Daily Reading List – December 1, 2025 (#675)

I ended up taking Friday off from the reading list, but I’m back with a vengeance today. I took a short trip up to Sunnyvale and back, but got some reading done ahead of time. It’ll be a busy week with AWS re:Invent going on, along with everyone else doing interesting AI things.

[blog] How LLM Inference Works. I’m increasingly convinced that all engineers should have a basic understanding of LLM fundamentals. Don’t treat this like a black box abstraction.

[article] Applying AI where it matters. Devs welcome AI for tedious work, but keep it away from identity-defining work. This, and other important findings shared here.

[blog] Building with Gemini in the newest Vertex AI Studio. This experience has gotten pretty great for those who want to vibe code an app with enterprise-grade tools.

[blog] 8 learnings from 1 year of agents – PostHog AI. These are great. I love seeing lessons learned, which provide unique insights from those really doing the work.

[blog] Google Antigravity: Google’s agentic IDE with Gemini 3 Pro (complete guide). Excellent overview of what Google Antigravity is, what it means to developers, and a few of the key adjustments to how we build with it.

[docs] Choose your agentic AI architecture components. Here’s an excellent new architecture guide that helps you pick the right components for your agent system based on your use case and needs.

[article] This Thanksgiving’s real drama may be Michael Burry versus Nvidia. Fascinating piece, and it’s interesting to see how this industry will adapt to so many companies investing in their own chips.

[blog] What’s New in Gemini 3.0. Addy provides a thorough review of what Gemini 3 brings to developers, including Google Antigravity and Nano Banana Pro.

[article] Building an AI-Native Engineering Team. Important topic. How do planning, design, development, testing, review, documentation, and deployment tasks change within the team? Open AI put together some good content.

[article] Four important lessons about context engineering. These seem like valid tips, although it does appear that “best practices” are evolving quickly. Keep an eye on what we learn next.

[blog] Open Source Doesn’t Fail Because of Code! It’s not the code; it’s the system around any product, especially an open source one.

[blog] Google Antigravity Editor — Tips & Tricks. It’s fun to explore new tools, but we need guidance so that we don’t get lost. Mete shares what he’s discovered so far.

Want to get this update sent to you every day? Subscribe to my RSS feed or subscribe via email below: