The important thing idea behind Copilot and other programs prefer it, sometimes called code assistants, is to place the knowledge that programmers need right next to the code they’re writing. The tool tracks the code and comments (descriptions or notes written in natural language) within the file that a programmer is working on, in addition to other files that it links to or which have been edited in the identical project, and sends all this text to the big language model behind Copilot as a prompt. (GitHub co-developed Copilot’s model, called Codex, with OpenAI. It’s a large language model fine-tuned on code.) Copilot then predicts what the programmer is attempting to do and suggests code to do it.

This round trip between code and Codex happens multiple times a second, the prompt updating because the programmer types. At any moment, the programmer can accept what Copilot suggests by hitting the tab key, or ignore it and carry on typing. 

The tab button seems to get hit lots. A study of just about one million Copilot users published by GitHub and the consulting firm Keystone Strategy in June—a yr after the tool’s general release—found that programmers accepted on average around 30% of its suggestions, in response to GitHub’s user data. 

“Within the last yr Copilot has suggested—and had okayed by developers—greater than a billion lines of code,” says Dohmke. “On the market, running inside computers, is code generated by a stochastic parrot.”

Copilot has modified the fundamental skills of coding. As with ChatGPT or image makers like Stable Diffusion, the tool’s output is commonly not exactly what’s wanted—but it could possibly be close. “Perhaps it’s correct, perhaps it’s not—nevertheless it’s start,” says Arghavan Moradi Dakhel, a researcher at Polytechnique Montréal in Canada who studies the usage of machine-learning tools in software development. Programming becomes prompting: somewhat than coming up with code from scratch, the work involves tweaking half-formed code and nudging a big language model to supply something more on point. 

But Copilot isn’t in every single place yet. Some firms, including Apple, have asked employees not to make use of it, wary of leaking IP and other private data to competitors. For Justin Gottschlich, CEO of Merly, a startup that uses AI to research code across large software projects, that can at all times be a deal-breaker: “If I’m Google or Intel and my IP is my source code, I’m never going to make use of it,” he says. “Why don’t I just send you all my trade secrets too? It’s just put-your-pants-on-before-you-leave-the-house form of obvious.” Dohmke is aware it is a turn-off for key customers and says that the firm is working on a version of Copilot that companies can run in-house, in order that code isn’t sent to Microsoft’s servers.

Copilot can also be at the middle of a lawsuit filed by programmers unhappy that their code was used to coach the models behind it without their consent. Microsoft has offered indemnity to users of its models who’re wary of potential litigation. However the legal issues will take years to play out within the courts.

Dohmke is bullish, confident that the professionals outweigh the cons: “We’ll adjust to whatever US, UK, or European lawmakers tell us to do,” he says. “But there may be a middle balance here between protecting rights—and protecting privacy—and us as humanity making a step forward.” That’s the form of fighting talk you’d expect from a CEO. But that is latest, uncharted territory. If nothing else, GitHub is leading a brazen experiment that might pave the way in which for a wider range of AI-powered skilled assistants.