In this episode, we dive into: The trade-of…

1
Episode 43: Tales from 400+ LLM Deployments: Building Reliable AI Agents in Production 1:01:03

10M ago1:01:03

1:01:03

Hugo speaks with Alex Strick van Linschoten, Machine Learning Engineer at ZenML and creator of a comprehensive LLMOps database documenting over 400 deployments. Alex's extensive research into real-world LLM implementations gives him unique insight into what actually works—and what doesn't—when deploying AI agents in production. In this episode, we …

1
Episode 42: Learning, Teaching, and Building in the Age of AI 1:20:03

10M ago1:20:03

1:20:03

In this episode of Vanishing Gradients, the tables turn as Hugo sits down with Alex Andorra, host of Learning Bayesian Statistics. Hugo shares his journey from mathematics to AI, reflecting on how Bayesian inference shapes his approach to data science, teaching, and building AI-powered applications. They dive into the realities of deploying LLM app…

1
Episode 41: Beyond Prompt Engineering: Can AI Learn to Set Its Own Goals? 43:51

11M ago43:51

43:51

Hugo Bowne-Anderson hosts a panel discussion from the MLOps World and Generative AI Summit in Austin, exploring the long-term growth of AI by distinguishing real problem-solving from trend-based solutions. If you're navigating the evolving landscape of generative AI, productionizing models, or questioning the hype, this episode dives into the tough…

1
Episode 40: What Every LLM Developer Needs to Know About GPUs 1:43:34

11M ago1:43:34

1:43:34

Hugo speaks with Charles Frye, Developer Advocate at Modal and someone who really knows GPUs inside and out. If you’re a data scientist, machine learning engineer, AI researcher, or just someone trying to make sense of hardware for LLMs and AI workflows, this episode is for you. Charles and Hugo dive into the practical side of GPUs—from running inf…

1
Episode 39: From Models to Products: Bridging Research and Practice in Generative AI at Google Labs 1:43:28

12M ago1:43:28

1:43:28

Hugo speaks with Ravin Kumar,*Senior Research Data Scientist at Google Labs. Ravin’s career has taken him from building rockets at SpaceX to driving data science and technology at Sweetgreen, and now to advancing generative AI research and applications at Google Labs and DeepMind. His multidisciplinary experience gives him a rare perspective on bui…

1
Episode 38: The Art of Freelance AI Consulting and Products: Data, Dollars, and Deliverables 1:23:47

1y ago1:23:47

1:23:47

Hugo speaks with Jason Liu, an independent AI consultant with experience at Meta and Stitch Fix. At Stitch Fix, Jason developed impactful AI systems, like a $50 million product similarity search and the widely adopted Flight recommendation framework. Now, he helps startups and enterprises design and deploy production-level AI applications, with a f…

1
Episode 37: Prompt Engineering, Security in Generative AI, and the Future of AI Research Part 2 50:36

1y ago50:36

50:36

Hugo speaks with three leading figures from the world of AI research: Sander Schulhoff, a recent University of Maryland graduate and lead contributor to the Learn Prompting initiative; Philip Resnik, professor at the University of Maryland, known for his pioneering work in computational linguistics; and Dennis Peskoff, a researcher from Princeton s…

1
Episode 36: Prompt Engineering, Security in Generative AI, and the Future of AI Research Part 1 1:03:46

1y ago1:03:46

1:03:46

Hugo speaks with three leading figures from the world of AI research: Sander Schulhoff, a recent University of Maryland graduate and lead contributor to the Learn Prompting initiative; Philip Resnik, professor at the University of Maryland, known for his pioneering work in computational linguistics; and Dennis Peskoff, a researcher from Princeton s…

1
Episode 35: Open Science at NASA -- Measuring Impact and the Future of AI 58:13

1y ago58:13

58:13

Hugo speaks with Dr. Chelle Gentemann, Open Science Program Scientist for NASA’s Office of the Chief Science Data Officer, about NASA’s ambitious efforts to integrate AI across the research lifecycle. In this episode, we’ll dive deeper into how AI is transforming NASA’s approach to science, making data more accessible and advancing open science pra…

1
Episode 34: The AI Revolution Will Not Be Monopolized 1:42:51

1y ago1:42:51

1:42:51

Hugo speaks with Ines Montani and Matthew Honnibal, the creators of spaCy and founders of Explosion AI. Collectively, they've had a huge impact on the fields of industrial natural language processing (NLP), ML, and AI through their widely-used open-source library spaCy and their innovative annotation tool Prodigy. These tools have become essential …

