Re: GitHub Copilot
David Haslam <dfhdfh-g/[email protected]> Thu, 24 Apr 2025 19:00:34 +0000
| Newsgroups | gmane.comp.literature.sword.devel |
|---|---|
| Message-ID | <kqBygZhqpHhLxW_HTUORLiTKwvf3iZhhNE3AqhRqcfJx4-4SM5VLjWX-m9bQWnYevyFTCC9ulIR98tu7AJmptFC_hpRWFP3BQYezf9_0g-U=@protonmail.com> |
Johan, Hehehe! 🤣 And my AI queries are not copyrighted! 😎 Best regards, David Sent with [Proton Mail](https://pr.tn/ref/SWXT9A5YZ67G) secure email. On Thursday, April 24th, 2025 at 7:37 PM, Johan Marais <[email protected]> wrote: > David, > I used your query (hope you do not mind), but asked for Afrikaans place names. > It listed two, both wrong, but conceded that the one name does not contain the letter sequence. > Indeed stumped! > > Johan > >> On 24 Apr 2025, at 20:21, David Haslam <[email protected]> wrote: > >>  >> I’m not a coder but I completely stumped ChatGPT today with a simple query. >> >> List all place names containing the letter sequence "rfr" >> >> The full detailed conversation is posted in my Facebook profile. >> >> David >> >> Sent from [Proton Mail](https://proton.me/mail/home) for iOS >> >> On Thu, Apr 24, 2025 at 19:09, Tobias Klein < [[email protected]](mailto:On Thu, Apr 24, 2025 at 19:09, Tobias Klein <<a href=)> wrote: >> >>> Hi pinoaffe, >>> >>> Thanks for your feedback! >>> >>> Regarding potential legal and ethical issues you mention I think >>> everyone will have to make their own judgment before using this technology. >>> The company I am working for has recently decided to deploy GitHub >>> Copilot for a large population of developers (multiple thousand >>> licenses) and they deemed it to be OK and I also did. >>> >>> Regarding the technical issue you mention: >>> >>>> - LLMs are very good at generating text/code that *looks* >>>> plausible/correct, but that is not necessarily correct. Therefore, it >>>> is often more difficult to verify that code generated by an LLM is >>>> not subtly broken than it is to write similar code yourself. *PLEASE* >>>> do not underestimate this issue. >>> >>> Of course the results must always be evaluated by the developer to >>> ensure correctness. >>> In my experience, there are sometimes cases were the results generated >>> by LLMs are not correct. I have seen this both with ChatGPT as well as >>> GitHub Copilot. >>> However, in my experience the positive results that I got definitely >>> outweigh the negative results. >>> >>> Best regards, >>> Tobias >>> _______________________________________________ >>> sword-devel mailing list: [email protected] >>> http://crosswire.org/mailman/listinfo/sword-devel >>> Instructions to unsubscribe/change your settings at above page >> >> _______________________________________________ >> sword-devel mailing list: [email protected] >> http://crosswire.org/mailman/listinfo/sword-devel >> Instructions to unsubscribe/change your settings at above page _______________________________________________ sword-devel mailing list: [email protected] http://crosswire.org/mailman/listinfo/sword-devel Instructions to unsubscribe/change your settings at above page