Github Copilot: Microsoft's Advanced Investment in Automatic Coding

Despair or Delight? Developers make their feelings known about an AI that writes code.


Microsoft assistant Github, on June 29, 2021, launched an AI-based coding assistant service for developers. This new service, monikered an "AI pair programmer", is embedded as an extension in Microsoft's Visual Code Studio editor.

OpenAI Codex has a superior understanding of popular coding methods.
OpenAI Codex has a superior understanding of popular coding methods.
Key Facts
  1. 1

    GitHub Copilot is powered by an emerging code generator created by Open AI, Open AI Codex.

  2. 2

    The invite-only technical preview version can only work with a few languages and frameworks.

  3. 3

    There have been feelings of ecstasy and outrage oozing from developers about this subject.


Many programmers have been feeling edgy seeing the potential and progress of Artificial Intelligence in many sectors over the years. Artificial Intelligence is undoubtedly the present and future of automation. However, not everyone is happy about new inventions, innovations or advancements. There is always someone that gets an early bath.

According to an Oxford University study, 47% of current jobs in the USA will be taken over by automation in 2030. This means even programmers stand a chance of being replaced by these ingenious codes they write.

There are divided opinions about AI in the developer populace. No doubt AI has made their jobs easy; this is easily common knowledge.

A faction of the developer populace has earmarked AI as an intervention to help programmers. Another faction is furious, especially with interventions like GitHub Copilot, which can play the role of an assistant programmer, therefore eliminating the need for an assistant developer. All well and good.

"Good job, AI!"

Theoretically, this hardly means AI can pass the stage of being an "assistant", let alone write entire codes by itself. Existent AI-powered apps like DeepCoder by Microsoft and Cambridge University researchers, Bayou by Google and DARPA, Commit Assistant by Ubisoft can generate lines of code. Still, they can't write an entire program yet, nor do they have the potential to. If anything, AI is helping developers, and businesses and relevant organisations cut the cost of software development by making it faster and cheaper.

A 2013 Oxford research estimated software engineering drifting to automation in the next 20 years.

The software scans the context of the code its pilot (the developer) is writing, gives suggestions, and makes corrections. Its mechanism is in many ways similar to the Gboard (Android Keyboard).

OpenAI Codex from OpenAI powers the AI-based coding assistant. GPT-3, a closer alternative, is significantly less capable than OpenAI Codex in code generation because of its public source code concept, what's more?!

OpenAI Codex has a superior understanding of popular coding methods. Pending its release into general availability, the technical preview version could be interested in popular frameworks and languages like Ruby, TypeScript, JavaScript, Python, and Go.

An exciting concern that comes with Copilot's code generation is copyright violation or open source code laundering from repositories without the proper license. This way, developers could also have their details chunked out by an insensitive programmer.

Get similar stories in your inbox weekly, for free

Is this news interesting? Share it with your followers

Latest stories

DevOps and Downed Systems: How to Prepare

Downed systems can cost thousands of dollars in immediate losses and more in reputation damage …

Cloud: AWS Improves the Trigger Functions for Amazon SQS

The improved AWS feature allows users to trigger Lambda functions from an SQS queue.

Google Takes Security up a Notch for CI/CD With ClusterFuzzLite

Google makes fuzzing easier and faster with ClusterFuzzLite

HashiCorp Announces Vault 1.9

Vault 1.9 released into general availability with new features

Azure Container Apps: This Is What You Need to Know

HTTP-based autoscaling and scale to zero capability on a serverless platform