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.
#4139: The Hosepipe-to-Digest AI: Your Outbox Middleware
An AI middleware that intercepts your outgoing emails, buffers them, and delivers a crisp executive summary.
#4106: Embedding Models vs LLMs: What Actually Connects?
Can you mix any embedding model with any LLM? And why are new embedding models still dropping if they're "solved"?
#4104: Why 20% of AI Scripts Loop on Themselves
Debugging the mysterious repetition bug affecting one in five podcast episodes.
#4094: One Mind or Two? AI Podcast Dialogue Showdown
Can two AI agents create better podcast banter than one? We explore the tradeoffs.
#4092: How AI Remembers What You Never Told It
How ChatGPT connected "wall anchors" to a power tool you bought days ago — without being asked.
#4090: When Visual Shortcuts Fail: Reading Politics by Appearance in Israel
How reliable are political signals from clothing? One Jerusalemite's stories of delightful failures.
#4087: What Connie Sachs’s Job Title Actually Is
How a fictional spy’s pattern-recognition skill maps to real CIA, MI5, and MI6 careers.
#4071: Four Tools for a Human Review Layer on AI Tags
Adding human review to AI-generated tags without building an admin panel from scratch.
#4069: How AI Is Rewriting Your Tech Stack Choices
What happens when AI agents change how we pick frameworks, ORMs, and databases?
#4068: How to Build a Go Image Pipeline for Your Inventory App
Stop treating your inventory app like a photo dump. Here's how to build a smart image pipeline in Go.
#4059: LLM Councils for Post-Gallbladder Care
Can multiple AI models solve what no single doctor can? A deep dive into LLM councils for post-cholecystectomy syndrome.
#4058: Can AI Agents Ever Be Truly Social?
Text-based AI simulations look social, but do they understand anything? We explore the gap between pattern-matching and real social intelligence.
#4057: How to Fix AI's Bullet Point Addiction
Why AI models default to bullet points and how textual LoRAs achieve 94% prose adherence.
#4056: How a $150 Geopolitical AI Simulation Scales to $15,000
One simulation run costs $150. To get meaningful results, you need 100 runs—that’s $15,000.
#4052: From Phone Number to Identity Map
How a single phone number becomes a map of someone's digital life through graph-based OSINT techniques.
#4044: How to Sound Like a Bot on Purpose
When AI detectors flag clean human writing as machine-made, sounding like a bot becomes a survival skill.
#4015: Why Phone Camera Manual Mode Breaks DSLR Rules
DSLR exposure rules will ruin your smartphone photos. Here's why ISO, shutter speed, and exposure work differently on tiny sensors.
#3995: Can Your Phone Upscale Photos Without the Cloud?
Local upscaling on phones is here — but which approach actually works?
#3974: How Pilots Land in Crazy Crosswinds
The physics, engineering, and pilot skill behind those jaw-dropping crosswind landings you've seen online.
#3962: What's Really Happening Inside That Jet Engine on the Tarmac?
The flashlight beam isn't casual curiosity. It's the last line of defense in aviation safety.