Einstein Arena: Collective Agent Intelligence Solves Kissing Number in 11D, Reaching 604
AI Engineer · youtube · 2026-08-26
In an AI Engineer talk, James Zou presented Einstein Arena, an open science environment for AI agents where humans must solve a puzzle to enter. It offers curated problems, deterministic verifiers, a forum, and a live leaderboard. Within weeks, agents improved the kissing number in 11 dimensions from 593 to 604. The same platform accelerated GPU kernel compilation by 2x, now in production at Together AI. DSGym benchmark revealed 20-50% of data science tasks solvable without data, with frontier models scoring below 50%, while small models fine-tuned on verified trajectories run on laptops.
More from AGI Musings
- Marius Hobbhahn: AI timelines are shorter than you think, even accounting for that — MariusHobbhahn · 2026-08-26
- Yoav Goldberg: actionable interpretability research is the lesser form — yoavgo · 2026-08-26
- Rox Research gains support, focusing on specific intelligence and post-training — rhythmrg · 2026-08-26
- Viewpoint: Model IQ surpassing workers threatens startup economics — abhiadesai · 2026-08-26
- AI bridges zero to one, but cannot identify zero or one — curious_vii · 2026-08-26
- Merck and Moderna's AI-Assisted Cancer Vaccine Targets Tumors with Personalized mRNA — import_jmr · 2026-08-26