OpenAI Codex

About OpenAI Codex

OpenAI Codex is an advanced AI system that translates natural language into code. It is the model that powers GitHub Copilot, a tool launched in partnership with GitHub. Proficient in more than a dozen programming languages, Codex can interpret simple commands in natural language and execute them, making it possible to build a natural language interface to existing applications.

Background and Development

OpenAI Codex is a descendant of GPT-3 and its training data contains both natural language and billions of lines of source code from publicly available sources, including code in public GitHub repositories. It is most capable in Python, but it is also proficient in over a dozen languages including JavaScript, Go, Perl, PHP, Ruby, Swift and TypeScript, and even Shell.

Core Features and Capabilities

OpenAI Codex has much of the natural language understanding of GPT-3, but it produces working code. This means you can issue commands in English to any piece of software with an API. It empowers computers to better understand people’s intent, which can empower everyone to do more with computers.

User Experience

OpenAI Codex is a general-purpose programming model, meaning that it can be applied to essentially any programming task. It has been successfully used for transpilation, explaining code, and refactoring code.

Applications and Use Cases

OpenAI Codex can be used to build a natural language interface to existing applications. It is now inviting businesses and developers to build on top of OpenAI Codex through its API.

Impact and Future Outlook

OpenAI Codex is now available in private beta via the API, and OpenAI is aiming to scale up as quickly as it can safely. During the initial period, OpenAI Codex will be offered for free. OpenAI will continue building on the safety groundwork it laid with GPT-3.