Improving Statistical Algorithms with Claude and Gemini

IanArawjo · x · 2026-07-16

The author shares their experience using LLMs for scientific research: Gemini provided the initial concept, and Claude Sonnet 3.5 handled the code implementation. The model successfully generalized an FWER correction method for pairwise confidence intervals into a universal version applicable to any CI method by reversing the alpha value instead of the critical value. This demonstrates the practical orchestration and coding capabilities of LLMs in cross-domain algorithmic innovation.

Original post →

More from coding & agent

coding & agent channel →