AI news
Third Moment says it runs 10,000 research agents for multi-day sessions
An OpenAI customer case says Third Moment Research uses Codex and GPT models to run up to 10,000 agents concurrently on 36–48-hour research sessions. It describes a backtest optimization from about three hours to several minutes and an outer harness that retries or escalates stalled work. These are one company’s reported methods and results, not proof that autonomous research is generally reliable.
Primary source · OpenAI · October 14, 2026
Opens OpenAI in a new tab. Read it there before you rely on the summary above.
Read the original
Free, email only
Unlock the full brief free.
- What to check before you trust this story, written down
- Each verified source, with why it matters and who published it
- A note whenever a source has been withdrawn
- Thirty days of stories to browse, not seven
Continuing subscribes the email on that account to the Rise Productive newsletter, the same as the form below, and unlocks every free tool in this browser. We only receive your email address. Unsubscribe in one click.