Third Moment Research runs 10,000 agents for 36+ hours using OpenAI models

Third Moment Research utilized GPT-6 Astra, GPT-6.1 Sol, Codex, and Daybreak to operate 10,000 agents continuously for over 36 hours. The system demonstrated sustained focus and performance improvement over time.

Read the full story at OpenAI News ↗

Timeline · 1 report

2026-10-14 07:00 · OpenAI News
How Third Moment Research runs 10,000 agents for 36+ hours

More stories

FBI arrests Saudi OpenAI engineer for allegedly planting recording device — Sky News Technology
Amp integrates OpenAI models to expand AI agent capabilities beyond coding — OpenAI News
Oracle Uses OpenAI Codex to Enable Business User Queries — OpenAI YouTube
OpenAI Introduces ChatGPT Space for Team Collaboration — OpenAI YouTube
AWS enables global cross-Region inference for OpenAI GPT models on Bedrock — AWS Machine Learning Blog
Set up your dot in the ChatGPT mobile app — OpenAI YouTube
How Oracle Uses ChatGPT Work to Transform Recruitment — OpenAI YouTube
AI Just Solved 372 Open Math Problems. The Competitive Implications — Forbes AI

Get the daily brief of stories like this at 6:30 every morning →