Forum > Other
Using chatgpt to bring the pascal/lazarus platform up to date more quickly.
Martin_fr:
Well....
About the licensing. Even if we could safely determine if any produced code by a given AI is free of "copied" material (either verbatim, or with negligible differences) or the source of the copy would permit use under the licenses that would be required ..... That would not be the end of it.
I guess, but do not know, that an AI under current law in probably all countries of the world can not itself hold legal rights. But that may change. Just to say, if a tree can have the right of owning itself: https://en.wikipedia.org/wiki/Tree_That_Owns_Itself ....
But then an AI is in the end a machine. And it may well be possible that the owners of a machine hold rights on the product of that machine. And those rights would be hold automatically, until explicitly give up or transferred....
Mind, all that needs to be checked for any country in the world.
But even then, lets for arguments sake ignore the above.
@Webdrifter Why don't you try how far an AI would actually get?
You say it can do debugging. Well then, we have a bugtracker full of bugs. Get the AI to tell you what is wrong. That is which exact line of code does the wrong thing.
It doesn't need to give the corrected line of code (or you do not need to forward the correction).
If we know which line is wrong (and in which way it is wrong), then for many bugs it would be a huge steps toward fixing them.
So all you need is add the info "which line is wrong, and why that is" .
Or pick a feature that you miss. And see if the AI really generates stable working code. (Because if it aint stable, it may be easier to do it from scratch than to fix some half baked code).
Because, if you don't succeed in getting good result for some bigger tasks, well then it really doesn't matter what the license would be.
Afaik most of the examples for AI generating code are either
- trivial / standard code blocks, just rewritten to use identifiers matching a give description
- small tasks, for which the human had to give very very precise description (in human language), and often had to go through several iterations before resulting in something useful. But if the human has to describe it that detailed, then it's just a translation, and for a programmer may be easier to describe it in a programming language right to start with.
Of course I could have missed some news. After all there is a huge flood of news going on... (Maybe I could filter those news using an AI... ;) )
Чебурашка:
--- Quote from: dseligo on January 12, 2023, 01:20:53 am ---I was asking OpenAI chat about licensing.
This is snippet:
--- Code: Text [+][-]window.onload = function(){var x1 = document.getElementById("main_content_section"); if (x1) { var x = document.getElementsByClassName("geshi");for (var i = 0; i < x.length; i++) { x[i].style.maxHeight='none'; x[i].style.height = Math.min(x[i].clientHeight+15,306)+'px'; x[i].style.resize = "vertical";}};} ---Me: I am more interested in licensing regarding the code you produce. Can I use code you generate without legal consequences? Answer:As a language model, I am not capable of having a legal standing or holding a license, any code I produce is intended to be used as an example and for educational or informational purposes. However, it's important to be aware that code generated by me, like any other code, may be subject to intellectual property rights. It's ultimately up to the owner of the rights to determine how the code can be used and distributed. So it is important to be cautious and get permission before using any code generated by me or any other third party if it is intended to be used for commercial purpose. Additionally, I suggest you double check the code and adapt it to fit your needs and verify that it does not infringe any other rights. I always include a LGPL license as an example of open-source license but that doesn't mean the code is automatically licensed under LGPL, you should verify if the code can be used under that license or any other. It's also a good practice to always check licenses of any open-source libraries or code you use to ensure that you are using them legally and in compliance with the license terms.
--- End quote ---
While reading this I started wondering: from now on how can anyone be sure that every contribution made to fpc (or any other community software) is genuine, and is not originating from an AI, that, in turn could have generated using copyrighted code?
440bx:
--- Quote from: Чебурашка on April 24, 2023, 04:42:27 pm ---<snip> ... from now on how can anyone be sure that every contribution made to fpc (or any other community software) is genuine, and is not originating from an AI, that, in turn could have generated using copyrighted code?
--- End quote ---
The problem of the code being _original_ pre-dates A.I. This is why projects that clone the functionality of some piece of software are done in "clean rooms".
What makes A.I very deficient in any technical field (even baking) is that it has no ability to _analyze_, therefore create even a semblance of consistency.
lainz:
chatgpt is not that bad, it works sometimes and sometimes not, like ourselves with make bugs in software as well.
dbannon:
WRT bugs, Iainz, sure, my first cut of code has bugs, I then find and fix the bugs. Thats easy because, having just written it, its clear in my head what it is supposed to do and how it does it. If you were debugging my code, or I was a year after writing it, harder. So, you or me, debugging the AI's code is always going to be harder.
WRT License, thats a lot harder. The statement Чебурашка posted does, IMHO, give fair warning to anyone using AI generated code, "someone", "sometime" may knock on their door and say "you are using my code". Maybe we need a tickbox on every bug report, every pull request, "No AI code or other unclear license included" ?
Remember Unisys ?
Davo
Navigation
[0] Message Index
[#] Next page
[*] Previous page