Notes from the lab
I write to think in public. Notes on measurement, agency, health, learning, and what building systems for people keeps teaching me about everything else. New pieces land here first, then cross-post out.
A provider made a frontier model unavailable to me overnight, no warning. It cost me twenty minutes, not a rebuild. Here's the architectural bet that made the difference.
June 2026 The Private ApprenticeBlock just shipped the fastest-adopted tool in its history: a way for anyone to build their own software, where the platform owns what makes it safe. It's the same bet I've spent the last year building Foundry on, with two deliberate differences.
We spent 2023 marveling that computers could talk. We are spending 2025 realizing that "talking" is a terrible interface for getting work done. The promise of AI was automation—the idea that we could hand off a task and get a result. But the reality of the "Chatbot Era" (ChatGPT, Gemini, Claude) is that we have simply traded *doing* the work for *micro-managing* the worker.
November 2025 From Podcast Spark to Gemini-Powered Personal PlaygroundDiscover how a casual podcast discussion ignited a journey to build a personal website and content creation engine using AI tools like Gemini, Claude, and Google Cloud. This post details the use of AI from concept to a custom Gemini-powered personal website, empowering my digital presence.
November 2025 Beyond the App: Crafting Personalized AI Experiences That Truly Understand UsThe chatbot is just the beginning. Discover a future where AI seamlessly integrates with our lives, moving beyond apps to create truly personalized, proactive experiences that anticipate our needs and empower our goals.
November 2025 Life as ExperimentWhether it's your investment portfolio, your health, your education, or your relationships, life is a day-by-day experiment of testing ideas that worked for others and applying them to yourself. Most of us run those experiments without a lab notebook.
More notes are on the way. I write when the experiment is worth reporting, not on a schedule.