acm-header
Sign In

Communications of the ACM

ACM Careers

OpenAI's Codex Turns Written Language Into Computer Code


View as: Print Mobile App Share:
OpenAI Codex logo

Credit: OpenAI

OpenAI is releasing an improved version of its Codex AI model that can read written instructions in conversational language and transform it into working computer code.

The model is the latest example of progress in natural language processing, and points toward a future in which coders will be able to offload some of their work to AIs, and where ordinary people may be able to code without programmer training.

Codex is a descendant of OpenAI's text-generating model GPT-3. While GPT-3 was trained on a huge quantity of language data taken from the Internet, Codex was trained on both language and billions of lines of publicly available computer code.

As a result, users can issue commands in written English, and Codex will produce computer code capable of carrying out those instructions, essentially making it an English-to-Python (or any of more than a dozen programming languages in Codex's training data) computer code translator.

From Axios
View Full Article


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account