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.
More from coding & agent
- 16-time Microsoft MVP demos a custom PowerShell agent inside Microsoft's Intelligent Terminal — dfinke · 2026-11-19
- Datadog and Baseten fine-tune Qwen 3.5 9B for a 50x faster LLM summarizer — baseten · 2026-11-19
- Developer adds a real-time talking-head avatar to his local voice agent using open-weight video model — Scobleizer · 2026-11-19
- Personal agent auto-clips a livestream into highlight videos with just two prompts — Scobleizer · 2026-11-19
- Beyond a single bot: building a small agent fleet with OpenClaw Specialist Teams — heyneighbor · 2026-11-19
- Cognition's Walden Yan gives away 10,000 Devin Bots with up to $10K credits via Text Poke — marvinvonhagen · 2026-11-19