501–510 of 1001 posts
Earlier quoted context omitted.
There is Tabnine that can work like this
Last time I tried Tabnine it wasn't really of much use to me, the top of the line GPT-3 is a much much bigger model, it should be able to do much more intelligent things.
Earlier quoted context omitted.
> - under what license the generated code falls under? Is it even copyrighted? Generally my understand is that to be copyrightable it has to be the output of a human creative process, this doesn't seem to qualify (I am not a lawyer). See also, monkeys can't hold copyright: https://en.wikipedia.org/wiki/Monkey_selfie_copyright_disput...
> Is it even copyrighted? Isn't it subject to the licenses the model was created from, as the learning is basically just an automated transformation of the code, which would be still the original license - as else I could just run some minifier, or some other, more elaborate, code transformation, on some FOSS project, for example the Linux kernel, and relicense it under whatever? Does not sound right to me, but IANAL…
Is this not subject to the same concern, but at a much greater scale? What happens when a large entity with a legal department discovers an instance of Copilot-generated copyright infringement? Is the project owner liable, is GitHub/Microsoft liable, or would a court ultimately tell the infringee to deal with it and eat whatever losses occur as a result?
In any case, I hope that GitHub is at least limiting any training data to a sensible whitelist of licenses (MIT, BSD, Apache, and similar). Otherwise, I think it would probably be too much risk to use this for anything important/revenue-generating.
As a business / product person I am naturally wondering how much more productive this will make my engineering team, should I overtime expect to reduction in costs, faster shipping times...or will the benefit manifest itself in more reliable code...?
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…
Whether you’re working in a new language or framework, or just learning to code, GitHub Copilot can help you find your way. Tackle a bug, or learn how to use a new framework without spending most of your time spelunking through the docs or searching the web.
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…
Some people think the problem is that we don't have enough code. Anyone that has to maintain code knows that the problem is that we have too much code.
This looks awesome! And I'd really like to try it out. 2 security thoughts that I couldn't find answers to: 1. how does the input fed into OpenAI codex filter out malicious code pollution? or even benign but incorrect code pollution (relevant research on stackoverflow for example - https://stackoverflow.blog/2019/11/26/copying-code-from-stac... ) 2. In an enterprise setting, what does the feedback loop look like? How…
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 tried the paid version of tabnine and was really unhappy because it suggested me code with syntax errors and introduced subtle bugs when I did not closely review every generated line. It was as if you have someone very impatient sitting next to you typing before actually really listening what you want to do. Is Copilot better? Does it suggest broken code, too?
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…
People have made some variation of this argument since the move from writing binary to writing assembly. With every new layer of abstraction there’s more power. The long term benefit of a tool that can do this well far exceeds what humans can do by hand, but that may not be true in the very short term. Either way, I suspect the benefits to be big.
Unlike an additional abstraction layer, the readibility is not increased.
So now I make a bot to upload repositories of intentionally buggy code so that when people blindly use this autocomplete my hacking becomes easier!