LLMs write working scientific code fast — but structure it terribly, researchers say

anshulkundaje · x · 2026-11-19

Berkeley statistician vsbuffalo highlights a stark contrast: LLMs are remarkably good at quickly producing working scientific code, but surprisingly awful at structuring it for readability and maintainability — illustrated with a sprawling analysis script. Since code is a kind of scientific argument, he argues, it should be beautiful. The take resonated widely among computational biology researchers.

Original post →

More from coding & agent

coding & agent channel →