1
Episode 33: What We Learned Teaching LLMs to 1,000s of Data Scientists 1:25:10

1+ y ago1:25:10

1:25:10

Hugo speaks with Dan Becker and Hamel Husain, two veterans in the world of data science, machine learning, and AI education. Collectively, they’ve worked at Google, DataRobot, Airbnb, Github (where Hamel built out the precursor to copilot and more) and they both currently work as independent LLM and Generative AI consultants. Dan and Hamel recently…

1
Episode 32: Building Reliable and Robust ML/AI Pipelines 1:15:10

1+ y ago1:15:10

1:15:10

Hugo speaks with Shreya Shankar, a researcher at UC Berkeley focusing on data management systems with a human-centered approach. Shreya's work is at the cutting edge of human-computer interaction (HCI) and AI, particularly in the realm of large language models (LLMs). Her impressive background includes being the first ML engineer at Viaduct, doing …

1
Episode 31: Rethinking Data Science, Machine Learning, and AI 1:36:04

1+ y ago1:36:04

1:36:04

Hugo speaks with Vincent Warmerdam, a senior data professional and machine learning engineer at :probabl, the exclusive brand operator of scikit-learn. Vincent is known for challenging common assumptions and exploring innovative approaches in data science and machine learning. In this episode, they dive deep into rethinking established methods in d…

1
Episode 30: Lessons from a Year of Building with LLMs (Part 2) 1:15:23

1+ y ago1:15:23

1:15:23

Hugo speaks about Lessons Learned from a Year of Building with LLMs with Eugene Yan from Amazon, Bryan Bischof from Hex, Charles Frye from Modal, Hamel Husain from Parlance Labs, and Shreya Shankar from UC Berkeley. These five guests, along with Jason Liu who couldn't join us, have spent the past year building real-world applications with Large Lan…

1
Episode 29: Lessons from a Year of Building with LLMs (Part 1) 1:30:21

1+ y ago1:30:21

1:30:21

Hugo speaks about Lessons Learned from a Year of Building with LLMs with Eugene Yan from Amazon, Bryan Bischof from Hex, Charles Frye from Modal, Hamel Husain from Parlance Labs, and Shreya Shankar from UC Berkeley. These five guests, along with Jason Liu who couldn't join us, have spent the past year building real-world applications with Large Lan…

1
Episode 28: Beyond Supervised Learning: The Rise of In-Context Learning with LLMs 1:05:38

1+ y ago1:05:38

1:05:38

Hugo speaks with Alan Nichol, co-founder and CTO of Rasa, where they build software to enable developers to create enterprise-grade conversational AI and chatbot systems across industries like telcos, healthcare, fintech, and government. What's super cool is that Alan and the Rasa team have been doing this type of thing for over a decade, giving th…

1
Episode 27: How to Build Terrible AI Systems 1:32:24

1+ y ago1:32:24

1:32:24

Hugo speaks with Jason Liu, an independent consultant who uses his expertise in recommendation systems to help fast-growing startups build out their RAG applications. He was previously at Meta and Stitch Fix is also the creator of Instructor, Flight, and an ML and data science educator. They talk about how Jason approaches consulting companies acro…

1
Episode 26: Developing and Training LLMs From Scratch 1:51:35

1+ y ago1:51:35

1:51:35

Hugo speaks with Sebastian Raschka, a machine learning & AI researcher, programmer, and author. As Staff Research Engineer at Lightning AI, he focuses on the intersection of AI research, software development, and large language models (LLMs). How do you build LLMs? How can you use them, both in prototype and production settings? What are the buildi…

1
Episode 25: Fully Reproducible ML & AI Workflows 1:20:38

1+ y ago1:20:38

1:20:38

Hugo speaks with Omoju Miller, a machine learning guru and founder and CEO of Fimio, where she is building 21st century dev tooling. In the past, she was Technical Advisor to the CEO at GitHub, spent time co-leading non-profit investment in Computer Science Education for Google, and served as a volunteer advisor to the Obama administration’s White …

1
Episode 24: LLM and GenAI Accessibility 1:30:03

1+ y ago1:30:03

1:30:03

Hugo speaks with Johno Whitaker, a Data Scientist/AI Researcher doing R&D with answer.ai. His current focus is on generative AI, flitting between different modalities. He also likes teaching and making courses, having worked with both Hugging Face and fast.ai in these capacities. Johno recently reminded Hugo how hard everything was 10 years ago: “W…

1
Episode 23: Statistical and Algorithmic Thinking in the AI Age 1:20:37

2y ago1:20:37

1:20:37

Hugo speaks with Allen Downey, a curriculum designer at Brilliant, Professor Emeritus at Olin College, and the author of Think Python, Think Bayes, Think Stats, and other computer science and data science books. In 2019-20 he was a Visiting Professor at Harvard University. He previously taught at Wellesley College and Colby College and was a Visiti…