Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GitHub Copilot

copilot.github.com

Post reply on HN
Print view View original

651–660 of 1001 posts

Re: GitHub Copilot

#651

Post by kyawzazaw »

onlyrealcuzzo wrote: post #319
the_arun wrote: post #302

Earlier quoted context omitted.

In addition, I would like to see GitHub reviewing my code & giving me suggestions on how I could improve. That will be more educative & a tool to ensure consistency across code.

I'm surprised this doesn't exist. Google, FB, and Apple (and I imagine Microsoft) have a lot of this stuff built in that is light-years better than any open source solution I'm aware of. Given that MS owns GitHub and how valuable this is - I imagine it will be coming soon.

SonarQube and IntelliJ does it in some way for me.

Re: GitHub Copilot

#653

Post by delaaxe »

richardanaya wrote: post #635
iandanforth wrote: post #619

Earlier quoted context omitted.

What is the licensing for code generated in this way? GPT-3 has memorized hundreds of texts verbatim and can be prompted to regurgitate that text. Has this model only been trained on code that doesn't require attribution as part of the license?

You're using the word "memorized" in a very loose way.

His point still holds, GPT-3 can output large chunks of licensed code, verbatim

Re: GitHub Copilot

#654

Post by hashingroll »

> Convert comments to code. Write a comment describing the logic you want, and let GitHub Copilot assemble the code for you.

I don't know if Copilot does it already but I would love if there was a tool that does exactly the opposite — convert code to comments and documentation.

Re: GitHub Copilot

#656

Post by antpls »

Another way to look at it : if an "AI" can predict what you would code next, it means your program is probably not that innovative, and was already created somewhere.

Re: GitHub Copilot

#657

Post by 6gvONxR4sf7o »

patrickthebold wrote: post #483
natfriedman wrote: post #345

Earlier quoted context omitted.

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…

What does "public" mean? Do you mean "public domain", or something else?

Unfortunately, in ML "public data" typically means available to the public. Even if it's pirated, like much of the data available in the Books3 dataset, which is a big part of some other very prominent datasets.

Re: GitHub Copilot

#658

Post by stakkur »

The goal, of course, should be to train your AI partner to eventually do all the work, while you sip a beer at the pub and monitor Slack (where an AI version of you is maintaining conversations).

Re: GitHub Copilot

#659

Post by antoniuschan99 »

There’s a lot of products that try to do away with programming in general such as no-code.

However, the elephant in the room is definitely a tool that can auto fix bugs - the type of bug that is usually given to a junior developer because the team doesn’t want them building features yet.

Re: GitHub Copilot

#660

Post by megablast »

handrous wrote: post #387
gentleman11 wrote: post #374

Earlier quoted context omitted.

It could start to replace us in 20 years. Or reduce. It is exciting for now

Until it automatically knows when and how it's wrong, you'll still need a human to figure that out, and that human will need to actually know how to program, without the overgrown auto-complete. May or may not reduce the demand for programmers, though. We'll see.

Thanks captain obvious.
Post reply on HN