OpenAI News·· 2 d ago
How Third Moment Research runs 10,000 agents for 36+ hours
How Third Moment Research runs 10,000 agents for 36+ hours
AI summary
With GPT-6 Astra and GPT-6.1 Sol, Codex, and Daybreak for cybersecurity, this AI lab builds agents that focus for days and improve with use.
Selection record
Threshold 60Official, first-handFirst 22Second 22
Not admittedSum of both 44 < twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：标题及摘要明确涉及AI智能体运行
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: OpenAI News · openai.com