Offtopic but I found cool stuff in chat GPT regarding IDNA versions. I didn't test it and it also confuses me because there are many cases depending on the context. Q: why idna2003 and idna2008 are not compatible? Give an example in java A: IDNA2003 and IDNA2008 are not compatible because they use different algorithms for encoding internationalized domain names (IDNs) into the ASCII-compatible format required by the domain name system (DNS). IDNA2003 uses a simpler, table-based algorithm, while IDNA2008 uses a more complex, context-sensitive algorithm that provides better handling of certain characters and character combinations. Java: import java.net.IDN; public class Main { public static void main(String[] args) { String domainName = "xn--bcher-kva.example"; // IDNA2003 String idna2003 = IDN.toASCII(domainName, IDN.ALLOW_UNASSIGNED); System.out.println("IDNA2003: " + idna2003); // IDNA2008 String idna2008 = IDN.toASCII(domainName, IDN.USE_STD3_ASCII_RULES | IDN.ALLOW_UNASSIGNED); System.out.println("IDNA2008: " + idna2008); } } Output: IDNA2003: bücher.example IDNA2008: xn--bcher-kva.example In this example, the domain name "bücher.example" is encoded using both IDNA2003 and IDNA2008, and the resulting ASCII-compatible strings are printed to the console. The IDNA2003 encoding results in "bücher.example", which may not be acceptable for use as a domain name in the DNS, while the IDNA2008 encoding results in "xn--bcher-kva.example", which is a valid ASCII-compatible string. ...... Regards, Nicolas. El jue, 2 feb 2023 a las 7:25, Arnt Gulbrandsen via UA-EAI (< ua-eai@icann.org>) escribió:
Hi,
This is precisely why ChaptGTP is banned on Stack Overflow. The ban announcement says “its answers are frequently bad but look plausible” or words to that effect.
Arnt
*From: *UA-EAI <ua-eai-bounces@icann.org> on behalf of Asmus Freytag via UA-EAI <ua-eai@icann.org> *Reply to: *Asmus Freytag <asmusf@ix.netcom.com> *Date: *Thursday, 2 February 2023 at 02:05 *To: *"ua-eai@icann.org" <ua-eai@icann.org> *Subject: *Re: [UA-EAI] Stackoverflow and ChatGPT
Marc,
you've identified two of the main problems with AI based answers. One, the impossibility to fix misperceptions embedded in the training data. The other, the difficulty for a human user to "rate" the level of expertise behind an AI generated answer. You can't use plausibility, because all AI generated answers are plausible. You can't use other "tells" of inexperience, because the AI generated texts don't have them. And you can't "rate" the AI like you can human experts; nor can you rate the true experts that it plagiarizes.
If, as can be expected, significant levels of AI generated output are then being published on various sites in ways that even an AI can't be sure it's AI generated, then you not only get garbage in, garbage out, but fully recycled garbage.
Misinformation of the human generated kind is harmless by comparison.
A./ _______________________________________________ UA-EAI mailing list UA-EAI@icann.org https://mm.icann.org/mailman/listinfo/ua-eai _______________________________________________ By submitting your personal data, you consent to the processing of your personal data for purposes of subscribing to this mailing list accordance with the ICANN Privacy Policy (https://www.icann.org/privacy/policy) and the website Terms of Service (https://www.icann.org/privacy/tos). You can visit the Mailman link above to change your membership status or configuration, including unsubscribing, setting digest-style delivery or disabling delivery altogether (e.g., for a vacation), and so on.