AI

We all know the usual Time Intelligence function based on years, quarters, months, and days. But sometimes, we need to perform more exotic timer intelligence calculations. But we should not forget to consider performance while programming the measures.  Introduction  There are many Dax functions in Power BI for Time Intelligence Measures.  The most common are:  You can find a comprehensive list of Time Intelligence functions here: Time Intelligence – DAX Guide. These functions cover the most

This post was co-authored with Rafael Guedes. Introduction Traditional models can only process a single type of data, such as text, images, or tabular data. Multimodality is a trending concept in the AI research community, referring to a model’s ability to learn from multiple types of data simultaneously. This new technology (not really new, but significantly improved in the last few months) has numerous potential applications that will transform the user experience of many products.

Large Language models (LLMs) have witnessed impressive progress and these large models can do a variety of tasks, from generating human-like text to answering questions. However, understanding how these models work still remains challenging, especially due a phenomenon called superposition where features are mixed into one neuron, making it very difficult to extract human understandable representation from the original model structure. This is where methods like sparse Autoencoder appear to disentangle the features for interpretability. 

27 days, 1,700+ commits, 99,9% AI generated code The narrative around AI development tools has become increasingly detached from reality. YouTube is filled with claims of building complex applications in hours using AI assistants. The truth? I spent 27 days building ObjectiveScope under a strict constraint: the AI tools would handle ALL coding, debugging, and implementation, while I acted purely as the orchestrator. This wasn’t just about building a product — it was a rigorous

Nowadays, data science projects do not end with the proof of concept; every project has the goal of being used in production. It is important, therefore, to deliver high-quality code. I have been working as a data scientist for more than ten years and I have noticed that juniors usually have a weak level in development, which is understandable, because to be a data scientist you need to master math, statistics, algorithmics, development, and have

Acknowledgements The research described here is a joint effort between many Google Research, Google Deepmind and Google Cloud AI teams. We thank our co-authors at Fleming Initiative and Imperial College London, Houston Methodist Hospital, Sequome, and Stanford University — José R Penadés, Tiago R D Costa, Vikram Dhillon, Eeshit Dhaval Vaishnav, Byron Lee, Jacob Blum and Gary Peltz. We appreciate Subhashini Venugopalan and Yun Liu for their detailed feedback on the manuscripts described here. We

In July 1959, Arthur Samuel developed one of the first agents to play the game of checkers. What constitutes an agent that plays checkers can be best described in Samuel’s own words, “…a computer [that] can be programmed so that it will learn to play a better game of checkers than can be played by the person who wrote the program” [1]. The checkers’ agent tries to follow the idea of simulating every possible move

Ethical issues aside, should you be honest when asked how certain you are about some belief? Of course, it depends. In this blog post, you’ll learn on what. Different ways of evaluating probabilistic predictions come with dramatically different degrees of “optimal honesty”. Perhaps surprisingly, the linear function that assigns +1 to true and fully confident statements, 0 to admitted ignorance and -1 to wrong but fully confident statements incentivizes exaggerated, dishonest boldness. If you rate forecasts

With the recent explosion of interest in large language models (LLMs), they often seem almost magical. But let’s demystify them. I wanted to step back and unpack the fundamentals — breaking down how LLMs are built, trained, and fine-tuned to become the AI systems we interact with today. This two-part deep dive is something I’ve been meaning to do for a while and was also inspired by Andrej Karpathy’s widely popular 3.5-hour YouTube video, which has racked