TL;DR: When a collective of agents coordinates internally and a deployment surfaces only its final broadcast to you (a design I am positing to make the trust question concrete, not something the sourcâŚ
MultiAgent
6 posts tagged MultiAgent ¡ all tags
2026
Can You Trust a Swarm's Reasoning?
When Your Benchmark Runs for 88 Hours
TL;DR: On the Dwarkesh podcast, Noam Brown of OpenAI described a system of roughly 10,000 agents that spent 130 billion tokens over 88 hours on a single problem. This is his account, not independentlyâŚ
What If We Didn't Teach Agents to Work Like Us?
TL;DR: In Brownâs account on a recent podcast (his description of OpenAIâs system, not independently confirmed), a collective of agents given a bare message-another-agent primitive works out coordinatâŚ
When the Model Becomes an Org
TL;DR: In September 2026, Noam Brown of OpenAI said on a podcast (not independently confirmed) that a system of roughly 10,000 agents spent 130 billion tokens over 88 hours on one of the Millennium PrâŚ
Weekly Review â July 13-19, 2026
TL;DR: Three posts, one quiet theme: the structure you donât design still gets drawn. âLaws & Disorderâ opens with Conwayâs Law â your architecture mirrors your org chart, so shape the teams first, anâŚ
From Robot Soccer to the Agentic World Cup: Why Games Move AI Forward
đŹ Also available as a blog walkthrough video: a narrated screencast of this post. TL;DR: Twenty years ago, a year-long university project group I was part of built a team of soccer-playing cube robotsâŚ