New Reasoning Mode in Codex on GitHub
A new reasoning mode called Persistent has been spotted in the Codex repository on GitHub, allowing agents to create tasks autonomously. OpenAI has confirmed testing of this feature, but no launch plans are currently available.
New Reasoning Mode in Codex on GitHub
A new possible reasoning mode called Persistent has been noticed in the Codex repository on GitHub. Its description is quite straightforward:
"Continue working until you are sent to sleep."
According to the code, the agent will also be able to create subsequent tasks for itself and continue working without constant commands from the user.
OpenAI has confirmed that it is testing this feature. Unfortunately, there are currently no plans for a quick launch.
Why it matters
AnalysisThis new feature could significantly enhance the efficiency of autonomous agents, allowing them to manage their tasks independently. This opens up new possibilities for automation in various fields.
Discuss in community
Share your questions and insights with developers
Related in Ecosystem
Practical guides, core terminology, and agent skills
Codex: Basic Onboarding, Setup, and First Tasks
There are three ways to work with AI when writing code - and Codex covers the most ambitious of them.
Codex Skills for Beginners: Automating AI Agent Workflows
A comprehensive hands-on guide to building and executing Codex Skills: SKILL.md anatomy, explicit vs. auto-triggering, skills vs. scripts vs. tools, Skills API, and safety boundaries.
Four Resume Tips from OpenAI’s Head of Applied AI Development
Wulfie Bain, OpenAI’s head of applied AI development, shared four resume rules: keep it short, remove irrelevant details, highlight outcomes, and lead with the strongest achievements.
Sam Altman Changes X Account Name to Ram Altman
Sam Altman, CEO of OpenAI, changed the display name of his X account to Ram Altman.