All Episodes
Page 16 of 320 · October 2026
#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.
#6217: Fine-Tuning a Trillion-Parameter Model at Home
What does it actually take to full fine-tune a trillion-parameter model? Sixteen terabytes of optimizer state, hundreds of GPUs, and a very big bill.
#6216: What Do You Call the Middle Tier Model?
Sonnet, Sol, Flash, Medium — the daily-driver models nobody can name, and why they're squeezed from above and below.
#6215: Can Anyone Still Spot an AI Voice?
Clones now pass as human. Generic AI voices still don't. And the detectors? They fall apart in the wild.
#6214: Nobody Trains an Uncensored Model From Scratch
Every "uncensored" model is a renovation, not a new build — and the political lean lives in the agreement layer, not the refusals.
#6213: Ten Weirdest AI Evals Ever Published
A pelican on a bicycle, a badger for Groundhog Day, and a benchmark where passing is the bad outcome — the strangest AI evals ever run.
#6212: Woolly Sedate Snail and Other Model Failures
Most of Hugging Face's 2.96M models sit unread. But the dust has a personality — snails, pirates, and a matchbox that resigns.
#6211: Attention Is Still Winning: The Hybrid Model Census
Mamba layers shipped — inside hybrids. A census of Qwen, Nemotron, Kimi, Granite, and why MiniMax went back to full attention.
#6210: Who Decides If an Election Is Real?
57 countries hold multiparty elections that aren't real contests. So who certifies a vote — and why do clean democracies skip full scrutiny?
#6209: Watching Elections: Who Collects the Numbers, and Why
From CIA tasking orders on France's 2012 race to hedge funds buying private Brexit polls — who watches elections, and what they do with the numbers.
#6208: Israel's 120-Seat Forecasting Ministry
A windowless office, a serious budget, and one job: forecast Israel's 120-seat Knesset as well as it can be done.
#6207: Two WERs, One Model: Inside ASR Eval Harnesses
Same model, same audio, two different word error rates. The gap lives in the normaliser — and that's just layer two of three.
#6206: Monte Carlo: How Random Guesses Solve Impossible Problems
From solitaire at Los Alamos to neutron diffusion, why rolling dice beats careful grids — and how many runs is enough.
#6205: Where Should Your Notebook Actually Run?
Colab's free GPU comes with a 12-hour wall and hidden secrets in your saved outputs. Here's where notebooks should actually live.
#6204: Two Humans, One Table Each: Calling Israel's Election
No models this time — just two seat-by-seat tables, fifty vs. fifty-nine, and a defector hunt two seats short of a majority.