While Model Trains

Read data blog posts.
Carefully handpicked.
Presented 3 at a time.

Why Correlation Usually ≠ Causation

Gwern

"Despite this admonition, people are overconfident in claiming correlations to support favored causal interpretations and are surprised by the results of randomized experiments, suggesting that they are biased & systematically underestimate the prevalence of confounds / common-causation."

Read it!

4.2 Gigabytes, or: How to Draw Anything

Andy Salerno

Sketching a cityscape and a spaceship, and then running both through Stable Diffusion to demonstrate the technology.

Read it!

Writing Robust Tests for Data & Machine Learning Pipelines

Eugene Yan

An in-depth analysis of why certain types of tests break more frequently than others, along with suggestions for creating more robust pipeline tests.

Read it!