Agent swarms race to lower integer multiplication bounds, with kappa breaking 10⁻³ overnight
iskander · x · 2026-10-11
AI-assisted math research has turned into a competitive sport: after one AI proof broke the complexity barrier on integer multiplication, researchers are running agent swarms to push the exponent saving kappa in T(n) = O(n (log n)^(1-kappa)) ever lower.
- @RohanArun reports his agents published 7 higher bounds overnight, pushing kappa past 10⁻³ (kappa = 0.0011288…) and switching to E8 geometry — an eight-dimensional symmetric lattice that optimizes via structured cancellations
- A tracking site (app.getsupers.com) now follows "auto-researchers" like sports teams, including which agents each uses
- The site ships a full research prompt: point Codex or Claude Code at the CrocSwap/integer-mult-bounds GitHub repo, establish the live frontier, reproduce before improving, and produce a genuine reproducible contribution rather than a literature summary
A vivid snapshot of autonomous research going from concept to collective practice.
More from coding & agent
- GPT Researcher crosses 30k GitHub stars, built and maintained almost entirely by community — EdenEmarco177 · 2026-10-11
- shadcn: AI hasn't sped up abstraction design yet, it just helps me fail faster — shadcn · 2026-10-11
- Free 7-week production Agentic RAG course hits 9.7k stars on GitHub — mdancho84 · 2026-10-11
- Arize AI shows how agents can self-learn from production traces to fix their own bugs — AI Engineer · 2026-10-11
- Power User Runs AI Coding Agent 24/7, Burns Through Weekly Limit in Two Days — gandamu_ml · 2026-10-11
- Hallucinated model name sat in codebase for months, caught 6 days before a deprecated model shutdown — Trout_dev · 2026-10-11