Gemini 3.7 Flash helps revive interactive CMA-ES explainer site
doodlestein · x · 2026-08-26
The author shared how they used Gemini 3.7 Flash to successfully fix and revive an explainer site for the CMA-ES (Covariance Matrix Adaptation Evolution Strategy) algorithm.
The site provides an interactive explanation, mathematical derivations, and live simulations of CMA-ES. CMA-ES is a standard workhorse for black-box optimization, particularly useful when gradients do not exist, suffer from severe noise, or are computationally expensive (e.g., aircraft CFD, bridge FEA). It maintains a Gaussian search distribution and iteratively adapts the mean and covariance matrix to mimic the inverse Hessian, discovering landscape curvature without derivatives. The site is built with WASM + Rust, running a sub-millisecond SIMD parallel engine in the browser.
More from Research
- OraRL: Efficient and Scalable RL for Video MLLMs — Yunheng Li · 2026-08-26
- Three hours of agentic research shows frontier LLMs can evade AI detectors — maier_ak · 2026-08-26
- How LLMs Self-Correct Mid-Generation: The Role of Reasoning RL and Instructions — dejanseo · 2026-08-26
- U. de Chile Students Publish Book on Maturana and Varela's Relevance in AI — PolarBearby · 2026-08-26
- Face Anything: 4D Face Reconstruction from Any Image Sequence (ECCV 2026) — rsasaki0109 · 2026-08-26
- From PDE Numerical Solvers to Neural Emulators and Back: PhD Thesis — chaumian · 2026-08-26