Contents# Introduction# Setting Up the Dataset# 1. Measuring Time Between Events with LAG()# 2. Comparing a Row to Other Rows in the Same Table with a Self-Join# 3. Selecting the Top Row per Group with ROW_NUMBER()# 4. Segmenting Customers by Spend with NTILE(n)# 5. Smoothing Noisy Data with a Rolling Window# 6. Aggregating Conditionally with FILTER# 7. Detecting Consecutive Activity Streaks with Window …

Practical SQL Tricks Every Data Scientist Should Know Read More »

ContentsIntroductionBarrier 1 | Context and failure recallBarrier 2 | Elastic infrastructureBarrier 3 | Operational Agents and Quality DataBarrier 4 | Git for DataBarrier 5 | Pervasion through the industryBarrier 6 | Agent Sandboxes and New OrchestratorsBarrier 7 | Standards for Proxy Servers and Agent DefinitionPutting it all together | A Single Pane of Glass for AI Introduction , AI examples …

7 Crucial Barriers Between Data Teams and Self-Healing Data Architecture Read More »

  Contents# Introduction# What Is a Loss Function?# Mean Squared Error# Mean Absolute Error# Cross-Entropy Loss# Loss vs. Accuracy# The Training Loop# Final Thoughts # Introduction  I know that when beginners start learning machine learning, things seem easy at first. You follow a tutorial that asks you to load a dataset, train a model, and then you see something like this: loss = “mse” …

Loss Function Explained For Noobs (How Models Know They Are Wrong) Read More »

AI has the potential to help solve some of the world’s biggest challenges — not just in the digital realm, but in the physical world, too. Robotics is one of the most exciting frontiers of AI, where advances in language, vision and action models can help create intelligent machines that interact with the real world …

Powering the future of robotics in Europe Read More »

says “this customer’s probability of leaving is 0.4” and your code does predict(X) >= 0.5, you have just made a pricing decision: you decided that the cost of sending a retention offer to a customer who would have stayed is exactly equal to the cost of losing one who would have left, and on the …

Your Churn Threshold Is a Pricing Decision Read More »

  Contents# Introduction# Step 1: Building the Foundation# Step 2: Designing Prompts and Building Tool-Calling Systems# Step 3: Building Retrieval Systems Beyond the Basics# Step 4: Fine-Tuning and Aligning Models# Step 5: Serving and Operating LLM Applications# Recommended Learning Resources# Final Thoughts # Introduction  An LLM engineer is not the same thing as a general machine learning engineer. Where a machine learning engineer might …

The Roadmap to Becoming an LLM Engineer in 2026 Read More »

Today, we are introducing Gemma 4 12B, our latest model designed to bring agentic multimodal intelligence directly to laptops. Bridging the gap between our edge-friendly E4B and our more advanced 26B Mixture of Experts (MoE), Gemma 4 12B packages powerful capabilities inside a reduced memory footprint. It is also our first mid-sized model to feature …

Introducing Gemma 4 12B Read More »

I was asked to do something new at work: Given a data dump of unstructured text data, give us a detailed PDF report of insights about what customers are saying about our products this quarter. So I wrote a clear prompt. Gave Claude a detailed set of instructions. Fed it the dataset. It gave me …

4 Lines You Should Include in Your Claude Skill Read More »

    Contents# Introduction# How Claude Code Connects to Any Local Model# Backend 1: Ollama# Backend 2: LM Studio# Backend 3: llama.cpp# The Complete settings.json# Best Local Models for Claude Code in 2026# Troubleshooting Common Issues# Conclusion # Introduction  Agentic coding sessions are expensive. A single Claude Code session — reading files, writing code, running tests, iterating — can burn 10–50x more tokens than a …

Pairing Claude Code with Local Models Read More »

ContentsWhy diffusion for text?The trade-off with traditional models Why diffusion for text? While the AI research community has explored diffusion-based text generation for years, applying it to large models has remained a challenge. DiffusionGemma changes this by shifting how models use hardware. The trade-off with traditional models Most language models act like a typewriter, generating …

Introducing DiffusionGemma Read More »