Maybe I'm wrong and I'm just a modern-day Luddite. I'd be interested to know if there are any genuine real-world cases where AI code is useful.
I think not for developing software. As others have pointed out, if you are not an expert, it is dangerous, because you cannot verify the results independently. If you are an expert, quite frankly, your top time killer is not being too slow with boilerplate code, but too many meetings. If I could send an AI to a meeting, that would free me up to write high quality code that beats any AI :)
But there are valid use cases outside of, but related to software development. For example, I found Chat GPT hugely useful when preparing a talk about some software development principles that I was semi-familiar with. I could actually ask Chat GPT about concepts and trade-offs for various techniques and it would give me very useful opinions. I don't think I could have gotten better answers from an experienced colleague and so, for me, Chat GPT has passed the Turing Test there.
As for Netbeans, how about fixing the refactoring function (https://github.com/apache/netbeans/issues/6335 et. al.) before worrying about AI companions :)
cheers, Ulrich -- iSYS Software GmbH Ulrich Mayring | Full Stack Developer Technology Lab / R&D Tel: +49 (0) 89 46 23 28-0 | Fax +49 (0) 89 46 23 28-14 email: ulrich.mayr...@isys.de Grillparzerstraße 10 | D-81675 München www.isys.de Sitz der Gesellschaft: München | HRB 111760 Geschäftsführer: Stefan Fischer und Max Haller --------------------------------------------------------------------- To unsubscribe, e-mail: users-unsubscr...@netbeans.apache.org For additional commands, e-mail: users-h...@netbeans.apache.org For further information about the NetBeans mailing lists, visit: https://cwiki.apache.org/confluence/display/NETBEANS/Mailing+lists
