So now I make a bot to upload repositories of intentionally buggy code so that when people blindly use this autocomplete my hacking becomes easier!
GitHub Copilot
41–50 of 1001 posts
Re: GitHub Copilot
#42and away we go to singularity.
Re: GitHub Copilot
#43Earlier quoted context omitted.
Don't most IDEs handle this already?
There are no tools that can format my code with my coding style AFAIK. There are multiple tool that can format my code with their coding style though, which I don't care about.
Most? All? Allow you to edit the config to get it to your coding style but it would be cool to infer it from files you’ve already written.
Re: GitHub Copilot
#44If you are interested to read[1] more about it.
[1] https://docs.github.com/en/early-access/github/copilot/resea...
Re: GitHub Copilot
#45How does this compare to TabNine or Kite?
Re: GitHub Copilot
#46GitHub says you don't need to credit GitHub for any of the code suggestions, but since it's trained on public sources of code, anyone have a clue on potential licensing pitfalls?
(not a lawyer) Copyright issues tend to involve the question of how transformative a work is. This means the code coming out the other end is probably fine. I don't know about the training side, though. Are there license issues in using copyrighted training data without any form of licensing? Typically ML researchers have a pretty free-for-all attitude towards 'if I can find data, I can train models on it.'
Re: GitHub Copilot
#47I've been using the alpha for the past 2 weeks, and I'm blown away. Copilot guesses the exact code I want to write about one in ten times, and the rest of the time it suggests something rather good, or completely off. But when it guesses right, it feels like it's reading my mind. It's really like pair programming, even though I'm coding alone. I have a better understanding of my own code, and I tend to give better na…
> and the rest of the time it suggests something rather good, or completely off
In what, proportion roughly?
Re: GitHub Copilot
#48So if it was trained using "source code from publicly available sources, including code in public repositories on GitHub." was it also GPLv2? So everything generated also GPLv2?
No, a model trained on text covered by a license is not itself covered by the license, unless it explicitly copies the text (you cannot copyright a "style").
Re: GitHub Copilot
#49Earlier quoted context omitted.
Yeah, running locally would be my preference. I get "Antitrust (2001)" vibes from this, but that's the tinfoil hat side of me.
Like this? https://visualstudio.microsoft.com/services/intellicode/ I bet it's the same people, trying to push their crap into all sorts of successful products.
As far as I know that also runs remotely.
Edit: looks like I remembered incorrectly: https://docs.microsoft.com/en-us/visualstudio/intellicode/ov...
> No user-defined code is sent to Microsoft