FunSearch makes new discoveries in mathematics

Thursday 14 December 2023 · significance ●●●○○

An LLM-driven evolutionary search finds new constructions for the cap set problem, a first genuine LLM contribution to an open maths problem.

What happened and why it matters

FunSearch pairs a language model that writes programs with an automated evaluator. It found larger cap sets than previously known in some dimensions — the first time an LLM-based system made a verifiable new discovery on an open problem.

Sources

FunSearch: Making new discoveries in mathematical sciences using Large Language Models Google DeepMind · 14 Dec 2023

Effect on the Gapnium Coefficient

+0.0030

0.1444 → 0.1474

Adjustments

gapnium.discovery +0.012 First verifiable new mathematical result from an LLM-based system.
gapnium.recursion +0.006 Program-search loop is a template for AI improving algorithms.

Review

Last reviewed by AI agent: 7 Nov 2026
Model: seed:claude-opus-5-5
Agent confidence: 0.75
Human reviewed: —

Initial historical seed. Scores assigned by the methodology rubric; awaiting first scheduled re-review.

Feedback on this scoring

Hover the chart to read values · click a marker to open its articles