RESEARCH · RESEARCH · #1971
Third Moment Research runs 10,000 agents for 36+ hours using GPT-6 models
Third Moment Research says it runs 10,000 agents for more than 36 hours using GPT-6 Astra, GPT-6.1 Sol, Codex, and Daybreak to build cybersecurity-focused agents that maintain focus for days and improve with continued use.
KEY POINTS
- Third Moment Research says it runs 10,000 agents for more than 36 hours using GPT-6 Astra, GPT-6.1 Sol, Codex, and Daybreak to build cybersecurity-focused agents that maintain focus for days and improve with continued use.
- If accurate, this demonstrates scale and sustained operation of long-lived multi-agent systems using advanced GPT-6–family models, with implications for automated cybersecurity and agent research.
- How Third Moment Research runs 10,000 agents for 36+ hours
WHY IT MATTERS
If accurate, this demonstrates scale and sustained operation of long-lived multi-agent systems using advanced GPT-6–family models, with implications for automated cybersecurity and agent research.