Friday, 23 October 2026
16 episodes · 6596 in all
#6233: Fibromyalgia's 26 Genetic Clues
A landmark study found 26 genetic regions linked to fibromyalgia — but the drugs are still catching up.
#6232: Daycare Germs: What Immunity Actually Means
Cold after cold, two hospital visits, and the phrase "building immunity." What actually changes in a child's immune system — and is it shared?
#6231: Why a Cold Makes Your Whole Body Ache
A sore throat shouldn't hurt your calves. Here's how one localized infection recruits your entire body into feeling terrible.
#6230: Why Synthetic Speech Needs Fake Room Noise
Synthetic voices can drop to digital black between sentences — so engineers add fake room tone to make the silence sound real.
#6229: Voice Design: Casting Ogres and Radio Voices
Text-described voices vs. reference audio, and which TTS knobs change who a voice is versus how it sounds.
#6228: What 12GB of VRAM Can Actually Do Now
Local AI on a mid-range AMD card: what fits, what's fast, and what's still out of reach in 2026.
#6227: Cork Chippers, Rooster Potatoes, and the Double Fry
What makes a proper chipper chip? Cork plumber Roy joins us to talk Roosters, dripping, and why the double fry is non-negotiable.
#6226: Sarah Tuttle-Singer: The Writer Who Lives Inside the Story
A Venice Beach kid who moved inside Jerusalem's Old City walls — and writes herself into every story she tells.
#6225: Reading the Iran Signal: Jets, Leaks, and the Midterm Deadline
Israel flew dozens of jets toward Iran and turned back. A secret Hegseth visit, a Trump pledge, and a lot of unnamed sources. What's actually being...
#6224: Marcus James: Jerusalem's Spiritual Mayor
He hitchhiked with Kerouac, followed the Grateful Dead, and now cleans windows near the Old City. Meet Jerusalem's spiritual mayor.
#6223: How Many Epochs Does Fine-Tuning Actually Need?
Epochs are a receipt, not a plan. How to pick a training ceiling, read the curves, and know when to stop.
#6222: Why Fine-Tuning Runs Can't Always Resume
Eighty cents and twenty-five minutes per training run — so why does the checkpoint question still keep a tinkerer up at night?
#6221: How Many Examples Does Fine-Tuning Actually Need?
Everyone says "thousands." Nobody says how many for your task. Here's how to measure the number yourself.
#6220: Mixture of Experts: Bigger Than It Looks
MoE models store a trillion parameters but only fire a few billion per token. Here's what the active number really measures — and why smaller isn't...
#6219: Dictation Beyond the Keyboard
Pedals, push-to-talk, and Android gesture apps promise keyboard-free dictation — but can any of it become a dependable daily setup?
#6218: Training a LoRA to Write Like You
A Humanizer model stripped every trace of the author. The fix isn't a better Humanizer — it's a LoRA trained on your own writing.