OpenAI releases code Agent to usher in the era of automated programming

GateUser-6433627c · 2025-05-19T00:42:26+00:00

OpenAI has released a cloud-based code agent Codex, capable of performing multiple tasks such as writing code, answering questions, fixing bugs, and making review requests, running in a sandbox environment and preloading user code repositories. Codex is powered by the Codex-1 model, specifically optimized for software engineering training, aligning with programmers' styles and preferences in the generated code, and strictly adhering to instructions.

GateUser-6433627c

2025-05-19 00:42:26

Abstract generation in progress

On May 19, OpenAI released a new cloud-based code agent - Codex - on its official website. Codex can automatically perform various tasks for developers, such as writing functional code, answering questions about codebases, fixing bugs, and proposing pull request reviews, with each task running in its own cloud sandbox environment while preloading the user’s codebase. It is reported that Codex is powered by the Codex-1 model, which is a fine-tuned version of OpenAI-o3, specifically optimized for software engineering. Trained through reinforcement learning on real-world coding tasks in various environments, the generated code can align with the programmer’s coding style and pull request preferences, adhering strictly to instructions. ( Jin10 )

AGENT4,04%

View Original

This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.