GitHub Copilot Q&A - 1

Key takeaways from the talk in Q&A format -

What is GitHub Copilot and how does it work?

GitHub Copilot is a suite of tools designed for code completion. It works by analysing the code and comments you type in your IDE and sending that context to GitHub. Copilot then uses OpenAI's language model (in December 2024, it is GPT 4o by default and you can also choose the preview versions of o1-mini & o1-preview if you like) to understand your intent and generate suggestions for code completion. You can then accept, reject, or modify these suggestions.

What context does GitHub Copilot consider when making suggestions?

Copilot considers the entirety of the file you are currently working on, not just the code from your cursor position upwards. It also analyses the content of other open tabs in your IDE, starting with those closest to the current tab. This helps Copilot focus on the most relevant information.

Is it necessary to meticulously manage open tabs for Copilot to work effectively?

Not really. Copilot often automatically picks up the relevant files based on your typical coding workflow. You would only need to specifically open certain files if you're working on a new feature or library that Copilot hasn't encountered before, or if the suggestions aren't meeting your expectations.

How can I write effective prompts for Copilot to get the most out of it?

Prompt crafting is the technique of phrasing comments and code to elicit the best suggestions from Copilot. Here are some tips for effective prompt crafting:

● Describe the goal: Briefly explain what you're trying to build at the top of the file. This gives Copilot valuable context.

● Be flexible: Remember that Copilot is probabilistic, meaning it might provide different suggestions even in the same scenario. Be prepared to rephrase or reframe your prompts if needed.

● Provide examples: This helps Copilot clearly understand your desired outcome.

● Be specific: Explicitly state what you want, including details like data types, variable names, and constraints.

● Use good variable names: Avoid abbreviations or single-letter variable names, as they can confuse both Copilot and your fellow developers.

● Follow best practices: Copilot learns from your coding style, so adhering to best practices will lead to better suggestions.

● Open relevant files: Ensure the files containing relevant code are open for Copilot to access the necessary context.

Can Copilot learn and adapt to my specific coding conventions?

Yes. By showing Copilot examples of code written according to your conventions, it will learn to follow those patterns in its suggestions.