-
Because the alternative is much too dangerous
17 min read -
An introduction to multi-agent systems
13 min read
Latest
-
My approach to guiding the choice between Eppo and Statsig, and the lessons learned
14 min read -
Building a forecast from Elo, Poisson, and 10,000 simulations
8 min read -
My SciPy ODE Solver Was Killing My Bayesian Inference: A Cosmologist’s Honest Account of Discovering Diffrax
Mathwhat it costs, what it gains and the three mistakes that I make
13 min read -
I got tired of copying files into an AI chat just to get feedback. So…
17 min read -
How a simple choice shapes exploration, safety, and efficiency
18 min read -
Using DSPy to automatically create, evaluate, and optimize your prompts
20 min read -
Python tutorial for fine-tuning a Mistral Small 3.1 on an imbalanced training set to classify…
9 min read -
Abacus.AI and the case for unified AI workflows
6 min read -
In Part 1 of this series, we introduced Chronos-2, a time-series foundation model. We got…
17 min read
Editor’s Picks
-
When images, mosaics, and data cubes exist in abundance, but field labels are expensive, rare,…
8 min read -
AI does not decide who gets fired. Companies do.
8 min read -
A comprehensive guide to optimizing LLM inference by eliminating padding overhead with hardware-aware sequence packing.
31 min read -
How to set the rules that keep agents effective and out of trouble
8 min read -
The barriers to building have collapsed. That shifts the bottleneck to ownership, validation, taste, and…
7 min read -
Research projects in the age of AI
11 min read -
How Knives Out teaches Bayesian thinking (without you realizing it)
11 min read -
Meta-Cognitive Regulation Might Be the Most Important AI Skill Nobody Is Talking About
Artificial IntelligenceAs AI gets smarter, the real differentiator may be how well humans regulate their own…
7 min read -
Part 1: A practitioner’s walkthrough of univariate, multivariate, covariate-informed, and cold-start forecasting.
22 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
-
Understanding how FPN allows deep learning models detecting small objects and how to implement it…
20 min read -
Testing fourteen engines on ninety-three human documents
16 min read -
Enterprise Document Intelligence [Vol.1 #3] – Why the ML toolkit (hyperparameter sweeps, train/test splits, explainability…
30 min read -
Enterprise Document Intelligence [Vol. 1 #2] Why the same vector search that handles synonyms and…
44 min read -
Most engineers see quantization as shrinking vectors. TurboQuant asks a harder question: can you shrink…
17 min read -
Enterprise Document Intelligence [Vol. 1 #1] The smallest version of RAG that actually works, on…
41 min read