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

521–530 of 1001 posts

Re: GitHub Copilot

#521

Post by ranguna »

ingvul wrote: post #386

I can only imagine one of the big reasons to release Copilot to the public for free is to make it better by sending back to GitHub the "reviewed code". Example: - Copilot suggests me a snippet of code - It's almost what I wanted. I fix the code - Copilot sends back the fixed code to GitHub - Copilot gets better at guessing my (and others) wishes Unless Copilot is running locally, I won't use it.

Same, I do quite a bit of mistakes like pasting secrets and immediately deleting them right after, and I also have local secrets that are gitignored which I think copilot would just upload without a second thought.

Re: GitHub Copilot

#522

Post by mdaniel »

6gvONxR4sf7o wrote: post #275
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.

If I put a section in my LICENSE.txt prohibiting use as training data in commercial models, would that be sufficient to keep my code out of models like this?

Only if they trained a model to be able to read and understand LICENSE.txt files -- wowzers what a monster improvement that would be for the world

Or, I guess a sentinel phrase that the scraper could explicitly check: `github-copilot-optout: true`

Re: GitHub Copilot

#523

Post by dennisy »

The site mentions the system this is built on: Codex by Open AI.

Has anyone seen anything about this system? Are others able to build upon it?

Re: GitHub Copilot

#524

Post by ayush--s »

hobofan wrote: post #266
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…

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-lines completes. which is where co-pilot should be strong.

Re: GitHub Copilot

#525

Post by ranguna »

reilly3000 wrote: post #229
colesantiago wrote: post #18

Gigantic caveat. > I agree to these additional telemetry terms as part of the technical preview

Right. If you’re comfortable giving access to your source files to GitHub+OpenAI, then go for it. I’m not sure how this would apply to secret keys or flat files with customer data/PII, but in any case that makes it a non-starter for me. Their “Please do not share this URL publicly.” Banner at the top of the page which disclosed this info makes my skin crawl a bit… If I were only working on public projects I would be…

No, you are not being paranoid. This tool literally uploads all the code it wants off your machine, and I see no way of filtering out secrets and the likes. You have all the rights to be worried about that.

Re: GitHub Copilot

#526

Post by dragonwriter »

6gvONxR4sf7o wrote: post #275
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.

If I put a section in my LICENSE.txt prohibiting use as training data in commercial models, would that be sufficient to keep my code out of models like this?

> If I put a section in my LICENSE.txt prohibiting use as training data in commercial models, would that be sufficient to keep my code out of models like this?

Neither in practice (because it doesn't look for it) nor legally in the US, if Microsoft’s contention that such use is “fair use” under US copyright law.

That “fair use” is an Americanism and not a general feature of copyright law might create some interesting international wrinkles, though.

Re: GitHub Copilot

#527

Post by WanderPanda »

vbezhenar wrote: post #512
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 that there's a division between "productive" developers and "meticulous" developers. I know that I'm not the first one. My best days are when I'm removing code. I'm very wary from using frameworks and huge libraries. I learned few frameworks and libraries, I've chosen few that correspond to my style and I'm very careful when it comes to adapting new ones. I prefer to spend a week coding auth layer rather than…

Sounds like you should be working on libraries instead of products then?!

Re: GitHub Copilot

#528

Post by kujino »

rberger wrote: post #488

Assuming this is actually a useful and powerful addition to a programmer's quiver (which it looks like it will be if not already is). Then the tying it to Visual Studio is a variation of Microsoft's "Embrace and Extend" philosophy but for Programmers and open source in general. It uses Open Source as its input but, as far as I can tell (and I would be pleasantly surprised if I was wrong), CoPilot itself is not Open S…

VSCode has telemetry, the extension market place can't be used by non-microsoft products, VSCode is not open source (only VSCodium is), many of the MS extension are not open source (like live collaboration), etc.

VSCode followed the classic big tech recipe : 1) make it open source to look like the good guys & get adoption and contributions 2) close-source many key components & add spyware.

Story of Android too pretty much

Post reply on HN