Daily Reading List – September 23, 2026 (#873)

It’s been one of those days that feels productive, but there have been so few pauses that I need to replay the highlights during the drive home to be sure.

[blog] Launching MCP Apps in Toolbox. Return interactive UI components along with your data? MCP Apps are an interesting idea, and reasonable if your client can render a web view.

[blog] Gemini 3.8 text-to-speech says hello. These are some wild models. Create new voices from scratch, replicate existing ones, and direct performances with that voice. Simon already built a fun example with it.

[blog] Leave the Class Path in the Rearview Mirror. From Netflix. They’re trying to make Java development easier with better modularity. Yes please.

[blog] Keep post-paid Gemini billing: use Vertex, not AI Studio Prepay. The effort by vendors to prevent runaway bills now means you have other things to worry about. Like making sure your app keeps running when you’ve eaten all your credits.

[blog] The Internet Is Not Ready for the Agentic Wave. Yes, the web assumes you’re human. Page layouts, CAPTCHAs, carefully crafted calls-to-actions on videos? Agents don’t care about any of that.

[blog] GKE becomes more elastic: Scale to zero, save costs, and keep workloads responsive. If you thought the optional KEDA extension was the only way to get a Kubernetes cluster to scale workloads to zero, you’re in luck. GKE now offers native scaling to and from zero.

[blog] Building generative media agents: model, harness, tools. Here’s advice for those building agents that produce images, video, and audio.

[blog] The Death of Apps Has Already Begun. I’m 100% down with this point of view. Apps won’t go away, but you’ll stop using them yourself.

[blog] My comment on MCP was always a bad idea? Makes sense. MCP isn’t necessary if your client has full access to CLIs and APIs. But many clients don’t, and won’t.

[blog] How to build a Jev-style classifier with DiffusionGemma and vLLM. Here’s a cool exploration by Karl. You’ve already got an open, high-performing option for classification if you use DiffusionGemma.

[article] Anthropic made Opus 5.5 cheaper. Then it broke four things your agent depends on. This applies to any provider. Don’t just switch over to new versions. Make sure you understand what got toggled on (or off) in a given release.

[article] Google Open-Sources AX a Kubernetes Style Orchestrator for Autonomous AI Agents. You can make existing infrastructure agent-ready with the frameworks and orchestrators we’ve been open sourcing lately.

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

Comments

Leave a comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.