PulseAugur
EN
LIVE 23:57:42

OpenAI's Codex shifts to long-running work with new persistent features

OpenAI has detailed new practices for its Codex coding tool, shifting its focus from single prompts to supporting long-running, persistent work. These updates include the concept of a "durable thread" for accumulating context over extended tasks, a "memory" system to store project information, and enhanced "steering" capabilities allowing users to guide Codex during its operation. Additionally, a "side panel" feature will display and allow review of work artifacts as they are generated, moving output into the active workflow. AI

IMPACT This shift in Codex's functionality could streamline complex coding tasks and improve developer workflows by enabling persistent context and user guidance.

RANK_REASON The item describes product changes and new working practices for an existing AI coding tool, not a new model release or fundamental research.

Read on dev.to — MCP tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

OpenAI's Codex shifts to long-running work with new persistent features

COVERAGE [1]

  1. dev.to — MCP tag TIER_1 English(EN) · Alex Merced ·

    AI Weekly: Codex Goes Long, MCP Goes Stateless

    <p>The past seven days pushed three quiet shifts forward. AI coding moved from single prompts toward long-running work that keeps its own context. The plumbing under AI agents got a major upgrade as the Model Context Protocol locked in a stateless core. And the hardware story spr…