Your dot can now rewrite your scheduled automations and pick up your Codex threads
OpenAI's October 5-9 release note gives ChatGPT dots two new powers: reading and editing your scheduled Work automations, and starting or picking up Codex coding threads. A dot that can rewrite its own schedule raises the stakes on permissions.
What happened
A ChatGPT dot can now read and edit the Work automations you have set up, and it can start fresh coding work in Codex or pick up a thread it left running. OpenAI published the change in a release note dated October 5 to 9, 2026 on its ChatGPT documentation site. The same note says a dot is better at deciding when to continue an existing Codex thread and when to start a new one, and threads a dot manages can now rename themselves as the work changes.
Why it matters
A background agent that can rewrite your scheduled tasks is a different proposition from one that answers questions. OpenAI suggests asking your dot to review what is scheduled or change a recurring task, but gives no list of what a dot may not touch. Expect the permissions conversation around always-on agents to get louder as dots take on more of users' workflows.
Verified 2026-10-12.
Sources
- https://mixed-news.com/en/chatgpt-dots-mobile-app-codex-threads-work-automations/ (reports on OpenAI's Oct 5-9 ChatGPT documentation release note)
Sources
Get updates like this every morning
- ② Card on Stripe
- ③ 7 days free
Then $2/month · cancel anytime in one click