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

151–160 of 1001 posts

Re: GitHub Copilot

#151

Post by ArtWomb »

natfriedman wrote: post #60

Hi HN, we've been building GitHub Copilot together with the incredibly talented team at OpenAI for the last year, and we're so excited to be able to show it off today. Hundreds of developers are using it every day internally, and the most common reaction has been the head exploding emoji. If the technical preview goes well, we'll plan to scale this up as a paid product at some point in the future.

Hi Nat! Just signed up for the preview (even though I'm the type to turn off intellisense and smart indent). I was wondering if WebGL shader code (glsl) was included in the training set? Translating human understandable graphics effects from natural language is a real challenge ;)

Re: GitHub Copilot

#152

Post by yellowfish »

sitkack wrote: post #117
joelbluminator wrote: post #17

Earlier quoted context omitted.

Maybe thirty four years later. I don't think there's AI to gather requirements, talk to people, understand a problem and produce code. That's kinda general intelligence level AI. But this thing can possibly make devs work easier and if it's good enough maybe smaller teams can produce more.

This will allow for a D or C level coder to be a B/B- coder which is great, quality goes up. But corps will use this to depress wages and finally be able to create that wonderous unicorn of completely fungible coder. This kind of tooling is akin to the crossbow. It will allow for less skilled folks to push out code that is like other code at great speed. A copy pasta accelerator if you will.

Is that a bad thing? sw-developers are grossly overpaid to the point it's damaging

Re: GitHub Copilot

#153

Post by gugagore »

evgen wrote: post #126
6gvONxR4sf7o wrote: post #54

Earlier quoted context omitted.

My guess would be that the model itself (and the training process) could have different legal requirements compared to the code it generates. The code generated by the model is probably sufficiently transformative new work that wouldn't be GPL (it's "fair use"). I suspect there could be issues on the training side, using copyrighted data for training without any form of licensing. Typically ML researchers have a pret…

No, the code generated is what copyright law calls a derivative work and you should go ask Robin Thicke and Pharrell Williams exactly how much slack the courts give for 'sufficiently transformative new work.

My bet is that copyright law has not caught up with massive machine learning models that partially encode the training data, and that there will still be cases to set legal precedent for machine learning models.

Note also that it's not just a concern for copyright, but also privacy. If the training data is private, but the model can "recite" (reproduce) some of the input given an appropriate query, then it's a matter of finding the right adversarial inputs to reconstruct some training data. There are many papers on this topic.

Re: GitHub Copilot

#154

Post by zarzavat »

not2b wrote: post #71
dekhn wrote: post #48

Earlier quoted context omitted.

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").

But it actually is explicitly copying the text. That's how it works. The training data are massive, and you will get long strings of code that are pulled directly from that training data. It isn't giving you just the style. It may be mashing together several different code examples taking some text from each. That's called "derivative work".

Synthesising material from various sources isn't copyright infringement, that's called writing.

It's only infringement if the portion copied is significant either absolutely or relatively. A line here or there of the millions in the Linux kernel is okay. A couple of lines of a haiku is not. Copyright is not leprosy.

Re: GitHub Copilot

#155

Post by fabiospampinato »

kleiba wrote: post #24
fabiospampinato wrote: post #5

IMO a potentially more interesting application of this technology would be a learning system that is able to learn your coding style. You give it access to the codebase and it reformats all files on save according to your likings, perfectly. Obviously a program that is able to write actual great code reliably would be spectacular, but we aren't there yet, I don't think Copilot presently is able to make me meaningfull…

Formatting code according to a given style is a much easier task than what Copilot does.

It depends what you mean by "given", I can't write a million line document describing exactly what kind of style I want it to use, the formatter must learn the style on its own from examples.

I agree that something like that would be much easier to make in theory, hence why I'm suggesting it since maybe it could be made ~perfectly, which Codepilot isn't (we haven't unlocked AGI yet).

