Development
Building software: programming, developer tools, APIs, deployment and DevOps, and building with AI (agents, MCP servers, RAG, AI coding tools). An extra channel alongside an episode's main one, so AI engineering episodes sit in both.
#4739: NFS Unmasked: Versions, Gotchas, and Hard Truths
NFS isn't one protocol—it's a succession of them. Here's what's really happening under the hood and where it breaks.
#4733: Why OAuth Still Makes You Dance on Your Own Machine
Why does OAuth treat your personal computer like a public terminal? We explore token storage, PKCE, and Linux secret APIs.
#4732: Travel Router Tailscale Subnet Bridge
Military network tactics for home users bridging subnets with Tailscale and travel routers.
#4731: Teaching Your Router Bedtime: Automated QoS with OPNsense
Can your router learn when to prioritize Netflix over backups? We build schedule-aware QoS with OPNsense and cron.
#4720: Compass vs. Warning Sign: Prompting for Long-Term AI
How positive and negative instructions reshape AI behavior differently — and why "preserve this" beats "fix this" in system prompts.
#4717: Building a Home Whisper Server: The Full Spec
Daniel wants a dedicated home server for Whisper dictation. Here's the exact build — GPU, RAM, storage, and runtime — to make it work.
#4713: MCP vs Browser-Use: The Agentic AI Showdown
Two patterns are fighting to define how AI agents interact with software. Which one wins shapes the next decade of building.
#4712: Codex vs Claude Code: The Real Agentic Coding Showdown
Benchmarks, model variants, and MCP setups — which coding agent actually wins where it matters?
#4704: Building a Unified AI Filesystem with Rclone and MinIO
How to build a single virtual filesystem for AI agents across multiple cloud storage providers — without the token headaches.
#4703: MCP Binary Payloads: Why URLs Beat Base64
MCP can't carry raw bytes. Here's why the URL pattern is the only legal move—and what the File Uploads Working Group might change.
#4702: Two Books, One AI Podcast: The Full Archive
Hilbert turned the entire My Weird Prompts archive into two physical books — the full production docs and all 4,620 episode descriptions.
#4701: Why Claude Code Re-Introduces Itself to Your Repo
Claude Code remembers your preferences but not your codebase. We explore why that's by design and how to work around it.
#4700: Browser Agents: Three Paths to One Protocol
How screenshot watching, dev-tools extensions, and native MCP in Chrome are converging — and what wins.
#4699: The Hidden Engine: What Makes Claude Code Tick
Is it the model or the harness? We break down the invisible scaffolding that turns LLMs into real agents.
#4690: Typst for Agents: Programmatic PDF Generation
How Typst's function-based design makes it the ideal document engine for AI agents generating professional PDFs.
#4689: Bootable Standby Drives: The Ship of Theseus Server Solution
Recovering from a dead NVMe drive in minutes, not days. A practical guide to building a bootable standby disk with rsync.
#4687: Bonding Cellular Connections: Why Can't You Buy It?
Why can't you buy a box that bonds two SIM cards? We explore the DIY build and the market gap.
#4686: How Claude Code's Patience Works: Fork, Wait, and the Transcript Stack
Claude Code's "waiting" is an illusion. We break down the Unix primitives behind its background task system and where the analogy cracks.
#4685: GitHub vs AWS: Agentic AI Cert Showdown
GH-600 vs AWS's AI ladder — which curriculum teaches transferable skills, and which is just product training?
#4684: Focus-Aware Key Remapping on Linux: The Hard Parts
How keyd bridges kernel input events and display-server focus — and why Wayland makes it harder than it should be.