Contents# Introduction# Why Gemma 4?# The Modelfile# Wiring Claude Code to the Local Model# Agentic Task Walkthrough# Wrapping Up # Introduction  Visualize this: a multi-agent workflow that reads files, writes patches, runs tests, and iterates across four services, making 400 API calls in a single afternoon. The notification arrives. You have crossed the soft limit again. Every token costs money, every …

Local Agentic Programming on the Cheap: Claude Code + Ollama + Gemma4 Read More »

Twenty years ago, translation at Google began as one of our pioneering machine learning experiments to turn the science of language into the magic of human connection. That experiment has come a long way with over a trillion words being translated for billions of users across our products every month. Today, we’re taking our next …

Gemini 3.5 Live Translate is here Read More »

ContentsWith FIFA set to kick off on Thursday, June 11, 2026, the opening match at the Mexico City Stadium, I think it would be fun to build the best ML model we can to predict match outcomes. To do this, I have brought together several databases—49,000 matches—with data on Elo ratings, match results, and cup …

Can Machine Learning Predict the World Cup? Read More »

  Contents# Introduction# Measuring Calibration# Why LLMs Complicate the Standard Setup# Applying Temperature Scaling# Applying Platt Scaling# Applying Isotonic Regression# What the Literature Leaves Open# Conclusion # Introduction  A model that says it is 90% confident should be right 90% of the time. When that relationship breaks down, you get a miscalibration problem. The model’s scores stop telling you anything useful about reliability. For …

A Deep Dive into Calibration of Language Models: Platt Scaling, Isotonic Regression, Temperature Scaling Read More »

3.5 Flash: agentic tasks at scale This balance of speed and performance makes 3.5 Flash ideal for tackling long-horizon agentic tasks. What used to take a developer days or an auditor weeks, 3.5 Flash can now help complete in a fraction of the time, often at less than half the cost of other frontier models. …

Gemini 3.5: frontier intelligence with action Read More »

. The functions had grown too long and the variable names made no sense anymore. Every time I wanted feedback on a file, I stopped, opened the chat, copied the whole thing in, and waited. Then went back to the editor, applied the change, opened the next file, and did it again. At some point …

My AI Couldn’t See My Files — I Built a Zero-Dependency MCP Server Read More »

  Contents# Introduction# Redefining the Baseline# The Orchestration Ecosystem# Shifting the Workflow: From Procedural to Evaluative# The 2026 Skill Stack# The Evolution of Roles# Keeping Pace # Introduction  Something has shifted at the intersection of AI and data science, and it’s changed how practitioners work. The systems deployed today don’t just generate a response and stop. They plan. They execute multi-step tasks. They …

What the Agentic Era Means for Data Science Read More »

As generative media becomes more advanced and accessible, it’s helpful to know where content comes from, and whether it’s been altered. Today, we’re expanding our content transparency and verification tools in Search, Gemini, Chrome, Pixel and Cloud, and deepening our partnership with the broader industry. ContentsScaling our technologyProviding more ways to verify content Scaling our …

Tools to understand how content was created and edited Read More »

underlying society is changing.  That was one of the ideas from Max Buckley’s talk at AI Engineer Singapore, and it has stuck with me ever since. For decades, software engineering was organised around scarcity. Code was expensive to write, engineers were scarce and features took time. This assumption shaped how teams worked. We prioritised carefully …

Code Is Cheap. Engineering Judgement Is Now the Scarce Resource Read More »

  Contents# Introduction# Step-by-Step Guide# Final Remarks # Introduction  Mocking Internet of Things (IoT) sensor data that would be otherwise difficult to gather at scale can constitute a valuable approach to facilitate experimental analyses, projects, and studies. However, it requires much more than random value generation: it necessitates a chronological timeline, device metadata, and a need to reflect natural …

Mocking a Year of IoT Sensor Time Series Data with Mimesis Read More »