Image by Editor # Introduction Data has become an easier commodity to store in the current digital era. With the advantage of having abundant data for business, analyzing data to help companies gain insight has become more critical than ever. In most businesses, data is stored within a structured database, and SQL is used to …
Data Analytics Automation Scripts with SQL Stored Procedures Read More »
you’re anything like me, “procrastination” might as well be your middle name. There’s always that nagging hesitation before starting a new project. Just thinking about setting up the project structure, creating documentation, or writing a decent README is enough to trigger yawns. It feels like staring at a blank page for a dreaded school essay. …
How to Spin Up a Project Structure with Cookiecutter Read More »
Image by Author # Introduction If you’ve used LLMs for different tasks, you’ve probably noticed that the response often depends on how you write the prompt. This is what we call prompt engineering. The way you give instructions can be the difference between a vague reply and a precise, actionable answer. I know prompt engineering …
Prompt Engineering Templates That Work: 7 Copy-Paste Recipes for LLMs Read More »
the final quarter of 2025, it’s time to step back and examine the trends that will shape data and AI in 2026. While the headlines might focus on the latest model releases and benchmark wars, they’re far from the most transformative developments on the ground. The real change is playing out in the trenches — …
Image by Author # Introduction There are numerous tools for processing datasets today. They all claim — of course they do — that they’re the best and the right choice for you. But are they? There are two main requirements these tools should satisfy: they should easily perform everyday data analysis operations and do so …
We Benchmarked DuckDB, SQLite, and Pandas on 1M Rows: Here’s What Happened Read More »
Earlier this year, we mentioned that we’re bringing computer use capabilities to developers via the Gemini API. Today, we are releasing the Gemini 2.5 Computer Use model, our new specialized model built on Gemini 2.5 Pro’s visual understanding and reasoning capabilities that powers agents capable of interacting with user interfaces (UIs). It outperforms leading alternatives …
are planning next year’s birthday celebrations for three friends: Gabriel, Jacques, and Camille. All three of them were born in 1996, in Paris, France, so they will be 30 years old next year in 2026. Gabriel and Jacques will happen to be in Paris on their respective birthdays, while Camille will be in Tokyo, Japan, …
Image by Ideogram # Introduction When you hear the word data science, you probably think of two words: programming and statistics. In fact, the prerequisite of learning statistics often discourages people from pursuing a career in data. It doesn’t help that most data science job descriptions make it seem like you need a PhD in …
How I Actually Use Statistics as a Data Scientist Read More »
Responsibility & Safety Published 6 October 2025 Authors Raluca Ada Popa and Four Flynn Using advanced AI to fix critical software vulnerabilities Today, we’re sharing early results from our research on CodeMender, a new AI-powered agent that improves code security automatically. Software vulnerabilities are notoriously difficult and time-consuming for developers to find and fix, even …
Introducing CodeMender: an AI agent for code security Read More »
of AI hype, it feels like everyone is using Vision-Language Models and large Vision Transformers for every problem in Computer Vision. Many people see these tools as one-size-fits-all solutions and immediately use the latest, shiniest model instead of understanding the underlying signal they want to extract. But oftentimes there’s beauty to simplicity. It’s one of …
Classical Computer Vision and Perspective Transformation for Sudoku Extraction Read More »
