, my AI assistant stored a memory with an importance score of 8/10. Content: “Investigating Bun.js as a potential runtime swap.” I never actually switched to Bun. To be fair, it was a two-day curiosity that went nowhere. But this memory persisted for six months, popping up each time I asked about my build process …
Image by Editor # Introduction Google NotebookLM has evolved far beyond a simple study aid. With the addition of the recent updates pushed just this year, it has transformed into a full-stack research, synthesis, and content production environment. For people regularly juggling complex sources, NotebookLM now bridges the gap between raw information and polished deliverables. …
Advanced NotebookLM Tips & Tricks for Power Users Read More »
Introduction After the initial euphoria with the new calendar-based time intelligence, I started looking deeper into the new feature to see what these new possibilities mean in the real world. You will find several links about it in the References section at the end of this piece, including a SQLBI article, which takes you deep …
When Things Get Weird with Custom Calendars in Tabular Models Read More »
Image by Editor # Introduction Working intensively with data in Python teaches all of us an important lesson: data cleaning usually doesn’t feel much like performing data science, but rather like acting as a digital janitor. Here’s what it takes in most use cases: loading a dataset, discovering many column names are messy, coming across …
All About Pyjanitor’s Method Chaining Functionality, And Why Its Useful Read More »
in AI for a while, you are probably an LLM/Agent/Chat user, but have you ever asked yourself how these tools will be trained in the near future, and what if we have already used up the data we need to train models? Many theories say that we are running out of high-quality, human-generated data to …
Why AI Is Training on Its Own Garbage (and How to Fix It) Read More »
Image by Author # Introduction Choosing a backend is one of the most important decisions you will make when building a modern web or mobile app. For years, Firebase has been the go-to choice for developers who want to launch quickly without managing servers. But recently, Supabase has emerged as a powerful open-source alternative. If …
Supabase vs Firebase: Which Backend Is Right for Your Next App? Read More »
This article is the first of three parts. Each part stands on its own, so you don’t need to read the others to understand it. The dot product is one of the most important operations in machine learning – but it’s hard to understand without the right geometric foundations. In this first part, we build …
The Geometry Behind the Dot Product: Unit Vectors, Projections, and Intuition Read More »
Image by Author # Introduction When applying for a job at Meta (formerly Facebook), Apple, Amazon, Netflix, or Alphabet (Google) — collectively known as FAANG — interviews rarely test whether you can recite textbook definitions. Instead, interviewers want to see whether you analyze data critically and whether you would identify a bad analysis before it …
The Most Common Statistical Traps in FAANG Interviews Read More »
At the edge, our E2B and E4B models redefine on-device utility, prioritizing multimodal capabilities, low-latency processing and seamless ecosystem integration over raw parameter count. Powerful, accessible, open To power the next generation of pioneering research and products, we’ve sized the Gemma 4 models specifically to run and fine-tune efficiently on hardware — from billions of …
we try to train a very deep neural network model, one issue that we might encounter is the vanishing gradient problem. This is essentially a problem where the weight update of a model during training slows down or even stops, hence causing the model not to improve. When a network is very deep, the gradient …
