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.
#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.
#2563: How Audio Fingerprinting Actually Works
Spectrogram peaks, constellation maps, and hash matching — the elegant mechanics behind identifying any song in seconds.
#2559: The Smartest Path to Python for AI
A practical guide to the best courses and platforms for learning Python, specifically for machine learning.
#2551: How Progressive Disclosure Saves MCP from Token Bloat
Why dumping all tool schemas into context breaks accuracy — and three implementations that fix it.
#2550: Idempotent Pipelines: Checkpoints, Manifests & Safe Re-Runs
How to design scripts and pipelines so re-running them is safe, even after a crash mid-execution.
#2548: Static vs Server-Side: What Actually Happens When You Deploy
The moment you see content appear instantly on production and realize it wasn't pre-built — that's when architecture gets interesting.
#2547: Self-Hosted Podcast Analytics & Caching Fixes
How to track listeners, handle caching delays, and get sponsor-ready numbers when self-hosting on Cloudflare R2 or S3.
#2546: The Invisible Engineering Behind a Single Click
The technical stack behind click-to-edit features in tools like Canva and Google Photos — from segmentation to inpainting.
#2545: Visual AI Pipelines: Beyond Python Glue Code
From ComfyUI to Dify — a tour of visual tools for building modular AI workflows without writing glue code.
#2544: How to Make AI Architectural Renders Photoreal Without Breaking Geometry
Fixing the uncanny valley in AI-enhanced architectural renders — without breaking the geometry.
#2543: Why Base64 Adds 33% Overhead (And Why You Still Need It)
Base64 isn’t compression — it’s a safe transport encoding. Here’s how it works with audio APIs and where its limits are.
#2541: Agent-to-Agent Scheduling: Building the Calendly for AI
How Google's A2A protocol and Anthropic's Remote MCP could power a new kind of agent handoff for scheduling meetings.
#2540: Does Your AI Framework Change the Output?
Same model, same prompts, different harness. Does the plumbing change the water?
#2536: Self-Hosted Zapier Alternatives in 2026
n8n, Huginn, and Dagu compared for personal automation on your own hardware.
#2535: Inside LangChain's Deep Agents: What's Actually in the Box
A deep dive into the batteries-included agent harness with terminal CLI, sub-agents, and production-ready evaluation.
#2534: Can AI Generate Diagrams Without Typo Disasters?
Why AI diagram tools still mangle text labels — and what to do about it today.
#2517: How Unsloth Makes LLM Fine-Tuning 2x Faster
Unsloth cuts memory usage by 50-70% and speeds up training 2.2x for models like Llama 3 and Mistral.
#2514: WebSockets vs SSE: Choosing the Right Real-Time Connection
WebSockets vs Server-Sent Events: when to use full-duplex vs one-way streaming, and why most developers pick wrong.
#2511: Measuring AI API Latency Through the Black Box
How to benchmark token throughput and debug slowdowns in closed CLI tools like Claude Code using OpenTelemetry and mitmproxy.
#2508: Why CORS Doesn't Protect Your Server
Why browsers block cross-origin requests, how CORS actually works, and the common pitfalls that trip up developers.