# GitHub Copilot GitHub Copilot is an AI-powered code completion and programming assistant developed by GitHub and OpenAI, first announced in June 2021 and made generally available in June 2022. It autocompletes code in multiple IDEs and supports various large language models. GitHub Copilot is a code completion and programming AI-assistant developed by GitHub and OpenAI that assists users of Visual Studio Code, Visual Studio, Neovim, Eclipse, and JetBrains integrated development environments (IDEs) by autocompleting code. Available by subscription to individual developers and businesses, the [generative AI](https://www.wikiprompt.org/wiki/generative-ai) software was first announced by GitHub on 29 June 2021. Users can choose the [large language model](https://www.wikiprompt.org/wiki/large-language-model) used for generation. Copilot represents a significant milestone in the application of [artificial intelligence](https://www.wikiprompt.org/wiki/artificial-intelligence) to software development, building on decades of research in [machine learning](https://www.wikiprompt.org/wiki/machine-learning) and [deep learning](https://www.wikiprompt.org/wiki/deep-learning). Its general availability in June 2022 marked a transition from experimental [neural network](https://www.wikiprompt.org/wiki/neural-network) models to a commercial product used by millions of programmers worldwide. ## History On June 29, 2021, GitHub announced GitHub Copilot for technical preview in the Visual Studio Code development environment. The initial release was limited to a small group of testers, but quickly expanded. GitHub Copilot was released as a plugin on the JetBrains marketplace on October 29, 2021. On October 27, 2021, GitHub released the GitHub Copilot Neovim plugin as a public repository. GitHub announced Copilot's availability for the Visual Studio 2022 IDE on March 29, 2022. On June 21, 2022, GitHub announced that Copilot was out of "technical preview" and available as a subscription-based service for individual developers. This general availability date is widely considered the formal launch of the product to the broader public. GitHub Copilot is the evolution of the "Bing Code Search" plugin for Visual Studio 2013, which was a Microsoft Research project released in February 2014. This plugin integrated with various sources, including MSDN and Stack Overflow, to provide high-quality contextually relevant code snippets in response to natural language queries. The lineage reflects a long-standing interest within Microsoft and GitHub in using [natural language processing](https://www.wikiprompt.org/wiki/natural-language-processing) to assist programmers. ## Features When provided with a programming problem in natural language, Copilot is capable of generating solution code. It is also able to describe input code in English and translate code between programming languages. These capabilities are powered by [transformer](https://www.wikiprompt.org/wiki/transformer) architectures, which excel at understanding context and generating coherent sequences. Copilot enables developers to choose between multiple large language models, including OpenAI's GPT models, [Anthropic](https://www.wikiprompt.org/wiki/anthropic)'s Claude, xAI's Grok, and Google's Gemini. This flexibility allows users to select models optimized for different tasks, such as speed, accuracy, or cost. According to its website, GitHub Copilot includes assistive features for programmers, such as the conversion of code comments to runnable code, and autocomplete for chunks of code, repetitive sections of code, and entire methods and/or functions. GitHub reports that Copilot's autocomplete feature is accurate roughly half of the time; with some Python function header code, for example, Copilot correctly autocompleted the rest of the function body code 43% of the time on the first try and 57% of the time after ten attempts. GitHub states that Copilot's features allow programmers to navigate unfamiliar coding frameworks and languages by reducing the amount of time users spend reading documentation. This is particularly valuable for [learning](https://www.wikiprompt.org/wiki/curriculum-learning) new programming paradigms and for onboarding into large existing codebases. ## Implementation GitHub Copilot was initially powered by the OpenAI Codex, which is a modified, production version of GPT-3. The Codex model is additionally trained on gigabytes of source code in a dozen programming languages. Copilot's OpenAI Codex was trained on a selection of the English language, public GitHub repositories, and other publicly available source code. This includes a filtered dataset of 159 gigabytes of Python code sourced from 54 million public GitHub repositories. OpenAI's GPT-3 is licensed exclusively to Microsoft, GitHub's parent company. The underlying technology relies on [multi-head attention](https://www.wikiprompt.org/wiki/multi-head-attention) mechanisms and [positional encoding](https://www.wikiprompt.org/wiki/positional-encoding) to process code sequences effectively. The model uses [top-p sampling](https://www.wikiprompt.org/wiki/top-p-sampling) and [temperature scaling](https://www.wikiprompt.org/wiki/temperature-scaling) during generation to balance creativity and correctness. In November 2023, Copilot Chat was updated to use OpenAI's GPT-4 model. In 2024, Copilot began allowing users to choose between different large language models, including Gemini and Claude. This shift reflected the broader industry trend toward offering multiple model options rather than a single proprietary system. On 6 February 2025, GitHub announced "agent mode", which is a more autonomous mode of operation for the Copilot. Given a programming task, it attempts to accomplish it by executing commands on a Visual Studio instance on the user's computer. The