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

581–590 of 1001 posts

Re: GitHub Copilot

#581

Post by IncludeSecurity »

Mountain_Skies wrote: post #477
inimino wrote: post #385

I'm amazed to see how positive the overall response is to this idea. Almost as if programmers think that writing programs is the worst part of the job and ready to be automated away. As someone more aligned with the Dijkstra perspective, this seems to me like one of the single worst ideas I've ever seen in this domain. We already have IDEs and other tools leading to an increase in boilerplate and the acceptance of it…

Not looking forward to dealing with this from a security point of view. It's difficult to get developers to accept responsibility for security vulnerabilities in libraries they've selected for their project ("That's not my code!"). I can see the same thing happening with generated code where they don't want to take responsibility for finding a way to remediate any vulnerabilities they didn't personally type in. Of co…

It says it's trained on "billions of lines of code"

I would augment that to "billions of lines of code that may or may not be safe and secure"

If they could tie in CodeQL into Copilot to ensure the training set only came from code with no known security concerns, that would be a big improvement.

Re: GitHub Copilot

#582

Post by krzyk »

croes wrote: post #368
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…

Fair use doesn't exist in every country, so it's US only?

It exists in EU also (and it much mire powerful here).

Re: GitHub Copilot

#583

Post by kbenson »

inimino wrote: post #385

I'm amazed to see how positive the overall response is to this idea. Almost as if programmers think that writing programs is the worst part of the job and ready to be automated away. As someone more aligned with the Dijkstra perspective, this seems to me like one of the single worst ideas I've ever seen in this domain. We already have IDEs and other tools leading to an increase in boilerplate and the acceptance of it…

I think the mistake you might be making is assuming that any tool adopted is always used all the time. Even professional race car drivers probably opt for an automatic transmission over the manual on the mini-van if they get one. Different choices for different needs.

There will always be a place for meticulous consideration of exactly what's being done, and many levels of that as well. For the same reason people reach for python to mock up a proof of concept or throw something together that is non-essential but useful to have quickly, even meticulous programmers might use this to good effect for small things they don't care to spend a lot of time on because it's not as important as something else, or the language they're using for this small task isn't one they feel as proficient in.

Re: GitHub Copilot

#585

Post by quek »

inimino wrote: post #385

I'm amazed to see how positive the overall response is to this idea. Almost as if programmers think that writing programs is the worst part of the job and ready to be automated away. As someone more aligned with the Dijkstra perspective, this seems to me like one of the single worst ideas I've ever seen in this domain. We already have IDEs and other tools leading to an increase in boilerplate and the acceptance of it…

> As someone more aligned with the Dijkstra perspective, this seems to me like one of the single worst ideas I've ever seen in this domain.

Absolutely true.

If your code is so repetitive that can be correctly predicted by an AI, you are either using a language that lacks expressiveness or have poor abstraction.

The biggest problem in the software world is excessive complexity, excessive amounts of (poor) code and reinventing the wheel.

Re: GitHub Copilot

#586

Post by spec-obs »

feross wrote: post #306
fzaninotto wrote: post #40

I'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…

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…

spot the Github PR folks!

Re: GitHub Copilot

#587

Post by meowface »

ayush--s wrote: post #524
hobofan wrote: post #266

Earlier quoted context omitted.

Have you used any intelligent code completion in the past? E.g. I'd really be interested how it compares to TabNine[0], which already gives pretty amazing single line suggestions (haven't tried their experimental multi-line suggestions yet). [0]: https://www.tabnine.com

I'm curious as to how relevant Copilot would be when autocompleting code that is specific to my codebase in particular, like Tabnine completes most used filters as soon as I type the db table name for the query. I'm a big tabnine fan because it provides this feature. I'm much more often looking to be suggested a line than an entire function because I'm mostly writing business logic. also tabnine is useless in multi-l…

Yeah, I've been very happy with Tabnine for a while, but the prospect of good multi-line completions is appealing. I might try running both Tabnine and Copilot simultaneously for a bit to A/B test.

Re: GitHub Copilot

#588

Post by bayindirh »

pvorb wrote: post #548
throwaway675309 wrote: post #454

Earlier quoted context omitted.

I mean you say this, but you and most likely the majority of programmers rely on dozens of repositories, packages and libraries with likely zero deep understanding of it (and at the very least haven't read the source code of ) so I don't really understand the difference here. The advantage of something like this is that instead of having to go to stack overflow or any number of reference sites and copy pasta it can j…

I really wonder who those folks copy-pasting from Stack Overflow all day are. I only rarely find pieces of code that I can copy-paste. Typically Stack Overflow only gives me an idea of how to solve something, but incorporating that idea into my code base is still not trivial.

> I really wonder who those folks copy-pasting from Stack Overflow all day are.

I can think about people who can do this happily. Some of them are professional programmers. Some are self-taught. Some have CS education. Seriously.

OTOH, I'm similar to you. I either re-use my own snippets or read SO or similar sites to get an idea generally how a problem is solved and adapt it to my code unless I find the concept I'm looking for inside the language docs or books I have.

Yes, I'm a RTFM type of programmer.

Re: GitHub Copilot

#589

Post by tasuki »

> Tests without the toil. Tests are the backbone of any robust software engineering project. Import a unit test package, and let GitHub Copilot suggest tests that match your implementation code.

Isn't that the wrong way around? I'd like to start by writing the tests, and for GitHub Copilot to please implement the function that makes them pass.

Re: GitHub Copilot

#590

Post by sama »

AI FTW!

(dang please don't ban me for a low-quality comment :) i couldn't resist but will not make it a habit!)

Post reply on HN