Large language models (LLMs) are increasingly becoming a primary source for information delivery across diverse use cases, so it’s important that their responses are factually accurate. In order to continue improving their performance on this industry-wide challenge, we have to better understand the types of use cases where models struggle to provide an accurate response …

FACTS Benchmark Suite: a new way to systematically evaluate LLMs factuality Read More »

with AI is an effective way of increasing coding speed. AI agents can handle a lot of the simple and repetitive tasks, while you can act as an orchestrator for your agents. A problem I often encounter, however, is that I have more context in my head than an AI agent could ever have. This …

How to Facilitate Effective AI Programming Read More »

Image by Author   Contents# Introduction# 1. Static Website Hosting with Nginx and Docker# 2. Multi-Container Docker Applications with Docker Compose# 3. One Database Shared by Multiple Containers# 4. Automated Continuous Integration with Jenkins in Docker# 5. Logging and Monitoring Docker# Wrapping Up # Introduction  Before jumping into the projects, let’s clear up what Docker is and why people care about it. Docker …

5 Fun Docker Projects for Absolute Beginners Read More »

AI presents an opportunity to build a more prosperous and secure world. The UK has already laid a strong foundation to seize this moment and is uniquely positioned to translate AI innovation into public benefit. That’s why we are excited to deepen our collaboration with the UK government to accelerate this work and offer a …

Our partnership with the UK government Read More »

I was working on a script the other day, and it was driving me nuts. It worked, sure, but it was just… slow. Really slow. I had that feeling that this could be so much faster if I could figure out where the hold-up was. My first thought was to start tweaking things. I could …

Think Your Python Code Is Slow? Stop Guessing and Start Measuring Read More »

Image by Author   Contents# Introduction# 1. olmOCR 2 7B 1025# 2. PP OCR v5 Server Det# 3. OCRFlux 3B# 4. MiniCPM-V 4.5# 5. InternVL 2.5 4B# 6. Granite Vision 3.3 2b# 7. Trocr Large Printed# Summary # Introduction  OCR (Optical Character Recognition) models are gaining new recognition every day. I am seeing new open-source models pop up on Hugging Face that have crushed previous …

Top 7 Open Source OCR Models Read More »

Google 2025 recap: Research breakthroughs of the year

were first introduced for images, and for images they are often easy to understand. A filter slides over pixels and detects edges, shapes, or textures. You can read this article I wrote earlier to understand how CNNs work for images with Excel. For text, the idea is the same. Instead of pixels, we slide filters …

The Machine Learning “Advent Calendar” Day 23: CNN in Excel Read More »

Image by Author   Contents# Introduction# The Data Professional’s Knowledge Problem# What Is Gistr?# Why Data Science Professionals Use Smart AI Notebooks# How Gistr Works# Here’s How You Can Use Gistr Day-to-Day# Why Gistr Is Better Than Productivity Tools# Tips to Get the Most Out of Gistr# Conclusion # Introduction  The work of a data scientist is not just about collecting data points, but about …

Gistr: The Smart AI Notebook for Organizing Knowledge Read More »

Announcing a new, open suite of tools for language model interpretability Large Language Models (LLMs) are capable of incredible feats of reasoning, yet their internal decision-making processes remain largely opaque. Should a system not behave as expected, a lack of visibility into its internal workings can make it difficult to pinpoint the exact reason for …

Gemma Scope 2: Helping the AI Safety Community Deepen Understanding of Complex Language Model Behavior Read More »