3 comments

[ 0.76 ms ] story [ 16.8 ms ] thread
I’ve been using it consistently for several weeks now after initially assuming I never would. While I am blown away by how accurate it often is at knowing exactly what I’m thinking, I personally find for languages and frameworks I know we’ll I get at most a 10% productivity boost. When I’m dipping my toe into a new language or framework though it probably goes up to 50%. Still I am in awe by how much it seems to understand and if nothing else I like having my jaw drop every once in a while by it’s understanding
Andrej is learning Rust. I’ve been holding out. Sounds like it’s almost time…
All you need you need to know about Copilot (taken from “Privacy – Copilot for Individuals” at https://github.com/features/copilot):

—————————

What data does Copilot for Individuals collect? GitHub Copilot relies on file content and additional data to work. It collects data to provide the service, some of which is then retained for further analysis and product improvements. GitHub Copilot collects the following data for individual users:

User Engagement Data When you use GitHub Copilot it will collect usage information about events generated when interacting with the IDE or editor. These events include user edit actions like completions accepted and dismissed, and error and general usage data to identify metrics like latency and features engagement. This information may include personal data, such as pseudonymous identifiers.

Code Snippets Data Depending on your preferred telemetry settings, GitHub Copilot may also collect and retain the following, collectively referred to as “code snippets”: source code that you are editing, related files and other files open in the same IDE or editor, URLs of repositories and files path.

————————