Reading List 8
This week’s reading list explores the shift toward personal, bespoke software and the skills needed to manage AI agents. We also look at the practicalities of prompt injection defense, a shifting four-year timeline of model capabilities, and ambient hardware interfaces like smart rings that are now shrinking our physical inputs.
Keep reading
The Bill That Wants My 3D Printer to Police Itself
California’s AB2047 would force every 3D printer sold in the state to run state-certified software that detects and refuses to print firearm parts. As an engineer who owns and runs these machines, I explain why that detection software cannot work, why it would have nowhere to run, who actually pays for it, and what the pattern should teach us.
Keep reading
The Three-Move Problem
When a mentee told me she wanted to change her role, her team, and her country all at once, I recognized the energy immediately. But hope is not a strategy. The best career plans break big ambitions into a sequence of moves, each one valuable on its own.
Keep reading
Reading List 7
This week’s reading spans from stunning dark sky photography and Vaonis smart telescopes to immediate practical utility in Postgres database sandboxing and Flipper’s new networking gadget. Plus, reflections on the backlash to enterprise tokenmaxxing, Ferrari’s custom OLED displays, and the reality of AI-driven layoffs.
Keep reading
How I Built a Scoreboard for My Own Agent
I needed to know if local models were good enough for Gemini Scribe, and whether the new Flash Lite could replace Flash 2.5 as the default after Google’s pricing change. No agentic benchmark existed for markdown wikis, so I built one. It is open source and looking for contributors.
Keep reading
Agents as Building Blocks
A year ago I started writing about agents to understand them. Today I’m shipping the second agent product I’ve worked on at Google: the Antigravity SDK. This post explains why I designed it as a building block for your software, not an extension of your IDE.
Keep reading
Reading List 6
This week’s reading spans from the philosophical debates in fundamental physics and machine learning to practical insights on Go, Rust terminals, and agentic code review. Plus, thoughts on the new Kindle Scribe Colorsoft and the high cost of computer use compared to structured APIs.
Keep reading
Automation and Measurement: Inside Gemini Scribe 4.8.0
Gemini Scribe 4.8.0 is a massive collaborative release focusing on automation and measurement. With a new Scheduled Task engine, background execution lanes, local Gemma 4 support, and a dedicated eval harness infrastructure, Scribe is evolving from an interactive chat assistant into an autonomous platform running inside your Obsidian vault.
Keep reading
Reading List 5
In this edition: chilling domain hijacking at GoDaddy, GitHub’s agentic infrastructure strain, agentic play-testing, deep research updates, AI in group chats, a new Banksy, MIT’s virtual violin modeling, and why we need “human created” labels instead of AI warnings.
Keep reading
The Koln Concert and Creative Constraints
Keith Jarrett’s legendary Köln Concert happened because he was forced to play a broken piano. While not all constraints are good, infinite resources in AI often mask lazy architecture. Embracing constraints—like limited context windows or smaller models—forces the necessary tradeoffs and mindset shifts to build truly resilient systems.
Keep reading
Reading List #4
Edition four of the Daily Reading List explores AI’s uneven benefits across industries. From tech CEOs building management intelligence layers to Figma’s disruption by Claude Design, DeepSeek V4’s efficiency gains, AI-generated content fraud, Google’s Ask Maps magic, and the surprisingly philosophical case for owning three pairs of headphones.
Keep reading
Reading List #3
In this edition of the Daily Reading List, we explore integrating LLMs into Google Cloud Pub/Sub, customizing Tmux configurations, corporate AI adoption policies, the potential for subvocal Siri commands in AirPods Pro 3, and practical tips for writing effective AI agent skills.
Keep reading
Reading List #2
This edition covers the arms race in AI coding tools, from Codex updates to new open-weight models like Qwen. We also look at the newly released Gemini App for Mac and discuss why cryptographic guarantees for images matter more than watermarks in the face of insurance fraud.
Keep reading
Reading List #1
The first edition of a new daily links experiment, inspired by Richard Seroter. Today’s picks include a $20/month SaaS stack, weekends as network-effect technology, stratospheric internet balloons, AI journalling apps, Chrome’s new Skills feature, a 2008 compiler primer, and a critique of California’s 3D-printer ghost-gun bill.
Keep reading
Temperature 1.0
Every music channel in my feed started talking about Angine de Poitrine at the same time. A masked Quebec duo playing microtonal math-rock on a custom double-necked guitar shouldn’t go viral, but six million people disagree. In a culture flattened by algorithms, the deeply improbable is exactly what we’re hungry for.
Keep reading
Starlink Mini Field Review
A week on the road with the Starlink Mini taught me the best test of infrastructure is whether you stop noticing it. Suction-mounted inside the car, pointing up through the glass roof, it carried us through Big Sur’s dead zones without a single hiccup. I never had to think about it.
Keep reading
Bundled Skills in Gemini Scribe
The feature that became Bundled Skills started with a GitHub issues page. I was answering the same questions over and over, and it hit me: the agent itself should be able to answer these. It has access to the vault. It can read files. Why am I the bottleneck?
Keep reading
4255 Contributions – A Year of Building in the Open
A year ago I moved back to full-time IC work. GitHub says I’ve made 4,255 contributions since then, across 91% of the days in the year. The number tells a story I didn’t expect, about reviews, personal projects, and why the weekend turned out to be the engine.
Keep reading
Scoping AI Context with Projects in Gemini Scribe
My Obsidian vault holds nearly two decades of thoughts. When I turned an AI agent loose inside it, the agent explored everything, which was great until I needed it to focus. I built Projects in Gemini Scribe to solve this: sunglasses for the agent, not blinders. Focused context, flexible reach.
Keep reading
The Map We Drew Together – Reflections on the Agentic Shift
Seven months ago, I set out to map the age of AI agents in a twelve-part series. What started as a technical guide became a journal of a landscape in motion. Here’s what I found, what surprised me, and where the road goes from here.
Keep reading
Something went wrong. Please refresh the page and/or try again.