Director, Developer Relations

Why the AI classifier came back: System 1 decisions and RLCD calibration with Jev from TypeSafe AI.

An evaluation of the Google Cloud Developer plugin with NVIDIA SkillEvaluator and Harbor

News, tutorials, and updates from the Firebase team.

Using deep research, a browser agent, and calendar integration for trip logistics

Are there tasks you find yourself doing repeatedly, wondering if there is a better way? For me, one of those is writing a bi-weekly…

The power of vibe coding is undeniable. Describe what you want in Google AI Studio, Antigravity, or your favorite agent, and you'll get it! You don't need to know the math behind why things work the w...

Most AI tools focus on writing new code, but up to 80% of the cost of software comes from maintenance. What if an intelligent agent could…

How can corporations better support open source maintainers? Explore feedback from open source communities on creative funding.

I share why most developers fall into the coverage trap when prompting AI coding agents and how I treat test suites as architectural guardrails. In this walkthrough, I break down five essential…

YouTube video by Cloud with Karl

Today's AI coding agents don't hallucinate the way they used to; we're generally past the "inventing fake APIs" stage. The failure mode now is subtler: they over-index on part of the codebase and miss...

YouTube video by Lon.TV

The Google Antigravity SDK is a Python framework for building and running autonomous agents. It decouples your agent’s logic from where it runs, letting you focus on what the agent does while the SDK ...

Can you turn a scribble on a paper napkin into a fully functioning, beautiful web application in under 3 minutes? In this video, I take on the Napkin Challenge! With any rehearsing, I uploaded a…

Nano Banana 2 and Nano Banana Pro are generally available today via Gemini Enterprise Agent Platform. These models empower you to integrate high-quality image generation and editing capabilities…

At 95% per-step reliability, a 20-step agent succeeds less than 36% of the time. I cover the three metrics — success rate, token usage, and duration — that tell you where your agent is actually…

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.

Agentic software development can be fast and furious. It can go even faster if you run multiple agents in parallel. Multiple agents can…

YouTube video by Cloud with Karl

Automating code reviews with AI can dramatically speed up your team’s development cycle. However, the reality is that many development…

Google just dropped Gemma 4, and I'm sharing the scoop on this new open weight model family. Built on Gemini 3 research, I'll walk you through its size variants, mixture of experts architecture, and…

YouTube video by Cloud with Karl

Learn the 5 essential techniques—including intelligent L7 routing, quantization, and speculative decoding—to move your LLM inference workloads closer to the efficient frontier, maximizing throughput…

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…

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…

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

Gemini 3.1 Flash-Lite is our fastest and most cost-efficient Gemini 3 series model yet.