GitHub Copilot

GitHub Copilot is supposed to suggest and complete code independently as an assistant. Currently, the GitHub AI is still in the testing phase and is prone to errors. As time goes on, however, it should work much more effectively.

To understand what exactly the GitHub Copilot is and what it is supposed to do, it is important to first look at GitHub. GitHub is a collaborative version control system whose US publisher has been part of Microsoft since 2018. GitHub is designed to allow large teams to work on code together and independently. All versions are stored and changes can be merged as desired.

Since 2021, the company now offers GitHub Copilot for some users. The AI tool is a smart assistant designed to help developers create code. Initially, this works via auto-completion. When the user starts typing in code, GitHub Copilot makes several suggestions to the user on how that code might look complete. Copilot obtains its information from publicly available code, such as different repositories. GitHub AI goes much further, recognizing numerous Internet programming languages such as Go, Java, JavaScript, Python, Ruby, and TypeScript. The artificial intelligence gets smarter and smarter as time goes on and then provides better suggestions.

Conversely, this also means that GitHub Copilot is currently still very expandable. The company itself also points out that the suggested code is not yet perfect. In addition, the hit rate of the suggestions is very low so far. Users must therefore assume that the code is not yet executable and that some of the suggestions are even unusable. However, the copilot in Git already offers the first useful hints or truly usable suggestions.

The basis for GitHub Copilot is provided by the language production system GPT-3. This was published in 2020 by OpenAI and uses deep-learning strategies to complete human texts or to compose its own texts. The AI uses various algorithms for this, collects huge amounts of data and creates new content from it, which should hardly differ from the texts of human authors. The same applies here: The more the AI is “fed”, the better its results will be. Attempts were already made with GPT-3 to create code on the basis of learned structures. Microsoft then invested massively in OpenAI and GPT-3, so that the knowledge gained can be used for GitHub Copilot.

Currently, GitHub Copilot is not yet freely available. Only a group of selected testers have the opportunity to test the AI at the moment, make suggestions, and improve the tool that way. The goal is to sooner or later turn GitHub Copilot into a commercial program used by developers for their daily work on new software. However, it is not yet known when the AI will be ready. During the learning and testing phase, those interested can only get a first glimpse. Visual Studio Code, Neovim, and JetBrains IDEs such as PyCharm and IntelliJ IDEA are currently supported.

While the initial reports are promising, GitHub Copilot still seems to be far from market-ready. The overall hit rate is not yet particularly high and the quality of the suggestions is also clearly expandable. For the most part, the code is not yet usable and leads to errors in many cases. The quality of a future commercial release will depend heavily on how well the AI learns and the quality of the source code provided to it. Errors in the source material are currently still taken over by GitHub Copilot just as unsuspectingly as unclean syntax. After the learning phase, the results should also get better.

In addition to the aforementioned problems with inappropriate suggestions or expandable syntax, there are also discussions about the basic error-proneness of the codes that currently arise with GitHub Copilot or could arise in the future. Since the basis through which the AI is supposed to learn is often faulty or at least untested, the end result is also too often uncertain. Although it is pointed out that all input provided by the AI is to be verified, it is at least questionable whether this can actually help daily work in the long run. In previous tests, the code from GitHub Copilot often performed poorly.

Some developers also fear that using Copilot in Git could potentially lead to copyright infringement should the AI simply take over entire blocks of code. While there are different fair use rules; whether an AI’s learning successes fall under them is at least debatable. This is all the more true if GitHub Copilot could also be used for commercial purposes in the future. The company itself explains that right now only a few source codes are taken over completely or partially unchanged. With greater learning successes, this figure is expected to drop even further.

Currently, GitHub Copilot is still a gimmick whose added value is very manageable. However, once the AI has learned more, it could take a lot of work off developers’ shoulders. On the one hand, it could show alternative solutions and provide suitable syntax examples without a tedious search in different documentation. On the other hand, it should add individual code blocks independently at some point and therefore contribute time-consuming lines. Although this would make the work easier, a certain basic knowledge will still be necessary for development. It will probably be a long time before an AI writes code independently.

GitHub Copilot is an obvious idea that could someday be a natural part of working with source code. The idea of an attentive assistant that takes over smaller tasks and points out possible errors is quite promising. Currently, however, the AI is still very far away from this role. The current test phase is only a first step in this direction and the error rate is therefore high, as expected. It is not yet possible to reliably say when GitHub Copilot will actually be available to all interested parties. However, a first step has been made with the test phase.