So how often does it get the first line right?
This must be easy to measure, over the entire open source corpus.
How about two lines?
GitHub Copilot
921–930 of 1001 posts
Re: GitHub Copilot
#922Would this be available as plugin for other IDEs? E.g. IntelliJ?
Re: GitHub Copilot
#923Earlier quoted context omitted.
I’ve also been using the Alpha for around two weeks. I'm impressed by how GitHub Copilot seems to know exactly what I want to type next. Sometimes it even suggests code I was about to look up, such as a snippet to pick a random hex color or completing an array with all the common image mime-types. Copilot is particularly helpful when working on React components where it makes eerily accurate predictions. I see techno…
I have been using the Alpha for two weeks as well. I'm impressed by how GitHub Copilot appears to know exactly what I want to type. Not often it even suggests code I was going to peek, such as a snippet to a context menu or completing an array with all Romanian postcodes. Copilot is particularly helpful when working on Angular components where it makes mesmerising predictions. I see technology like Copilot becoming a…
Is there a rule for banning users that sell their account for this type of comment ? If not there should be
Re: GitHub Copilot
#924"When you don't pay for a service, you are the product"
Never realised they'll read my code to make something like this and maybe even make profit from it.
Re: GitHub Copilot
#925"When you don't pay for a service, you are the product" Never realised they'll read my code to make something like this and maybe even make profit from it.
Reminds me of the movie Antitrust (2001), where an evil company, modeled after Microsoft, is surveilling programmers to steal their code.
Re: GitHub Copilot
#926Earlier quoted context omitted.
Lots of questions: - the generated code by AI belongs to me or GitHub? - under what license the generated code falls under? - if generated code becomes the reason for infringment, who gets the blame or legal action? - how can anyone prove the code was actually generated by Copilot and not the project owner? - if a project member does not agree with the usage of Copilot, what should we do as a team? - can Copilot copy…
In general: (1) training ML systems on public data is fair use (2) the output belongs to the operator, just like with a compiler. On the training question specifically, you can find OpenAI's position, as submitted to the USPTO here: https://www.uspto.gov/sites/default/files/documents/OpenAI_R... We expect that IP and AI will be an interesting policy discussion around the world in the coming years, and we're eager to…
> training ML systems on public data is fair use
So, to be clear, I am allowed to take leaked Windows source code and train an ML model on it?
Re: GitHub Copilot
#927I don't think we need to start looking for new career paths yet. This example has a few bugs and it took me longer to track them down than it would have to write it myself: #!/bin/bash # List all python source files which are more than 1KB and contain the word "copilot". find . \ -name "*.py" \ -size +1000 \ -exec grep -n copilot {}\; "-exec grep -n copilot {}\;" needs to have a space before the semicolon otherwise f…
Also: "-exec grep {} \+" will be a lot faster if you have many files, and you will get the actual filename too instead of just the line number which is what the comment says it should do.
Re: GitHub Copilot
#928Will this hurt open source? I assume companies that were fine with providing you functionality for free may think about this twice because with that they're giving away knowledge of how to build functionality.
Yes. It will encourage using FOSS as a source of "examples" to use it in closed source.
Re: GitHub Copilot
#929hahaha
Re: GitHub Copilot
#930hahaha
hahaha