Podcast Episodes
Back to Search
Can a Dremel Be Gym Equipment?
Episode 5783
If a power tool does the work, why are you sweating? A hobbyist's afternoon engraving HDPE storage boxes with a corded Dremel turned into a real rese…
3 days, 21 hours ago
Unraid in a VM: When the License Is the Wall
Episode 5782
Daniel runs a Synology for backups, but DSM fights his custom Python scripts — and two RAM upgrades left the box refusing to boot. His plan: keep the…
3 days, 22 hours ago
Measuring Keyhole Spacing: Why the Tool You Want Doesn't Exist
Episode 5781
Daniel wants a measuring tool between a caliper and a laser range finder — something like a slider over a ruler that reports millimeters, for mountin…
3 days, 22 hours ago
Why Keyhole Slots Never Line Up
Episode 5780
You've measured the keyhole slots on the back of a power strip, drilled exactly, and the thing still doesn't line up — because there was never a stan…
3 days, 22 hours ago
Tunnel Girl Dug 80 Feet Under Her House
Episode 5779
Kala — known online as Tunnel Girl — spent years excavating a tunnel and underground chamber beneath her Herndon, Virginia home, documenting every ja…
3 days, 23 hours ago
How J.K. Rowling Builds Characters That Last
Episode 5778
How does a writer keep dozens of characters vivid across seven books and two very different fictional worlds? This episode digs into J.K. Rowling's a…
3 days, 23 hours ago
Lorebooks: The Hobbyist RAG That Beat the Labs
Episode 5777
A language model has no memory of your character. Everything — voice, history, how they react to being interrupted — has to be re-injected into a fin…
3 days, 23 hours ago
Why UV Epoxy Keeps Curing in the Dark
Episode 5776
Daniel asked why epoxy can't cure itself, and whether light can replace the hardener. The answer runs through a three-membered ring under strain, a h…
4 days ago
What "Leaked System Prompts" Actually Mean
Episode 5775
Anthropic is the only major lab publishing its user-facing system prompts, yet the published versions leave out tool descriptions, accessory models, …
4 days ago
Reading the Model's Mind Mid-Inference
Episode 5774
Most LLM observability stops at the API boundary: request in, tokens out, everything between is a sealed box. Mechanistic interpretability tries to o…
4 days ago