OpenAI Develops English to Code Translation System

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.

The model works sort of like a machine translation (MT) program that can translate between English and computer languages like Python and JavaScript. According to the company, Codex is most proficient in Python, but also has proficiency in more than a dozen other coding languages. In addition to allowing individuals to type in English and have the commands translated into code, individuals can also use their computers microphone to say commands aloud and have Codex translate that into code — videos on OpenAI’s website show users creating simple computer games with the system and also editing text on a word processing system using only voice commands. 

“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.”

Andrew Warner
Andrew Warner is a writer from Sacramento. He received his B.A. in linguistics and English from UCLA and is currently working toward an M.A. in applied linguistics at Columbia University. His writing has been published in Language Magazine, Sactown Magazine, and The Takeout.

Related Articles

Weekly Digest

Subscribe to stay updated