agent mode can connect to different LLMs, including GPT-4o, o1, o3-mini, Claude 3.5 Sonnet, and Gemini 2.0 Flash. On 17 May 2025, GitHub announced "coding agent", which is a more autonomous mode of operation for the Copilot. The user would assign a task or issue to Copilot, which would then initialize a development environment in the cloud (powered by GitHub Actions) and perform the request. It would compose a draft pull request and pushes commits to the draft as it works. After accomplishing the request, it tags the user for code review. It is essentially an asynchronous version of agent mode. ## Reception Since Copilot's release, there have been concerns with its security and educational impact, as well as licensing controversy surrounding the code it produces. The tool has been both praised for increasing developer productivity and criticized for potential negative effects on learning and code quality. ### Licensing controversy While GitHub CEO Nat Friedman stated in June 2021 that "training ML systems on public data is fair use", a class-action lawsuit filed in November 2022 called this "pure speculation", asserting that "no Court has considered the question of whether 'training ML systems on public data is fair use.'" The lawsuit from Joseph Saveri Law Firm, LLP challenges the legality of Copilot on several claims, ranging from breach of contract with GitHub's users, to breach of privacy under the CCPA for sharing PII. GitHub admits that a small proportion of the tool's output may be copied verbatim, which has led to fears that the output code is insufficiently transformative to be classified as fair use and may infringe on the copyright of the original owner. In June 2022, the Software Freedom Conservancy announced it would end all uses of GitHub in its own projects, accusing Copilot of ignoring code licenses used in training data. In a customer-support message, GitHub stated that "training machine learning models on publicly available data is considered fair use across the machine learning community", but the class action lawsuit called this "false" and additionally noted that "regardless of this concept's level of acceptance in 'the machine learning community,' under Federal law, it is illegal". ### Privacy concerns The Copilot service is cloud-based and requires continuous communication with the GitHub Copilot servers. This opaque architecture has fueled concerns over telemetry and data mining of individual keystrokes. Unlike local code completion tools, Copilot sends code snippets and context to remote servers, raising questions about data security for proprietary codebases. In late 2022 GitHub Copilot has been accused of emitting Quake game source code, with no author attribution or license. This incident highlighted the risk of models reproducing training data verbatim, a known challenge in [deep learning](https://www.wikiprompt.org/wiki/deep-learning) systems. ## Impact on Software Development The release of GitHub Copilot accelerated the adoption of AI-assisted development tools across the industry. It demonstrated practical applications of [large language models](https://www.wikiprompt.org/wiki/large-language-model) beyond text generation, influencing subsequent products from companies like [Google DeepMind](https://www.wikiprompt.org/wiki/google-deepmind) and [OpenAI](https://www.wikiprompt.org/wiki/openai). Copilot's success also spurred research into [model pruning](https://www.wikiprompt.org/wiki/model-pruning) and efficiency improvements, as running these models at scale requires significant computational resources. Cloud providers like [Amazon Web Services](https://www.wikiprompt.org/wiki/amazon-web-services), [Azure](https://www.wikiprompt.org/wiki/azure), and [Google Cloud](https://www.wikiprompt.org/wiki/google-cloud) have developed specialized hardware, such as [AWS Trainium](https://www.wikiprompt.org/wiki/aws-trainium), to support such workloads. The tool has also influenced educational approaches in computer science. Some educators worry that students may become overly reliant on AI assistance, while others see it as an opportunity to focus on higher-level design and architecture skills. Institutions like [MIT CSAIL](https://www.wikiprompt.org/wiki/mit-csail) and [Stanford AI Lab](https://www.wikiprompt.org/wiki/stanford-ai-lab) have studied the implications of AI pair programming on learning outcomes. ## Future Directions As of 2025, GitHub continues to evolve Copilot with more autonomous capabilities, including agent mode and coding agents that can complete entire tasks with minimal human intervention. These developments point toward a future where AI systems handle routine coding tasks, allowing human developers to focus on complex problem-solving and system design. The integration of multiple LLM providers reflects a broader industry shift toward model-agnostic platforms. This approach allows users to benefit from rapid advances in [AI](https://www.wikiprompt.org/wiki/artificial-intelligence) without being locked into a single vendor's model. ## See Also - [OpenAI](https://www.wikiprompt.org/wiki/openai) - [Generative AI](https://www.wikiprompt.org/wiki/generative-ai) - [Large Language Models](https://www.wikiprompt.org/wiki/large-language-model) - [Transformer Architecture](https://www.wikiprompt.org/wiki/transformer) - [Microsoft](https://www.wikiprompt.org/wiki/microsoft) - [Azure](https://www.wikiprompt.org/wiki/azure) - [Anthropic](https://www.wikiprompt.org/wiki/anthropic) - [Google DeepMind](https://www.wikiprompt.org/wiki/google-deepmind) ## References Source facts provided by Wikipedia under CC BY-SA license. ## External Links Official website --- Source: https://www.wikiprompt.org/wiki/github-copilot-ga License: CC BY-SA 4.0 (https://creativecommons.org/licenses/by-sa/4.0/) Last updated: 2026-09-12T16:24:19.398095+00:00