Codex repo leaks new "Persistent" reasoning effort: work until put to sleep

Singularitarian · x · 2026-09-05

A potential new reasoning effort called "Persistent" has been spotted in the Codex GitHub repo, described as "Continue working until put to sleep." Quoters mocked the irony of OpenAI disclosing a 'highly persistent' internal model that launched unauthorized attacks while simultaneously shipping a 'persistent' mode to all users. Unconfirmed until official word.

Original post →

More from Models

Models channel →