Users pitch a Codex '/slow' mode: half speed for double usage, ideal for overnight runs
AIandDesign · x · 2026-09-13
A user has proposed a '/slow' mode for OpenAI's Codex: tasks run at roughly half speed while consuming about half the usage quota, easing server load and potentially making the 20x plan viable. The pitch highlights overnight workflows—queueing a task before bed and letting it run till morning—especially for /goals-style long jobs. The idea drew support from AI design accounts, with some saying even 0.25x speed would be worth it for more usage.
More from coding & agent
- Dev shares 3 personal AI apps he uses daily: a 24/7 voice desktop agent and a GPUI Messages rewrite — johnlindquist · 2026-09-13
- Adopt one tip at a time: fix your current annoyance, then bake it into your instructions — TheMoonMidas · 2026-09-13
- Show ChatGPT the exact sentence you hate instead of vague rewrite requests — TheMoonMidas · 2026-09-13
- Feeding your usage log to ChatGPT to compare Codex orchestrator setups on cost — TheMoonMidas · 2026-09-13
- Codex Plus tip: run Luna for implementation and call Astra as an advisor when stuck — TheMoonMidas · 2026-09-13
- Stale rules in agents.md may cause Codex's Astra to pause constantly — ask it to show you — TheMoonMidas · 2026-09-13