Skip to main content
ModelsResearchSecurity

How Third Moment Research runs 10,000 agents for 36+ hours

Source: OpenAI (opens in a new tab)

Intel Summary

OpenAI highlights how AI lab Third Moment Research deploys fleets of 10,000 autonomous agents running for over 36 hours. The organization utilizes models and tools including GPT-6 Astra, GPT-6.1 Sol, Codex, and Daybreak to build cybersecurity agents designed to operate over multi-day horizons.

Why It Matters

Demonstrates practical multi-agent execution scaling to tens of thousands of concurrent autonomous units over sustained multi-day operational windows. For cybersecurity and enterprise automation builders, long-running agent persistence represents a key step toward continuous defensive and research operations without frequent human intervention.

Organizations & Entities

Topics