Artificial Intelligence
Episodes whose main subject is AI itself: building with, training, evaluating, or debating AI systems. AI used only as a tool for another topic goes to that topic.
#5396: Teaching a Small Model to Stop Spelling Out Numbers
Your ASR pipeline is fine until someone dictates "three point two" and gets "three point two" spelled out. Here's how inverse text normalization ac...
#5393: Fine-Tuning a Model on 100 Hand-Edited Answers
You don't need 10,000 examples to make a model sound like you. The real number is closer to 100 — if the edits are opinionated.
#5392: Building Agents You Can Actually Move
Agent portability isn't a copy job — it's a rebuild. Why memory, not code, is where lock-in lives.
#5391: The Software Behind Urgent Care Triage
Big buttons, emoji vitals, and a system that says "order IV" — what's actually running behind the triage screen?
#5390: Chaining Small Models for Dictation Cleanup
Daniel's Android dictation fork won't render "three point five" as a decimal. How many models does cleanup actually need?
#5389: Hugging Face vs Kaggle: Where Models Actually Live
Hugging Face and Kaggle aren't rivals — one is infrastructure, one is a practice field. Here's how the two platforms actually differ.
#5387: Who Decides What Your Keyboard Knows?
Your keyboard's word list was probably frozen in 2014. Here's who maintains the open-source dictionaries — and why Gboard's stays fresh.
#5384: Android ASR Runtimes: LiteRT, ExecuTorch, and Why Your Phone Has No VRAM
Why does your phone have no VRAM number? A tour of Android's runtime layer and what it takes to run ASR locally.
#5383: Android's Open Core, Closed Governance
Android's code is open, but its roadmap isn't. What happens when Google changes the core and developers just have to cope?
#5381: What Hotels Know About Laundry Machines
Washer-extractors, 400 G-force spins, and why a hotel laundry machine won't fit in your apartment.
#5370: The Spotlight Effect and the Heckler's Playbook
Why a waiting room feels scarier than a stage — and how performers handle hostile crowds without losing the room.
#5355: Why AI Emails Don't Sound Like You
ChatGPT's Gmail integration can now send email for you. The hard part is making it sound like you — not a committee-written average.
#5353: Egypt's 700,000-Pilgrim Party at Bubastis
Herodotus called it Egypt's biggest festival — a boozy Nile flotilla of 700,000 pilgrims bound for the cat goddess's city.
#5350: Messiah, Eschaton, and the AI Singularity
Four traditions, four different job descriptions for "Messiah" — and what the AI singularity borrowed from all of them.
#5345: Forecasting for Cranes, Fires, and 15-Minute Decisions
The public five-day forecast is a loss leader. Here's what bespoke weather looks like when money and lives ride on it.
#5327: Catching Duplicate Submissions Before They Burn Credits
A dropped webhook response caused a double submission. Here's how to build a screener that catches duplicates before generation runs.
#5326: What Makes a Bar a Third Place?
A listener's search for a bar where you can actually hear your friend — and the 35-year-old sociology that explains why it's so hard to find.
#5313: System Prompt Order Is Load-Bearing
The guides disagree on guardrails-first vs guardrails-last, and the research says system prompts don't create hierarchy at all.
#5312: Fighting Fake-Personalized Spam With AI Sinkholes
Scraped flattery, fake familiarity, and the one-sided ask — plus the tarpit history behind Daniel's sinkhole agent idea.
#5311: Churchill's McKinsey Interview: When Oratory Meets the Case
Churchill's rhetoric was architectural, every sentence load-bearing. McKinsey wants the answer in sixty seconds. Let's roleplay the collision.