-
Cursor is great at writing code but not as good when it comes to design
6 min read -
This article introduces the Gaussian Mixture Model as a natural extension of k-Means, by improving…
6 min read
Latest
-
What a simple puzzle game reveals about experimentation, product thinking, and data science
14 min read -
A detailed walkthrough of the YOLOv1 architecture and its PyTorch implementation from scratch
17 min read -
How to upgrade and optimize legacy AI/ML models
19 min read -
On the challenges of producing reliable insights and avoiding common mistakes
3 min read -
A new NeurIPS 2025 paper shows how self-supervised learning imbues ViT with better image understanding…
16 min read -
How to implement a training algorithm that finally looks like “real” machine learning
7 min read -
A factory operator that discovered happiness by switching from notebook to streamlit – (Image Generated…
21 min read -
Using Apache Iceberg on AWS with Athena, Glue/Spark and DuckDB
12 min read -
Why continuous learning matters & how to come up with topics to study
7 min read
Editor’s Picks
-
Overcoming the Hidden Performance Traps of Variable-Shaped Tensors: Efficient Data Sampling in PyTorch
Deep LearningPyTorch Model Performance Analysis and Optimization — Part 11
10 min read -
What mattered: robust agents, glass-box reasoning, and red-team resilience
16 min read -
A beginner-friendly tutorial exploring the Python “qrcode” Package
7 min read -
A modification to the Boruta algorithm that dramatically reduces computation while maintaining high sensitivity
19 min read -
The most dangerous KPIs aren’t broken; they’re the ones trusted long after they’ve lost their…
7 min read -
An honest view from a 10-year AI Engineer
9 min read -
The simple shift in training that unlocks foresight, faster inference, and better reasoning.
14 min read -
Have we all been tricked into believing in an impossible, extremely expensive future?
10 min read -
From insurance premiums to courtrooms: the impact of noise
24 min read
The Variable Newsletter
-
TDS Newsletter: November Must-Reads on GraphRAG, ML Projects, LLM-Powered Time-Series Analysis, and More
The VariableDon’t miss our most-read stories of the past month
3 min read -
Many practitioners like to jump headfirst into the nitty-gritty details of implementing AI-powered tools. We get…
3 min read
Deep Dives
-
And what this means for generative engine optimization (GEO)
15 min read -
The most famous applications of LLMs are the ones that I like to call the…
15 min read -
Benchmarking JSON libraries for large payloads
12 min read -
This first day of the Advent Calendar introduces the k-NN regressor, the simplest distance-based model.…
16 min read -
You can’t align what you don’t evaluate
16 min read -
Neural Networks Are Blurry, Symbolic Systems Are Fragmented. Sparse Autoencoders Help Us Combine Them.
Deep LearningNeural and symbolic models compress the world in fundamentally different ways, and Sparse Autoencoders (SAEs)…
17 min read