---
type: "raw_signal"
id: "how-third-moment-research-runs-10-000-agents-b5a001"
slug: "how-third-moment-research-runs-10-000-agents-b5a001"
title: "How Third Moment Research runs 10,000 agents for 36+ hours"
description: "OpenAI published a case study describing how Third Moment Research uses OpenAI models, Codex, and Daybreak in a quantitative-research system."
retrieval_nugget: "OpenAI published a case study describing how Third Moment Research uses OpenAI models, Codex, and Daybreak in a quantitative-research system."
observed_at: "2026-10-14"
record_date: "2026-10-14"
date_kind: "observed_at"
why_it_matters: "OpenAI published a case study describing how Third Moment Research uses OpenAI models, Codex, and Daybreak in a quantitative-research system. The company says it runs 10,000 agents concurrently and supports autonomous research sessions lasting 36–48 hours. Agents work with a Dockerized Codex environment, a terabyte of data, documentation, and a research repository. An outer harness reviews unfinis"
novelty: "notable"
verification_level: "source-linked"
signal_type: "research"
source_platform: "openai.com"
topics: ["codex"]
entities: ["OpenAI","Third Moment Research","Codex","GPT-6 Astra","GPT-6.1 Sol","Daybreak"]
related_patterns: ["harness-architecture-outlives-model-choice","goal-scoped-loops-replace-manual-continuation"]
source_url: "https://openai.com/index/third-moment-research"
source_urls: ["https://openai.com/index/third-moment-research"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:how-third-moment-research-runs-10-000-agents-b5a001"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/how-third-moment-research-runs-10-000-agents-b5a001/","markdown":"https://newruntime.com/signals/how-third-moment-research-runs-10-000-agents-b5a001.md","json":"https://newruntime.com/signals/how-third-moment-research-runs-10-000-agents-b5a001.json"}
---

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

## Retrieval answer

OpenAI published a case study describing how Third Moment Research uses OpenAI models, Codex, and Daybreak in a quantitative-research system.

OpenAI published a case study describing how Third Moment Research uses OpenAI models, Codex, and Daybreak in a quantitative-research system. The company says it runs 10,000 agents concurrently and supports autonomous research sessions lasting 36–48 hours. Agents work with a Dockerized Codex environment, a terabyte of data, documentation, and a research repository. An outer harness reviews unfinished work and can retry, terminate, or escalate a job for human review. In one example, Codex identified caching and memory-packing changes that reduced a backtest from approximately three hours to approximately 3–5 minutes. Third Moment also uses Daybreak to test whether agents can escape their research environment and access the wider network. These are claims and examples reported in OpenAI’s account; the source does not provide independent validation of the figures or results.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Codex](https://newruntime.com/topics/codex.md): Explore the codex topic hub.
- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)