Insider rebuts claim that agent swarm contributed only 10% to Navier-Stokes proof
scaling01 · x · 2026-09-18
Pushing back on the claim that the "agent swarm" component contributed only 10% to the Navier-Stokes discovery, the author calls it plainly false. The simplest reason: even if a single sequential agent were 100x more efficient than the swarm (which it isn't), it would still take roughly a year to generate the tokens needed for the proof — the proof wouldn't exist without the swarm. He adds the caveat that reachability still had to hold: the problem's probability of a proof existing was likely around 0.00001%, and the swarm's role was finding it under that condition.
Related event: Debate Erupts Over Agent Swarm's Role in Navier-Stokes Proof(12 posts)→
More from coding & agent
- Musk cites unsustainable Grok Bot costs as Hermes offers one-command agent migration — Teknium · 2026-11-04
- Open-source agent Cindy launches: cross-device tasks, files and model sharing — yangyi · 2026-11-04
- Multi-Agent Loop Workflow Curates 1,132 Top Bilibili Videos Into a Website — huangyun_122 · 2026-11-04
- Graphic designer builds NASA-data 3D Solar System in 2 months with Claude Code, no coding — Shevei1342 · 2026-11-04
- How to Run a 5-Person Office With Claude: Assistant, Bookkeeper, PM, Analyst & Office Manager — evielync · 2026-11-04
- Replit's User Ops lead built an AI app to prioritize and route support tickets — amasad · 2026-11-04