Research Blog
How compere uses bandit algorithms to rank items with minimal pairwise comparisons — applications in search evaluation, recommendation, and tournament design, vs Bradley-Terry and TrueSkill.
How savanty turns English problem descriptions into mathematically guaranteed solutions. The case for LLM-to-formal-solver pipelines over pure LLM output.
How compere uses MAB algorithms to rank items effectively with minimal pairwise feedback — applications in search and recommendation.
Describe optimisation problems in plain English and receive mathematically guaranteed solutions — no PhD required.
From visual signal specification to verified Rust executable — how sigc turns alpha hypotheses into production-ready code in minutes.