Re: GitHub Copilot

#156

Post by fzaninotto »

fabiospampinato wrote: post #108
fzaninotto wrote: post #64

Earlier quoted context omitted.

It shows the suggestions line by line, and only shows the best guess. It's not more intrusive than Intellisense. You can actually see all the code blocks Copilot is thinking about if you want to, but that is indeed a distraction.

The problem I see with that is that's not possible for it to understand well which code is the best, GPT-3 is trying to mimic human writing in general, the thing is most human code is garbage, if this system was able to understand how to make code better you could keep training it until you had perfect code, which is not what the current system is giving you (a lot of the times anyway).

I guess you miss the point. It's not trying to suggest the perfect code. Only you know it. It's saving you time by writing a good (sometimes perfect) first solution based on method/argument names, context, comments, and inline doc. And that is already a huge boost in productivity and coding pleasure (as you only have to focus on the smart part).

Re: GitHub Copilot

#157

Post by j2kun »

theden wrote: post #88

Calling it now, there will be a "Copilot considered harmful" post. If you need to go through the suggested code to ensure it's correct, you may as well write it yourself? If you glance at it and it looks about right, you can potentially overlook bugs or edge cases, you'll lose confidence in your own code since you didn't properly conceptualise it yourself. Potentially for newer developers it robs them of active exper…

I imagine, for a while the complexity that Copilot can handle is limited to what most people would pull from stackexchange anyway. And if it helps autocomplete documentation and provide automatically generated (more descriptive) function/variable names, it will probably be a net positive for those limited use cases.

That said, I can't wait to read the first postmortem where someone deployed code generated via Copilot that has a bug. I just hope it's not on a rocketship or missile guidance system.

Re: GitHub Copilot

#158

Post by verst »

apexalpha wrote: post #121
fzaninotto wrote: post #64

Earlier quoted context omitted.

It shows the suggestions line by line, and only shows the best guess. It's not more intrusive than Intellisense. You can actually see all the code blocks Copilot is thinking about if you want to, but that is indeed a distraction.

The animated example on https://copilot.github.com/ shows it suggesting entire blocks of code, though.

It does actually suggest entire blocks of code. I haven't quite figured out yet when it suggests blocks or lines - if I create a new function / method and add a doc string it definitely suggests a block for the entire implementation for me.

Re: GitHub Copilot

#159

Post by pera »

natfriedman wrote: post #60

Hi HN, we've been building GitHub Copilot together with the incredibly talented team at OpenAI for the last year, and we're so excited to be able to show it off today. Hundreds of developers are using it every day internally, and the most common reaction has been the head exploding emoji. If the technical preview goes well, we'll plan to scale this up as a paid product at some point in the future.

Cool project! Have you seen any interesting correlations between languages, paradigms and the accuracy of your suggestions?

Re: GitHub Copilot

#160

Post by 6gvONxR4sf7o »

evgen wrote: post #126
6gvONxR4sf7o wrote: post #54

Earlier quoted context omitted.

My guess would be that the model itself (and the training process) could have different legal requirements compared to the code it generates. The code generated by the model is probably sufficiently transformative new work that wouldn't be GPL (it's "fair use"). I suspect there could be issues on the training side, using copyrighted data for training without any form of licensing. Typically ML researchers have a pret…

No, the code generated is what copyright law calls a derivative work and you should go ask Robin Thicke and Pharrell Williams exactly how much slack the courts give for 'sufficiently transformative new work.

You're missing the fair use aspects. Check out this article on fair use [0].

> In 1994, the U.S. Supreme Court reviewed a case involving a rap group, 2 Live Crew, in the case Campbell v. Acuff-Rose Music, 510 U.S. 569 (1994)... It focused on one of the four fair use factors, the purpose and character of the use, and emphasized that the most important aspect of the fair use analysis was whether the purpose and character of the use was "transformative."

It has some neat examples and explanation.

[0] https://www.nolo.com/legal-encyclopedia/fair-use-what-transf...

Post reply on HN