Daily Reading List – August 26, 2025 (#615)

One reason that I could never be a solo worker is that I like the epiphanies that come from conversations with smart colleagues. Today there were a couple, and it makes me better at what I do.

[blog] Introducing Gemini 2.5 Flash Image, our state-of-the-art image model. Remarkable model, and a whole new way to iterate on AI-generated images. Some press coverage here.

[blog] Building next-gen visuals with Gemini 2.5 Flash Image on Vertex AI. This will be the best image generation model you’ve ever used, and it’s not just for “fun” stuff outside of work. Use it in corporate settings as well.

[blog] Why Your Prompts Don’t Belong in Git. Haven’t seen this POV. There’s an argument for keeping prompts out of your source code.

[blog] How to use the AI Function in Google Sheets (with 10 examples). I don’t spend my day in spreadsheets, but if I did, this AI function would drive a lot of value.

[blog] Who are we designing for now? You’ve got to ask and answer this question. Your UI and APIs now have agentic consumers which require new patterns.

[blog] Announcing general availability of Firestore with MongoDB compatibility. You want to use MongoDB, but also want easy scale, a great SLA, and pay-as-you-go pricing? We’ve got that.

[blog] From massive models to mobile magic: The tech behind YouTube real-time generative AI effects. Interesting behind-the-scenes look at how we do generative AI effects for mobile users.

[blog] How we leveraged vLLM to power our GenAI applications at LinkedIn. There’s a lot of AI happening at LinkedIn (good and bad), but go into the architecture by reading this post.

[article] Developers lose focus 1,200 times a day — how MCP could change that. I’m down with this. We’re all using too many apps and context switching more than needed. If MCP (or whatever) makes it easier to pull the data and actions we need into the place we’re at, it’s a win.

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