Podcast Episodes
Back to Search
When Great Museums Fail: The Sincerity Gap
Episode 4590
Why do some of the world's most important museums leave visitors checking their watches? We dig into the "sincerity gap" — the distance between an in…
1 week, 1 day ago
The Answer Reflex: Why AI Models Can't Follow Instructions
Episode 4589
Why do cutting-edge models from OpenAI and Anthropic fail a simple system prompt test that DeepSeek V4 Pro passes consistently? We dig into the "answ…
1 week, 1 day ago
The Hidden Cost of Conversational AI: Why Stateless LLM Calls Matter
Episode 4588
When Daniel wrote in about the "strange paucity" of text-in, text-out AI tools, he tapped into a fundamental gap in how LLMs are built and deployed. …
1 week, 1 day ago
Can Agentic AI Finally Break the Google Workspace Grip?
Episode 4587
Daniel, a 19-year Google Workspace veteran, makes a bold case: agentic AI could finally break the grip of the big cloud monoliths. We unpack the thre…
1 week, 1 day ago
Fixing Stale UI: The 4-Link Chain of Data Flow
Episode 4586
When you upload a photo and the badge on screen refuses to update, the instinct is to reach for WebSockets. But that's the wrong layer entirely. This…
1 week, 2 days ago
Why `export` Fails But Files Work: Linux Process Secrets
Episode 4585
Ever wondered why a file written in one terminal tab is instantly visible in another, but an exported variable isn't? This episode traces the exact m…
1 week, 2 days ago
Directing Context Loss: Smart Compaction Prompts
Episode 4584
When you run /compact in Claude Code, you're not stuck with a generic summary. By passing a compaction directive — a prompt that shapes what survives…
1 week, 2 days ago
Structural Stone: The Building Material That Lasts 500 Years
Episode 4583
Reinforced concrete crumbles in 50 years and emits a ton of CO2 per ton produced. Meanwhile, stone buildings have stood for 500 years. This episode e…
1 week, 2 days ago
Designing a Home MCP Gateway for Conversational AI
Episode 4582
Daniel asks how to design an MCP gateway for home use that conversational AI clients can actually connect to. We break down the transport options — S…
1 week, 2 days ago
Text In, Text Out: Designing Single-Purpose AI Utilities
Episode 4581
Most productive AI use isn't flashy agents or chatbots — it's small, single-purpose utilities that transform text reliably. But these models are trai…
1 week, 2 days ago