-
👁 An image of scissors cutting off the tail of a bell curve Behind a customer’s API, a high-quality answer isn’t enough. It has to be usable, which…
27 min read -
👁 Image A concrete bias–variance lesson: why the smallest model had the best cross-validated fit, and how…
10 min read
Latest
-
👁 Image A team cut their AI inference bill by more than half. Three months later, customer…
21 min read -
👁 Image Use coding agents to power your knowledge base
9 min read -
👁 Image Using Gemma 4, Ollama, OpenAI Agents SDK, and Tavily MCP to build a lightweight research…
8 min read -
👁 Image Why memorizing for the exam doesn’t mean you understand the subject
10 min read -
👁 Image Enterprise Document Intelligence [Vol.1 #M1] – The thesis behind every architectural choice in this series
20 min read -
👁 Image How to smash through data / ML behavioural interviews
10 min read -
👁 Image I benchmarked raw chat history, vector-only RAG, and a context graph on the same multi-agent…
19 min read -
👁 Image A reproducible benchmark on latency, cost, and reproducibility, and where agents actually earn their keep.
17 min read -
👁 Image Beyond the Straight Line: Choosing Between OLS, Interaction Terms, and Tweedie Regression
Data ScienceWhether you should stick to a classic Ordinary Least Squares regression, introduce interaction terms, or…
14 min read
Editor’s Picks
-
👁 Image Your First Task as a Data Engineer in a New Company? Make the ETL Pipeline Testable
Data EngineeringA practical data engineering onboarding workflow for environment setup, automated testing, and AI-assisted development.
9 min read -
👁 Image A practical walkthrough using text-to-SQL as the example
13 min read -
👁 Photo by National Institute of Allergy and Infectious Diseases on Unsplash How Gemini solved my Pandas problem in seconds, and why data science fundamentals still matter…
7 min read -
👁 Image GPU-Resident Top-K for Agentic RAG: I Built a CUDA Kernel So My Retrieval Step Would Stop Bouncing Off the GPU
Agentic AIThe PCIe transfer latency is silently bottlenecking your agentic inference. Here is how building a…
31 min read -
👁 Image Structured Outputs with LLMs: JSON Mode, Function Calling, and When to Use Each
Large Language ModelsGetting reliable, readable responses out of your LLM, and knowing which tool to reach for
13 min read -
👁 Image How unit economics should set your classification cutoff, and why they rarely do.
15 min read -
👁 Image Most LLM applications need a clear workflow, not an autonomous agent. Here’s how to build…
19 min read -
👁 Image Budgets for AI tokens can’t be infinite, no matter how much hyperscalers wish they were
8 min read -
👁 Soccer goal in a desert by sunset. Image generated with Leonardo AI A single model hands you a single answer and no sense of how much it…
11 min read
The Variable Newsletter
Deep Dives
-
👁 Image Beat the 8GB VRAM limit. Learn how to run three different LLMs on a single…
21 min read -
👁 Image Finding the right anchors for RAG: keyword, embedding, and TOC signals in parallel
Large Language ModelsEnterprise Document Intelligence [Vol.1 #7B] – Retrieval is filtering on structured tables: keywords first, TOC…
33 min read -
👁 Image Enterprise Document Intelligence [Vol.1 #7A] – Stop searching strings. Filter line_df and toc_df. Pick anchors…
21 min read -
👁 Image Why one-hot encoding isn’t always the best approach, and alternative encodings
21 min read -
👁 Image The intuition behind neural networks and why they need activation functions.
20 min read -
👁 Image Understanding how LLMs interact with the world around them, from returning data to taking action
12 min read
