Stay Ahead of the Curve
Latest AI news, expert analysis, bold opinions, and key trends — delivered to your inbox.
OpenAI Launches Codex — A Smarter, Autonomous AI Coding Agent in ChatGPT
2 min read OpenAI has launched Codex, an AI coding agent in ChatGPT powered by the new codex-1 model. It writes, tests, and debugs code in a cloud-based environment, integrates with GitHub, and can handle multiple engineering tasks in real-time. May 16, 2025 16:42
OpenAI has launched a research preview of Codex, its most advanced AI coding agent to date, now integrated into ChatGPT.
Codex is powered by codex-1, a specialized variant of the o3 AI reasoning model fine-tuned for software development. OpenAI says it generates cleaner code, follows instructions more accurately, and automatically tests its output until it works.
🧪 Key Features:
-
Runs in a sandboxed cloud environment
-
Preloads your GitHub repos for contextual coding
-
Handles bug fixes, feature generation, testing, and codebase Q&A
-
Supports parallel tasking without disrupting your current device usage
Tasks can take 1–30 minutes, making Codex a powerful AI collaborator for solo developers and engineering teams alike.
This move positions ChatGPT as more than a code assistant — it’s now becoming a hands-on coding partner that can navigate real repositories and perform end-to-end development tasks.
User Comments (0)
Editor's Choice
AI Agents