On Aug. 10, OpenAI released an improved version of its Codex AI model to developers — Codex AI can translate commands written in natural, conversational language into computer code. Codex AI is descended from the company’s GPT-3 model, which was launched last summer, and was trained on data from both natural human language and billions of lines of publicly available source code.
“We’ve created an improved version of OpenAI Codex, our AI system that translates natural language to code, and we are releasing it through our API in private beta starting today,” OpenAI wrote in an Aug. 10 blog post. “Proficient in more than a dozen programming languages, Codex can now interpret simple commands in natural language … making it possible to build a natural language interface to existing applications.”
Currently, Codex is available in beta through OpenAI’s API, though the company is planning to scale up its operations as soon as it possibly can. Developers and academic researchers can both sign up to access Codex through the company’s access applications, though there is currently a waitlist.
“OpenAI Codex is a general-purpose programming model, meaning that it can be applied to essentially any programming task (though results may vary),” the company wrote in its blog post. “We’ve successfully used it for transpilation, explaining code, and refactoring code. But we know we’ve only scratched the surface of what can be done.”