Crowdsourced AI agents push Quasi-RH boundary to θ=0.87477 with Lean verification
IgorCarron · x · 2026-10-22
A community auto-research project around the Quasi-RH effort reports a new Lean-verified zero-free half-plane bound of θ = 0.8747729897, submitted by contributor @HaileyStormC. The approach repeatedly sharpened bounds on sums, feeding each proved improvement into the next until zeros beyond the new boundary would yield a contradiction.
The repo (quasi-rh-hillclimb) is explicitly designed for AI research agents, with an auto-research.md guide for pushing past OpenAI's 7/8 preprint bound (Re s > 7/8). Best audited bound stands at Re s > 7/8 − 1/23600, with an architectural ceiling near 0.864 under idealized inputs. Submissions don't require full Lean verification, with official verification run in parallel; the project is now sponsored by @Agent37.
More from coding & agent
- OpenLore gives every coding agent the same memory with one folder of Markdown — Arindam_1729 · 2026-10-22
- Walking bento box built with Claude Code + Blender Python, no MCP needed — sidahuj · 2026-10-22
- Claude Code Autonomously Generated 2,000+ Krea2 Images Overnight — reynadsaltynuts · 2026-10-22
- Indie dev building game #4 with AI starts with a central game asset management hub — ezshine · 2026-10-22
- Diffy: a cross-platform desktop code review app with a custom semantic diff engine — seatedro · 2026-10-22
- Open-Source Garmin MCP Connector Plugs Workout Data Into AI Agents — Vast-Grapefruits · 2026-10-22