OpenAI tests Codex's Continuous Mode: Task Completed But Follow-up Still Possible

Dynamic Beating AI News: OpenAI is testing Codex's Persistent mode, which allows the AI to continue running after completing a task. Normally, a regular agent would stop after completing a task, but this mode enables Codex to finish the current task and then proceed to check and handle subsequent items. The relevant code has already appeared in Codex's public repository, but OpenAI stated that there are no immediate plans for deployment.