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.
#2639: The Hidden Layer That Makes Search Work
Why your search results miss the mark — and how cross-encoders fix it.
#2638: How to Build Disposable AI Agents at Runtime
Create ephemeral AI agents that answer questions about specific items, then vanish. No persistent configuration needed.
#2634: The Two-Stage Pipeline for Persistent User Memory
How to extract durable personal context from raw prompts and build a self-healing memory layer for AI systems.
#2633: How Live UA Map Bridges Conflict Information Gaps
A curated conflict map that trades raw speed for verified, de-duplicated event tracking — used by civilians in active warzones.
#2632: How to Start a Meetup Without Burning Out
Practical steps for launching a local community around any interest — without it taking over your life.
#2629: The ADHD Archaeologist of Scent
How a frankincense obsession led to discovering perfume oils — a 4,000-year-old tradition that's being rediscovered today.
#2622: How Transformers Actually Work: Attention, Tokens, and Context
How one architectural change unlocked chatbots, image generation, and protein folding — explained without the jargon.
#2621: Wartime Ingenuity: Powering Connectivity in a Faraday Cage
Four 18650 cells can't stack to 230V. The secret is switching, not stacking.
#2618: Text Normalization's Hidden Complexity
How to handle acronyms in text-to-speech pipelines using BERT models, lexicons, and layered preprocessing.
#2612: Can You Speed-Date Your Way to the Right Therapy?
Finding the right therapy is a guessing game. What if you could sample different approaches before committing?
#2609: Mapping the Therapy Family Tree: CBT, ACT, DBT & Beyond
How CBT, ACT, and DBT actually evolved — and why matching therapy to personality matters.
#2603: Defining the Agentic Workspace
How composable AI agent skills turn tedious media tasks into one-instruction operations for creatives.
#2602: Letting Non-Experts Direct Audio Tools Through Conversation
How to use AI for podcast mastering — and why agentic AI works better for small tasks than big promises.
#2597: Voice Control for Renters: $25 Per Room, No Wall Damage
Distributed voice control on a budget with wake words, centralized processing, and zero wall damage — perfect for rentals.
#2591: Decoupling Script from Voice
How dynamic voice replacement could let listeners choose who narrates each host's lines.
#2590: The Uncanny Valley of Clean Speech
How transformer models distinguish "um" from meaningful speech — and why removing too much makes you sound like a robot.
#2586: Pseudo-Personalized Emails: The New Spam Uncanny Valley
How to detect and filter AI-generated outreach emails that fake personal connection without nuking legitimate messages.
#2582: What Your Browser Does to Mic Audio Before It Reaches Your Server
getUserMedia returns audio, but not raw audio. Here's what browsers actually do to your mic feed before it hits your server.
#2578: Building Deliberately Slow Deployment Pipelines
How to build CI/CD pipelines designed as filters, not firehoses — with manual gates, staging environments, and quality checks.
#2567: Beyond Pixels: Controlling Apps Without Vision
How MCP agents can use accessibility APIs and COM to control Windows and macOS apps at the protocol level.