-
Part 1: The basics — discretization of time, censoring and the life table
11 min read -
Improve Claude Code performance by having it validate its own work
8 min read
Latest
-
Your RAG system isn’t failing at retrieval — it’s failing at reasoning. This article shows…
25 min read -
Part 2. Building scale-invariant agents that seamlessly change contexts
11 min read -
A practical guide to understanding AI agent design, ReAct workflows, and when to scale from…
13 min read -
Building a knowledge base for AI models isn’t a one-time task but an iterative process…
15 min read -
Solving multiplayer games with function approximation
9 min read -
How AI Tools Generate Technical Debt in IoT Systems — and What to Do About It
Artificial IntelligenceAI tools speed up IoT development — but closer to the hardware, the same code…
8 min read -
A review of the Cross-Stage Partial Network paper — and a from-scratch PyTorch implementation
23 min read -
Inference Scaling (Test-Time Compute): Why Reasoning Models Raise Your Compute Bill
Large Language ModelsWhy reasoning models dramatically increase token usage, latency, and infrastructure costs in production systems
11 min read -
A practitioner’s decision framework for Ridge, Lasso, and ElasticNet based on three quantities you can…
14 min read
Editor’s Picks
-
What people actually look for when hiring juniors that stand out.
7 min read -
Or why what appears powerful can be methodologically fragile
17 min read -
Caching, lazy-loading, routing, compaction, and more
25 min read -
Using autoresearch to optimise marketing campaigns under budget constraints
14 min read -
What does correlation tells us?
6 min read -
Blast-radius control tells you how much to break. Intent tells you what breaking it will…
18 min read -
Sabrine Bendimerad on why flexibility is a crucial data science skill, the risks of outsourcing…
9 min read -
Why learn 8 scripts when you can learn 256 bytes?
12 min read -
How does decision-gravity dictate this gap?
12 min read
The Variable Newsletter
-
Authors can now benefit from updated earning tiers and a higher article cap
2 min read -
Sorting through the good, bad, and ambiguous aspects of vibe coding
4 min read
Deep Dives
-
A data quality case study from English local elections on categorical normalisation, metric validation, and…
11 min read -
How to make decisions when your spreadsheet is lying about the future
15 min read -
Structure is all you need
15 min read -
System Design Series: Apache Flink from 10,000 Feet, and Building a Flink-powered Recommendation Engine
Data ScienceA deep dive into how Apache Flink works, why it exists, and learning it while…
17 min read -
PyTorch NaNs Are Silent Killers — So I Built a 3ms Hook to Catch Them at the Exact Layer
Deep LearningNaNs don’t crash your training — they quietly destroy it. After losing hours to a…
11 min read -
A simulation of how a single forecast change moves through five planning teams, and why…
14 min read