Microsoft gets a taste of OpenAI’s tech. A technical preview of a new AI tool called Copilot has been launched by GitHub and OpenAI. Copilot lives inside the Visual Studio Code editor and autocompletes code snippets. Copilot does more than just auto-completing code it’s seen before, according to GitHub. It instead analyzes the code you’ve already written and generates new matching code, including specific functions that were previously called. It works best with Python, JavaScript, TypeScript, Ruby, and Go, according to a blog post from GitHub CEO. Examples on the project’s website include automatically writing the code to import tweets, draw a scatter plot, or grab a Goodreads rating.
This project has been considered to be an evolution of pair programming where two coders will work on the same project to catch each others’ mistakes and speed up the development process. With Copilot, one of those coders is virtual. Copilot is built on a new algorithm called OpenAI Codex, which OpenAI CTO describes as a descendant of GPT-3. This project is the first major result of Microsoft’s $1 billion investment into OpenAI. GPT-3 is OpenAI’s flagship language-generating algorithm. The algorithm can generate text sometimes indistinguishable to human writing. It’s able to connect relationships between letters, words, phrases, and sentences. While GPT-3 generates English, OpenAI Codex generates code. OpenAI plans to release a version of Codex later this summer so developers can build their own apps with the tech. Codex was trained on terabytes of openly available code pulled from GitHub, as well as English language examples. “Due to the pre-release nature of the underlying technology, GitHub Copilot may sometimes produce undesired outputs, including biased, discriminatory, abusive, or offensive outputs,” Copilot’s website says. Right now, Copilot is in a restricted technical preview, but anyone can sign up on the project’s website for a chance to access it.
