Vanishing Gradients
Technology

Vanishing Gradients

by Hugo Bowne-Anderson

A podcast for people who build with AI. Long-format conversations with people shaping the field about agents, evals, multimodal systems, data infrastructure, and the tools behind them. Guests include Jeremy Howard (fast.ai), Hamel Husain (Parlance Labs), Shreya Shankar (UC Berkeley), Wes McKinney (creator of pandas), Samuel Colvin (Pydantic) and more. hugobowne.substack.com

72 episodes
EN language
All Episodes
1
Episode 72: Why Agents Solve the Wrong Problem (and What Data Scientists Do Instead)
1:33:39 Mar 20, 2026
2
Episode 71: Durable Agents - How to Build AI Systems That Survive a Crash with Samuel Colvin
51:27 Feb 18, 2026
3
Episode 70: 1,400 Production AI Deployments
1:09:52 Feb 12, 2026
4
Episode 69: Python is Dead. Long Live Python! With the Creators of pandas & Parquet
55:27 Feb 3, 2026
5
Episode 68: A Builder’s Guide to Agentic Search & Retrieval with Doug Turnbull & John Berryman
1:28:42 Jan 23, 2026
6
Episode 67: Saving Hundreds of Hours of Dev Time with AI Agents That Learn
1:18:22 Jan 14, 2026
7
Episode 66: The Agent Paradox - Why Moderna's Most Productive AI Systems Aren't Agents
42:58 Jan 8, 2026
8
Episode 65: The Rise of Agentic Search
51:53 Dec 19, 2025
9
Episode 64: Data Science Meets Agentic AI with Michael Kennedy (Talk Python)
1:02:56 Dec 3, 2025
10
Episode 63: Why Gemini 3 Will Change How You Build AI Agents with Ravin Kumar (Google DeepMind)
1:00:13 Nov 22, 2025
11
Episode 62: Practical AI at Work: How Execs and Developers Can Actually Use LLMs
59:04 Oct 31, 2025
12
Episode 61: The AI Agent Reliability Cliff: What Happens When Tools Fail in Production
28:04 Oct 16, 2025
13
Episode 60: 10 Things I Hate About AI Evals with Hamel Husain
1:13:16 Sep 30, 2025
14
Episode 59: Patterns and Anti-Patterns For Building with AI
47:37 Sep 23, 2025
15
Episode 58: Building GenAI Systems That Make Business Decisions with Thomas Wiecki (PyMC Labs)
1:00:45 Sep 9, 2025
16
Episode 57: AI Agents and LLM Judges at Scale: Processing Millions of Documents (Without Breaking the Bank)
41:28 Aug 29, 2025
17
Episode 56: DeepMind Just Dropped Gemma 270M... And Here’s Why It Matters
45:41 Aug 14, 2025
18
Episode 55: From Frittatas to Production LLMs: Breakfast at SciPy
38:09 Aug 12, 2025
19
Episode 54: Scaling AI: From Colab to Clusters — A Practitioner’s Guide to Distributed Training and Inference
41:18 Jul 18, 2025
20
Episode 53: Human-Seeded Evals & Self-Tuning Agents: Samuel Colvin on Shipping Reliable LLMs
44:50 Jul 8, 2025
21
Episode 52: Why Most LLM Products Break at Retrieval (And How to Fix Them)
28:38 Jul 2, 2025
22
Episode 51: Why We Built an MCP Server and What Broke First
47:42 Jun 26, 2025
23
Episode 50: A Field Guide to Rapidly Improving AI Products -- With Hamel Husain
27:42 Jun 17, 2025
24
Episode 49: Why Data and AI Still Break at Scale (and What to Do About It)
1:21:46 Jun 5, 2025
25
Episode 48: How to Benchmark AGI with Greg Kamradt (ARC-AGI)
1:04:26 May 23, 2025
26
Episode 47: The Great Pacific Garbage Patch of Code Slop with Joe Reis
1:19:13 Apr 7, 2025
27
Episode 46: Software Composition Is the New Vibe Coding
1:08:57 Apr 3, 2025
28
Episode 45: Your AI application is broken. Here’s what to do about it.
1:17:30 Feb 20, 2025
29
Episode 44: The Future of AI Coding Assistants: Who’s Really in Control?
1:34:12 Feb 4, 2025
30
Episode 43: Tales from 400+ LLM Deployments: Building Reliable AI Agents in Production
1:01:03 Jan 16, 2025
31
Episode 42: Learning, Teaching, and Building in the Age of AI
1:20:04 Jan 4, 2025
32
Episode 41: Beyond Prompt Engineering: Can AI Learn to Set Its Own Goals?
43:52 Dec 30, 2024
33
Episode 40: What Every LLM Developer Needs to Know About GPUs
1:43:35 Dec 24, 2024
34
Episode 39: From Models to Products: Bridging Research and Practice in Generative AI at Google Labs
1:43:29 Nov 25, 2024
35
Episode 38: The Art of Freelance AI Consulting and Products: Data, Dollars, and Deliverables
1:23:47 Nov 4, 2024
36
Episode 37: Prompt Engineering, Security in Generative AI, and the Future of AI Research Part 2
50:36 Oct 8, 2024
37
Episode 36: Prompt Engineering, Security in Generative AI, and the Future of AI Research Part 1
1:03:47 Sep 30, 2024
38
Episode 35: Open Science at NASA -- Measuring Impact and the Future of AI
58:14 Sep 19, 2024
39
Episode 34: The AI Revolution Will Not Be Monopolized
1:42:52 Aug 22, 2024
40
Episode 33: What We Learned Teaching LLMs to 1,000s of Data Scientists
1:25:11 Aug 12, 2024
41
Episode 32: Building Reliable and Robust ML/AI Pipelines
1:15:11 Jul 27, 2024
42
Episode 31: Rethinking Data Science, Machine Learning, and AI
1:36:05 Jul 9, 2024
43
Episode 30: Lessons from a Year of Building with LLMs (Part 2)
1:15:24 Jun 26, 2024
44
Episode 29: Lessons from a Year of Building with LLMs (Part 1)
1:30:22 Jun 26, 2024
45
Episode 28: Beyond Supervised Learning: The Rise of In-Context Learning with LLMs
1:05:38 Jun 9, 2024
46
Episode 27: How to Build Terrible AI Systems
1:32:25 May 31, 2024
47
Episode 26: Developing and Training LLMs From Scratch
1:51:35 May 15, 2024
48
Episode 25: Fully Reproducible ML & AI Workflows
1:20:39 Mar 18, 2024
49
Episode 24: LLM and GenAI Accessibility
1:30:04 Feb 27, 2024
50
Episode 23: Statistical and Algorithmic Thinking in the AI Age
1:20:37 Dec 20, 2023
Select an episode
0:00 0:00