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 and how — you can transform context loss into a strategic advantage. This episode breaks down the mechanics of the separate summarization model call, explores why vague instructions fail, and reveals four powerful patterns: reframing conversations as decision logs, extracting task lists, distilling reusable knowledge, and shifting perspectives. If you've ever felt the sting of lost context after a long session, this episode shows you how to make every compaction count.

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 explores the growing movement to revive structural stone — from post-tensioned footbridges in London to earthquake-tested buildings in Japan. We break down the tech, the economics, and why developers still won't bite.

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 — Streamable HTTP vs WebSocket — and the authentication landscape: OAuth 2.1 with PKCE, device authorization grants, and mutual TLS. Then we get practical: Cloudflare Tunnel and Tailscale Funnel for safe network exposure, and why the ecosystem still feels immature for this exact use case.

Most productive AI use isn't flashy agents or chatbots — it's small, single-purpose utilities that transform text reliably. But these models are trained to be conversational, and that friendliness breaks the utility pattern. In this episode, we break down why the conversational default is baked into the model, and walk through a four-part system prompt structure that makes AI utilities behave like functions: role framing, explicit output instructions, strict format specs, and deterministic error handling. If you've ever gotten "Sure, here's your JSON!" when you needed raw data, this one's for you.

Daniel's been building a collection of small, single-purpose AI assistants for daily tasks — from formatting podcast dictation to inventory logging. In this episode, we dig into why these constrained utilities often beat big agentic workflows, how MCP integrations let them grow into lightweight agents without losing reliability, and why the chat interface is the wrong home for them. Plus: what would a proper launcher for a dozen mini AI tools look like?

Hannah noticed something from the airline websites alone: Emirates and flydubai offer a level of hospitality that feels worlds apart from Western carriers. That observation led her to a deeper question — what is Emirati culture actually like underneath the skyscrapers and luxury branding? In this episode, we unpack the UAE's Bedouin and maritime roots, the meaning behind the kandura and the abaya, the etiquette of Arabic coffee, and whether a transit stop at Dubai International can offer any glimpse of the real thing. Plus: how a country where citizens are only 11% of the population preserves its identity at the center of a global crossroads.

Daniel has relied on Google Groups for flexible mail routing across his Workspace domains for years—but he's always suspected it's a workaround, not a real feature. We break down what Google actually offers for mail routing today, why Groups feels like using a restaurant as a hallway, and how modern platforms like Cloudflare Email Routing, Zoho, and Microsoft 365 handle shared addresses and aliases with dedicated tools. Plus, the trade-offs of leaving the Google ecosystem after two decades of muscle memory.

What actually happens when reality contradicts what you believe? We trace cognitive dissonance from Leon Festinger's infiltration of a doomsday cult to the lab experiments that revealed how the mind quietly rewrites itself — and why the Theatre of the Absurd might be the best metaphor for modern life. This isn't the pop-psych version about hypocrisy; it's the unsettling mechanism underneath the feeling that things don't add up.

A long-time immigrant to Israel notices something shifting: phone trees that contradict themselves, credit card disputes that go nowhere, a bus driver attacked in broad daylight. Is this ordinary Israeli bureaucracy — or the hidden cost of years of war and collective trauma? We explore allostatic load, the "week three spike" at a national scale, and what history teaches us about societies that keep functioning while the gears underneath grind slower. The answer changes how you read the daily news.

Daniel's trying to measure his new apartment with photos, but AR apps keep drifting. In this episode, we dive into fiducial markers — AprilTags, ArUco, ChArUco, and plain checkerboards — to figure out which one can actually establish accurate scale in a normal smartphone photo. We cover how pose estimation works, why scale only transfers on a single plane, and what the ideal physical reference board looks like. If you've ever wondered why your phone says one thing and the tape measure says another, this one's for you.