-

Implementing cross-silo federated learning step by step
11 min read -

From notebooks to real-world systems
10 min read
Latest
-

I Ditched My Mouse: How I Control My Computer With Hand Gestures (In 60 Lines of Python)
Computer VisionA step-by-step guide to building a “Minority Report”-style interface using OpenCV and MediaPipe
9 min read -

Estimating neighborhood-level pedestrian risk from real-world incident data
12 min read -

Explore a practical approach to analysing massive datasets with LLMs
24 min read -

Recognize data science as an engineering practice and structure education accordingly.
15 min read -

From Connections to Meaning: Why Heterogeneous Graph Transformers (HGT) Change Demand Forecasting
Data ScienceHow relationship-aware graphs turn connected forecasts into operational insight
12 min read -

If adding a feature feels like open-heart surgery on your codebase, the problem isn’t bugs,…
11 min read -

Exploring the RAG pipeline in Cursor that powers code indexing and retrieval for coding agents
10 min read -

Deploying and running Python code on cloud-based clusters
11 min read -

Learning audio embeddings with contrastive learning and deploying them in a real music recommendation app
13 min read
Editor’s Picks
-

Why specialized models still hold the 30x speed advantage in production environments
19 min read -

Why the Sophistication of Your Prompt Correlates Almost Perfectly with the Sophistication of the Response, as Research by Anthropic Found
Large Language ModelsHow prompt engineering has evolved, examined scientifically; and implications for the future of conversational AI…
9 min read -

Evaluating Multi-Step LLM-Generated Content: Why Customer Journeys Require Structural Metrics
Large Language ModelsHow to evaluate goal-oriented content designed to build engagement and deliver business results, and why…
13 min read -

Google Trends is one of the most widely used tools for analysing human behaviour at…
11 min read -

How I used open-source models to explore new frontiers in efficient code generation, using my…
10 min read -

Why modeling SKUs as a network reveals what traditional forecasts miss
11 min read -

Do you know where your data has been?
14 min read -

A multi-tier approach to segmentation, color correction, and domain-specific enhancement
13 min read -

Shapley Values are one of the most common methods for explainability, yet they can be…
9 min read
The Variable Newsletter
-

Let’s zoom in on recent approaches that push AI-powered workflows to the next level
3 min read -

Let’s make sense of the current state of retrieval-augmented generation
3 min read
Deep Dives
-

An accessible introduction to causal inference and ML
18 min read -

An introduction to neural machine translation
15 min read -

A deep dive on data transfer bottlenecks, their identification, and their resolution with the help…
15 min read -

Why SaaS Product Management Is the Best Domain for Data-Driven Professionals in 2026
Product ManagementHow I use analytics, automation, and AI to build better SaaS
14 min read -

And how it compares to the run-of-the-mill z-score
21 min read -

Numpy or SciKit-Learn might meet all your retrieval needs
14 min read