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

Summary

Third Moment Research is building a self-improving AI system that uses OpenAI models, including GPT-6 Astra, GPT-6.1 Sol and Codex, to run 10,000 agents at once on investigations lasting 36-48 hours. The company also uses Daybreak to test the security of the environments where its agents work. In one quantitative finance case, Codex cut a trading strategy backtest from approximately 3 hours to approximately 3 to 5 minutes.

Related items

• InfoOpenAI’s Sachin Katti to leave infrastructure role, stay on as advisorSame vendor · CNBC Technology
• InfoOpenAI claims an ex-employee took its product plans and presented them to AppleSame vendor · The Verge (AI)
• InfoToilet paper and secret recorders: What we know about the arrest of the Saudi OpenAI engineerSame vendor · BBC Technology
• InfoAmp puts AI agents to work beyond code with OpenAI modelsSame vendor · OpenAI Blog
• InfoResearchers Used a Public OpenAI Model to Build a $250,000 Chrome Full-Chain Exploit in Six DaysSame vendor · The Hacker News