Want to ask an AI about a book you're reading without spoilers? In the S2 premiere of Code, Commit, Deploy, Repeat, Marina and I build a spoiler-free book Q&A app with on-device AI and Firebase: go.peterfriese.dev/firebase-no...

No spoilers, Sherlock! Building a book Q&A using on-device AI | Code, Commit, Deploy, Repeat (S2E1)

Join us for a hands-on live coding session - we will build a spoile...

youtube.com

Ready to take your Model Context Protocol (MCP) servers out of local dev and into the cloud? ☁️🚀 Join me on Aug 19 at 11 AM UTC! I’ll be showing you how to securely deploy and scale MCP tools using Cloud Run & GKE, lock them down with IAM, and wire them directly to your AI agents. 🤖 Details below 👇️

They swapped the model mid-experiment. The café failed the same way. So the model wasn't the problem. It shipped with no spend cap and no approval gate—the seatbelts you install on day one. The proof and the five fixes: www.linkedin.com/pulse/ai-did...

The AI Didn't Fail. The Deployment Did.

The Infographics Show, one of the biggest explainer channels on YouTube with an audience in the millions, just put out a video titled "Google Gemini Ran a Real Business for a Month and It Almost Bankr...

linkedin.com

Awesome conversation with @mumshad.bsky.social. If you watch very closely, you can see the exact moment when he broke my brain I'm a master interviewer... it was very subtle... youtu.be/FYD1cV2F6sc

"Is it broken?" This question often crosses a user's mind when clicking a button and waiting for a response. Checkout this post from my colleague on how we solved it specifically for AI interactions: genkit.dev/blog/streami... #AI #Genkit #UX #appDev #Developers

Is it thinking or is it broken? Building transparent AI chat UIs with Genkit

Learn how to extract and stream model thought processes using Genkit and server-sent events, and render them in a custom React component to create a highly responsive user experience.

genkit.dev

The making-of of a vibe-coding app (built with #GoogleAiStudio and #Gemini) for students revising their philosophy exam: glaforge.dev/posts/2026/0...

How I Vibecoded a Philosophy Prep App with Google AI Studio and Gemini

My daughter’s French Bac de Philosophie (philosophy baccalaureate) is tomorrow. Preparing for this examination usually involves reviewing handwritten …

glaforge.dev

Guillaume Laforge@glaforge.dev · 3mo ago

Pour nos lycéens qui passent le bac de philo demain, révisions des auteurs, oeuvres, citations clés, mouvements philo, voici une appli avec : 1⃣ un quiz d'association 2⃣ des fiches type "active recall" 3⃣ un mémento global par thème et auteur philosophia-300654570476.europe-west2.run.app

I will show you how to prevent your AI coding agent from building the wrong thing. Use the /grill-me skill so it knows what you really want. A few extra questions upfront saves lots of refactoring and frustration later.

What's next after you've built a great app on your laptop? Don't you want an agent to handle all of that for you? Find out more in my latest blog post. cloud.google.com/blog/topics/...

Ship code within minutes with the Gemini CLI DevOps Extension | Google Cloud Blog

Ship code to Google Cloud in minutes with the new CI/CD extension for Gemini CLI. Automate deployments and pipelines using AI-powered skills and MCP servers.

cloud.google.com

The new #Gemini 3.1 Text-to-Speech is pretty expressive! You can tune voices and intonation with audio tags and scene descriptions. I played with it, via my 𝗚𝗲𝗺𝗶𝗻𝗶 𝗜𝗻𝘁𝗲𝗿𝗮𝗰𝘁𝗶𝗼𝗻𝘀 𝗦𝗗𝗞 in #java glaforge.dev/posts/2026/0...

Streaming Gemini 3.1's expressive new TTS model in Java

Google just released Gemini 3.1 Flash Text-to-Speech (TTS), a new expressive TTS model that you can steer with audio tags and scene descriptions. I wanted to see how it worked with the Gemini Interact...

glaforge.dev

From a Google prototype to a production-ready v1.0 standard with 100+ partners! 🚀 We're thrilled to see the Agent2Agent protocol thriving. Let's keep building open, accessible standards together. What are you building with A2A? 🛠️ goo.gle/a2a-annivers...

A year of open collaboration: Celebrating the anniversary of A2A

The A2A protocol is one year old! Join us in celebrating with A2April.

goo.gle

Hi GKE Friends 👋 New edition of #ThisWeekInGKE is out 👇 linkedin.com/posts/sabdel... #GoogleCloud #Kubernetes #ThisWeekInGKE #GKE #GKEAutopilot #TechNews #AI #GenAI

We love seeing non-Google open source projects thrive! 🌟 Jaspr, created by Kilian Schulte, was so impressive we used it to rebuild the official Dart & Flutter websites. What open source project is inspiring you lately? 💙 goo.gle/jaspr-good-i...

goo.gle

Explore Jaspr: an open source framework making web development in Dart a great idea. See how it gives teams the freedom to innovate faster.

goo.gle

🚨 FIRST TIME EVER! 🎉 We are officially bringing a Kubernetes Developer Meetup to #GoogleCloudNext! ☁️ 🗓️ Date: Friday, April 24 ⏰ Time: 11:30 AM – 12:15 PM 📍 Location: Developer Meetup - Green lnkd.in/dgqdDRiR #GoogleCloudNext #Kubernetes #GKE #DevOps #CloudNative #K8s

Get your own tiny hat and celebrate with us! #A2April goo.gle/celebrate-a2...

goo.gle

Celebrate the Agent2Agent protocol's 1st birthday with us.

goo.gle

Running powerful local models on your phone is now a reality. The Google AI Edge Gallery goes way beyond chat with agent skills, device control, and more. It's not only useful, it's a lot of fun to play with. www.youtube.com/shorts/7vYh-...

