AI agent swarm beats SoTA on Karpathy's NanoChat benchmark in 3 days, 15k+ entries
zsakib_ · x · 2026-09-16
A team claims a swarm of AI agents crushed SoTA on Karpathy's NanoChat benchmark in just 3 days. They built their own harness on top of a graph database to run auto-autoresearch, with each iteration learning from past mistakes to improve. The agents wrote over 15,000 entries, and the whole run appears to fit on a single GPU pod.
More from coding & agent
- awa-video-reel: free Claude Code skill auto-edits shorts and records website B-roll — TawohAwa · 2026-11-02
- Econ PhD Job Market Database Hits 900+ Candidates, Open to Codex and Claude Code — aniketapanjwani · 2026-11-02
- Cron works by hand, fails on schedule: a 7-point debugging checklist — petrusenko_max · 2026-11-02
- Local quants vs Claude on 9 real private bugs: 3-bit costs thinking time, not score — FeydRowan · 2026-11-02
- Build products for AI, not humans: MCP lets Claude Code run everything — gefei55 · 2026-11-02
- Solo dev launches hosted MCP server with 31 tools scheduling to 20+ social networks — troyizzle · 2026-11-02