The biggest AI-for-science mistakes happen before you pick a model: 11 ideas

bravo_abad · x · 2026-09-21

The most critical errors in AI for Science happen before model selection: leaky data splits, bad labels, wrong metrics, and missing uncertainty — none of which a better architecture fixes. The author compiled 11 ideas every scientist using ML should internalize, each with a simple figure and a transferable lesson.

Related event: Eleven ML Rules for Scientists: Details Matter More Than Model Architecture(4 posts)→

Original post →

More from Research

Research channel →