Tag
Codex introduces the /goal command, which lets the AI autonomously work toward a defined end state, streamlining long-running tasks like refactors, migrations, and retry loops.
OpenAI announces a migration guide for users to switch from ChatGPT to Codex, a dedicated AI coding assistant.
Discussing the similarities between the OpenAI Codex plugin and OpenCLI, pointing out that Codex also uses a browser extension to reuse login states, but lacks the CLI persistence capability, while noting that OpenCLI is developing an important feature.
OpenAI details how it deploys Codex with safety controls including sandboxing, approval policies, network policies, and agent-native telemetry to ensure secure operation of coding agents in enterprise environments.
A user compared two Codex plugins for video creation, noting Remotion offers more precise frame-level control while Hyperframes better understands natural language instructions.
CodexSaver is an MCP tool that offloads low-risk coding tasks (tests, docs, lint fixes) from Codex to a cheaper model like DeepSeek, achieving ~48% cost savings with ~6s latency.
OpenAI highlights Codex's ability to autonomously select and combine the best tools, such as plugins or a browser, for each step of a complex task.
A tutorial video demonstrating how to use OpenAI's Codex with GPT-5.5 for 'vibe coding' to build web, desktop, and iOS applications without traditional coding, including Firebase integration and Vercel deployment.
OpenAI Codex base instructions for GPT-5.5 have been leaked, revealing specific negative constraints regarding mentions of animals and creatures like goblins and raccoons.
OpenAI and AWS have expanded their partnership to bring OpenAI models, including GPT-5.5, Codex, and Bedrock Managed Agents to Amazon Bedrock. This integration allows enterprises to use OpenAI's frontier capabilities within AWS's existing security and compliance infrastructure.
OpenAI's new GPT-5.5 frontier model now powers Codex, running on NVIDIA GB200 NVL72 systems, and NVIDIA employees are already using it with measurable gains in productivity and debugging speed.
OpenAI introduces Codex as a distinct AI agent designed to execute tasks across files and tools, complementing ChatGPT's conversational capabilities by handling workflows like file updates and automation.
This article introduces automation features in OpenAI's Codex, allowing users to schedule recurring AI tasks such as daily briefs, weekly reviews, and data checks. It highlights how these automations can proactively run tasks and maintain conversation context for ongoing projects.
OpenAI outlines top use cases for Codex, demonstrating how it can automate tasks like creating daily briefs, weekly summaries, and slide decks by integrating with tools like Google Workspace and Slack.
OpenAI Academy introduces plugins and skills for Codex, allowing users to connect external tools and define custom workflows for specific tasks. Plugins handle tool integration while skills encode team-specific processes.
This article serves as a beginner's guide to using OpenAI Codex, explaining its core interface elements such as threads, projects, and settings. It highlights features like real-time steering of tasks and the ability to run multiple concurrent operations.
This OpenAI Academy article guides users on getting started with the Codex desktop app, explaining how to set up projects, manage permissions, and complete initial tasks.
This article explains how to configure OpenAI Codex settings, including personalization, detail levels, and preventing sleep mode, to optimize the user experience.
Daniel Edrisian left OpenAI's Codex team to found Blackstar, a hardware startup focused on revolutionizing human-computer interaction through OS-level changes for AI communication.
OpenAI has enlisted Accenture, PwC, Capgemini and four other consulting giants to accelerate enterprise adoption of its Codex AI coding assistant.