Google AI Edge Gallery: Run Gemma 4 on your Phone

YouTube video by Cloud with Karl

youtube.com

Cloud Run Jobs or Cloud Batch? If you're running offline processing on Google Cloud, the choice isn't always obvious. While both services are built for run-to-completion tasks, they serve very different needs. Let me help you choose with my guide: medium.com/p/8590a8e3a3b1

Cloud Run Jobs vs. Cloud Batch: Choosing Your Engine for Run-to-Completion Workloads

Google Cloud offers plenty of different products and services, some of which seem to be covering overlapping needs. There are multiple…

medium.com

I created a small #Java library to extract #JSON structures from chatty #LLM outputs that don't always output pure JSON glaforge.dev/posts/2026/0...

Extracting JSON from LLM chatter with JsonSpotter

LLMs are great at generating structured data, in particularly those which support a strict JSON output mode (sometimes also called structured decoding), but sometimes they give you a bit more than the...

glaforge.dev

In real-world data, 1 is the leading digit 30% of the time. Does generated LLM data reflect Benford's Law? 📖 medium.com/google-cloud... 🎥 www.youtube.com/shorts/YtFqN...

Benford's Law: Experiments with Generated Data

Do Large Language Models Follow Benford's Law? I tested the new Gemini 3 models to see if they possess an intuitive understanding of natural numerical distributions. In this video, I explain how…

youtube.com

📢 Applications for Google Summer of Code (GSoC) are open now through March 31, 2026. Spend 12+ weeks coding with experienced mentors and earn a stipend. Read more at goo.gle/gsoc-2026-ap... #GSoC #OpenSource #GoogleSummerofCode #StudentPrograms

goo.gle

Google Summer of Code 2026 applications are now open

goo.gle

Stop hand-holding your AI agents! 🤖 Run Gemini CLI in "yolo mode" safely with a custom Docker sandbox and limited permissions. 🛡️ Link in the first comment! 👇 #GeminiCLI #GoogleCloud #AI #SoftwareDevelopment #AgenticAI

Hi GKE Friends 👋 Wow, we made it to Edition 50 of This Week In GKE! 🎉 Huge thanks to this awesome community. www.linkedin.com/pulse/in-pla... KubeCon EU in Amsterdam 🇳🇱 is almost here too! Let me know if you'll be around 🙌. #Kubernetes #GKE #GoogleCloud #TechNews #CloudNative #ThisWeekInGKE

In-Place Pod Resizing is GA, Native Custom Metrics, & Managed OpenTelemetry!

The News GKE GKE Natively Supports Custom Metrics [Preview]: GKE now natively supports custom metrics, making it significantly easier to scale your workloads using Horizontal Pod Autoscaler (HPA) base...

linkedin.com

Andrej Karpathy just open-sourced autoresearch: a framework where AI agents don't just tune hyperparameters, they rewrite the entire training codebase to improve model performance. I break down how it works in under 2 minutes. www.youtube.com/shorts/zxYF2...

Autoresearch explained: Karpathy's research automation framework

Andrej Karpathy just open-sourced autoresearch: a framework where AI agents don't just tune hyperparameters, they rewrite the entire training codebase to improve model performance. I break down how…

youtube.com

A2A Protocol v1.0 is here! 🚀 It's the first stable, production-ready standard for AI agent communication. We’re proud to build this alongside our partners. 🌉 Don't build a fence; build a bridge. a2a-protocol.org/latest/annou... How are you connecting your agents?

The Gemini 2 Embedding model is natively multimodal and now in preview. What's new? How to get started? Migration considerations? Find out more in my latest post: medium.com/google-cloud...

What you need to know about the Gemini Embedding 2 model

Embedding models typically understand one thing at a time. Text goes into one model. Images into another. And then audio requires a…

medium.com

Stop wasting your GPU budget! 🛑💻 We published a new guide on the #GoogleCloud blog with #vCluster on how to build cost-effective AI infra. Run more models, keep your costs down. 📉🚀 Read more: cloud.google.com/blog/topics/... #K8s #AI #GCP #Ollama #vCluster

Cost-Effective AI with Ollama, GKE GPU Sharing, and vCluster | Google Cloud Blog

cloud.google.com

I've just published the next part of my "Vibe Coding to Production" blog series. If you're relying on environment variables for your API keys, it's time to upgrade. I've described the end-to-end process at blog.ankur.cc/vibe-to-prod...

Fixing #AISlop with a #SKILL.md in #geminicli Well, at least, removing as much sloppiness as possible from AI generated text! And making it more human-readable ☺️ Inspired by the awesome tropes.fyi Explanations and skill: glaforge.dev/posts/2026/0...

Open source should be accessible to everyone. Join us at #KubeCon Europe 2026 for a breakdown of Kubernetes structure and communication for new contributors! 🤝 kccnceu2026.sched.com/event/2ITlD What open source skill are you most excited to build this year?

KubeCon + CloudNativeCon Europe 2026: Kubernetes Contribution 101

View more about this event at KubeCon + CloudNativeCon Europe 2026

kccnceu2026.sched.com

OpenTitan®—the first open-source silicon Root of Trust—now shipping in Chromebooks. 🚀 It brings transparency to the hardware level and a more secure ecosystem for everyone. goo.gle/opentitan-in... What's essential to securing the hardware supply chain for you? #OpenSource #OpenTitan #Security