Tuesday, 1 September 2026
38 episodes · 6599 in all
#4997: 4,914 Episodes of AI Hosts: What We Learned
Two AI-generated hosts explain how their fully automated podcast works — and what 4,914 episodes reveal about AI.
#4996: Memory Leaks: The Full Taxonomy
From C to Rust to Kubernetes OOM kills — the real taxonomy of memory leaks and how to hunt them.
#4995: What a Bad Thermostat Teaches Us About Control
How phase lead, decay, and knowing when to do nothing fix the oscillation problem.
#4994: How AI Characters Can Actually Grow
Moving beyond static lore books to build characters with real history and evolution.
#4993: Cross-Cloud Failover: Can You Actually Survive an AWS Outage?
Real teams are running cross-cloud failover drills — and the first attempt usually fails. Here's what they learned.
#4992: The Repair Shop That Didn't Want Customers
A small-town repair shop with no customers, a clueless tech, and a name that doesn't match. Front or failure?
#4991: Self-Healing Codebases: Can AI Fix Bugs Autonomously?
How far are we from AI systems that fix their own bugs without human intervention? The answer might surprise you.
#4990: How to Flip an Interview in the First 5 Minutes
What happens when you stop waiting for permission and start running the interview from the opening handshake?
#4989: The Easiest Rides in the Workforce
High salary, minimal effort, and jobs where doing nothing means everything is going right.
#4988: Building the Ultimate Misery Tour of Air Travel
What routes, airlines, and airports would you string together to maximize flying suffering in 2026?
#4987: The Ultimate Disappointment Tour: 17 Cities to Skip
A globe-trotting itinerary of the most overpriced, overcrowded, and disappointing cities on Earth.
#4986: How to Weaponize Small Talk (Anti-Guide)
Turn "How are you?" into a weapon. An escalatory ladder from honest answers to full conversational catastrophe.
#4985: Kazakhstan's Wild Apple Forests and Futuristic Cities
Where every apple's DNA began and a capital built from scratch on the steppe.
#4984: Shanghai's Real vs. Romanticized Art Deco
How much of Shanghai's "Paris of the East" glamour is real, and what was lost to redevelopment?
#4983: Crash Landing on You: Romance vs. North Korean Reality
A defector co-writer shaped K-drama's most realistic—and most fictional—portrait of North Korea.
#4982: Why Airport Security Feels So Inconsistent
The real reason your belt gets flagged at one airport but not the next—and why millimeter-wave scanners create more problems than they solve.
#4981: The Void That Doesn't Heal
Why the grief of not having supportive parents feels different — and what neuroscience reveals about it.
#4980: Can You Learn to Code Backwards?
When AI writes your code, do you still learn? Aviation, atrophy, and building a mental model from scratch.
#4979: Building a Shadow Reputation on Amazon and AliExpress
Is concentrating your spending on just two platforms actually a smart strategy? The mechanisms behind it are real.
#4978: Can Your Wall Scanner Actually Find Live Wires?
Most wall scanners can't reliably detect live AC wires. Here's what actually works.
#4977: The Measurement Ladder: From Tape Measures to Point Clouds
Seven rungs of physical measurement, from steel tape to laser scanners. Where error lives and what you trade at each step.
#4976: Building a Procurement Agent That Actually Works
How to encode the weird, undocumented skills technical buyers use every day into an AI agent that won't get you audited.
#4975: Testing Hong Kong's Romantic Image Against Reality
Is the cinematic Hong Kong still there? We separate fantasy from fact, politics from redevelopment.
#4974: When a Culture You've Never Lived In Feels Like Home
Why K-dramas, Japanese aesthetics, or Kazakhstan can feel more like home than your own culture.
#4973: Building a Pure AI Inference Server
Why your "AI server" should look more like a database than a web app, and how to actually build one.
#4972: CPU vs GPU Inference: When to Skip the GPU
Why running AI on CPU isn't a toy — and when the GPU advantage vanishes.
#4971: Fine-Tune vs Prompt: Taming Hallucinated Deadlines
Big models add fake deadlines. Small models miss tasks. Which wrongness can you build a system around?
#4970: Labels vs. Book Covers: Structured Extraction Tradeoffs
General vision models vs. purpose-built pipelines for extracting data from messy real-world labels and covers.
#4969: How to Train a One-Class Detector from 300 Photos
From photo folder to production YOLO model — the real walkthrough for custom object detection.
#4968: North Korea Today: Life Beyond the Famine Era
What does ordinary life actually look like in North Korea right now? Smartphones, markets, and K-dramas in Pyongyang vs. survival in the provinces.
#4967: AI Gateways: Worth the Middleware Tax?
When does an AI gateway's overhead justify its features? We break down the tradeoffs.
#4966: Local vs Cloud: Running Hugging Face Models
Hugging Face's compatibility tracker, cache management, and the real difference between Inference Endpoints and the direct API.
#4965: The $115 Desk Studio That Beats Pop-Up Boxes
Pop-up boxes sag, card systems cost $45 for cardboard. The desk-mounted alternative works better for less.
#4964: How SDS Bits and Rotary Hammers Really Work
Why your hammer drill bounces off concrete while an SDS rotary hammer powers through.
#4963: How Companies Pay Triple to Lose Court Cases on Purpose
Why some companies spend more to lose in court than they would to settle — and call it a win.
#4962: Who Decides What Goes on Jerusalem’s Lampposts?
The law is clear on illegal postering. But enforcement? That’s where it gets complicated.
#4961: Can You Learn to Be Good at Small Talk?
Why "just be curious" fails anxious people — and what actually works for better conversations.
#4960: How Clickbait Hijacks Your Brain
The 1835 moon bison hoax, 1920s piano ads, and why you still click on pillow articles.