"Software eats world" just got more real. Funny that programmers thought they were eating the world with software, now, software has eaten them.
far from it, this thing won't write full applications by itself
GitHub Copilot
701–710 of 1001 posts
Re: GitHub Copilot
#702Awesome - but I fear maintaining the code generated by it in the future.. can the AI maintain it as well?
I am looking forward to AI testing the programs I write though. That would be awesome.
Re: GitHub Copilot
#703"Software eats world" just got more real. Funny that programmers thought they were eating the world with software, now, software has eaten them.
far from it, this thing won't write full applications by itself
I know.. But we can dream. Also I'me sure when we first got code completion we said - "This thing won't write functions by itself."
Re: GitHub Copilot
#704Earlier quoted context omitted.
> Almost as if programmers think that writing programs is the worst part of the job and ready to be automated away. writing the programs is definitely boring garbage work. Typing is so slow and annoying - hence autocomplete being a standard tool. This is, to me, just fancy autocomplete. > to an increase in boilerplate and the acceptance of it because they make it easier to manage. Boilerplate optimizes for the right…
>Boilerplate optimizes for the right things - code that's easier to read and analyze, but takes longer to write. This is wrong and the same retarded logic Java used to defend not introducing var and similar features for ages. Boilerplate is usually noise around the actual logic - it's a result of limited abstractions. When you're repeating same code over and over you raise that segment to a separate concept, that's h…
Thanks for being the person who I knew would try to make this about Java. I don't care about Java, it was a trivial example.
The rest of your post doesn't really have to do with mine. Yeah, you can cut down on boilerplate with changes to languages... duh. But in terms of conveying context there's always a tradeoff of explicit vs implicit, and one of those costs is taking the time to actually turn your mental model into a written implementation - this eases that burden.
As I said, it's a fancy autocomplete.
Re: GitHub Copilot
#705I don't think we need to start looking for new career paths yet. This example has a few bugs and it took me longer to track them down than it would have to write it myself: #!/bin/bash # List all python source files which are more than 1KB and contain the word "copilot". find . \ -name "*.py" \ -size +1000 \ -exec grep -n copilot {}\; "-exec grep -n copilot {}\;" needs to have a space before the semicolon otherwise f…
the main argument against Copilot for me. it takes longer to grok existing code than just write it from ground up.
That's why this copilot won't fly. The junior programmer will not be able to spot subtle errors but will kind-of feel "productive" by some random pastes from a giant brain, which cannot be interrogated.
If anything, I see copilot generating more work for existing, senior programmers - so there you have it.
Re: GitHub Copilot
#706Hi 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?
In the end this would slightly increase likelihood of such sections appearing in licenses generated by AIs.
Re: GitHub Copilot
#707I'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…
You can only solve relatively small problems this way. As I get older, I like the physical act of programming less and less, and just want to solve problems so I can get going on all of my ideas backlog. I've been programming almost every day for the last 38 years. What I really want to do is solve (my) problems.
But programming is the greatest fun on earth. Wait no, being able to work on your ideas and communicating them to the computer is the greatest fun on earth. Now, if your only tools for communication are made by "productive developers", this is where the problem is. Not with programming itself.
Re: GitHub Copilot
#708How does this compare to tabnine?
Re: GitHub Copilot
#709The landing page is really cool. It looks like the screencast is built with Javascript, is there any tool that helps building such screencasts? I assume that it's not trivial to build such animations.
Re: GitHub Copilot
#710To see all the 1100+ comments, you'll need to click More at the bottom of the page, or like this:
https://news.ycombinator.com/item?id=27676266&p=2
https://news.ycombinator.com/item?id=27676266&p=3
https://news.ycombinator.com/item?id=27676266&p=4
https://news.ycombinator.com/item?id=27676266&p=5
(Comments like this will go away when we turn off pagination. I know it's annoying. Sorry.)