Codex ran for up to 32 hours on some of the math problems
FinanceYF5 · x · 2026-07-26
He says the key was to paste the prompt into Codex and let it run autonomously.
Because Codex can work for long stretches, keep full research context, and use local files without human intervention, he advises giving it patience and time: some problems were solved in about 6 hours, while others took around 32 hours.
Related event: GPT-5.6 Sol Powers 32-Hour Long-Range Math Searches(2 posts)→
More from coding & agent
- LLM Zoomcamp demo traces a Pydantic AI agent into DuckDB as 24 tables — Al_Grigor · 2026-07-26
- CREAO schedules a July 30 panel on getting AI from demo to production — thetripathi58 · 2026-07-26
- An AI agent clears Slay the Spire 2 on Ascension 8 and opens its harness and trajectories — bdsqlsz · 2026-07-26
- MemGym benchmarks long-horizon memory for LLM agents across coding and web tasks — dhruv2038 · 2026-07-26
- Developer says $5 a month bought 339.8 hours of agent sandbox compute — aniketmaurya · 2026-07-26
- The loop makes the model attack its own proof until no flaw remains — FinanceYF5 · 2026-07-26