From mboxrd@z Thu Jan 1 00:00:00 1970 X-Spam-Checker-Version: SpamAssassin 3.4.4 (2020-01-24) on inbox.vuxu.org X-Spam-Level: X-Spam-Status: No, score=-0.7 required=5.0 tests=DKIM_INVALID,DKIM_SIGNED, HTML_MESSAGE,MAILING_LIST_MULTI,T_SCC_BODY_TEXT_LINE,URIBL_SBL_A autolearn=ham autolearn_force=no version=3.4.4 Received: (qmail 26860 invoked from network); 5 Jun 2023 14:51:44 -0000 Received: from zapf.ntg.nl (5.39.185.232) by inbox.vuxu.org with ESMTPUTF8; 5 Jun 2023 14:51:44 -0000 Received: from localhost (localhost [127.0.0.1]) by zapf.ntg.nl (Postfix) with ESMTP id 6D949EDF; Mon, 5 Jun 2023 16:51:18 +0200 (CEST) X-Virus-Scanned: Debian amavisd-new at zapf.ntg.nl Received: from zapf.ntg.nl ([127.0.0.1]) by localhost (zapf.ntg.nl [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id VJlkzU-Vx0Zc; Mon, 5 Jun 2023 16:51:13 +0200 (CEST) Received: from zapf.ntg.nl (localhost [127.0.0.1]) by zapf.ntg.nl (Postfix) with ESMTP id 02348CF0; Mon, 5 Jun 2023 16:51:13 +0200 (CEST) Received: from localhost (localhost [127.0.0.1]) by zapf.ntg.nl (Postfix) with ESMTP id A5C2DCF0 for ; Mon, 5 Jun 2023 16:51:10 +0200 (CEST) X-Virus-Scanned: Debian amavisd-new at zapf.ntg.nl Received: from zapf.ntg.nl ([127.0.0.1]) by localhost (zapf.ntg.nl [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id jlBt5jG3wrDp for ; Mon, 5 Jun 2023 16:51:08 +0200 (CEST) Received-SPF: Pass (mailfrom) identity=mailfrom; client-ip=209.85.216.43; helo=mail-pj1-f43.google.com; envelope-from=luigi.scarso@gmail.com; receiver= Received: from mail-pj1-f43.google.com (mail-pj1-f43.google.com [209.85.216.43]) (using TLSv1.3 with cipher TLS_AES_128_GCM_SHA256 (128/128 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by zapf.ntg.nl (Postfix) with ESMTPS id 7DE12CD3 for ; Mon, 5 Jun 2023 16:51:08 +0200 (CEST) Received: by mail-pj1-f43.google.com with SMTP id 98e67ed59e1d1-2565b864f9aso2301908a91.1 for ; Mon, 05 Jun 2023 07:51:08 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20221208; t=1685976665; x=1688568665; h=cc:to:subject:message-id:date:from:in-reply-to:references :mime-version:from:to:cc:subject:date:message-id:reply-to; bh=t9q/scydZnqZ7PBKaySMUYgAEb+gXiQVm9pDy7JKhRs=; b=JKWjarEWZOmdDl7hl6RD/3x82W5EHReyZdfcjQWgI/5w/9ZOHgTq3DCPZBGXp91njE +nT6sqB5bYZtwGOeQaRDoeOfTgZJYf0FYLyCacfDmRviJdiq0U9+Hw0Cwkmj8IkMlaOA MDPuIh2bH7PUYJ2N/3UICCVnP/Ko43MOj9Klesfp3CH6WU/6Z1Wj1TohoSeGhzNYyVn4 RphMQYNUY5+qOyGGEDYrfitlY2sPGhgPHzX9ekIzlhYrnTbkWZU/jk8KHqBM5W2UwUL8 xzJiS4qqT+c+I43uQi+WJC+cXfVspYire3gapeCB/N1abugNtHoOnIXbrST/W4oAN6QL LOAw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20221208; t=1685976665; x=1688568665; h=cc:to:subject:message-id:date:from:in-reply-to:references :mime-version:x-gm-message-state:from:to:cc:subject:date:message-id :reply-to; bh=t9q/scydZnqZ7PBKaySMUYgAEb+gXiQVm9pDy7JKhRs=; b=ECkxv6f+I8swF3CkdLM6RTu1so8FsC0jsiNxwNWJMEtyDcAx4kPNkoHBs39IMlfdoR dup5UsEylZ53CRG5YwuOtv41A11J8oFD0gLPrps0G9B7zfdxgJBdV/41cEc8Fh5J1PH/ u+Di3UEkTiX6kPg7FK+4JsRdKPh9DVMHl5yrZq9UTysGn626+3KGd1QVyehYTQ/oqfP6 GbwHootusJK77BVBHFBB3h9PD2MTKd1z57owGb672YzAUZNXYMiDGDIe3thXFQuv90be iYeelERUMzrUUocvuGEeJyeOojKwy0ZhHYhO6W/chk40vFhFV55sObi3T4MjxOpDEsso 4xeA== X-Gm-Message-State: AC+VfDwx8CbZ91mU84Q0SaHKw6T6wTMWT/fbmOnOcxNBdNhT0FyqiFIE C3mMZRHYlOHa1L4kFSDbti95q7IrOhCTngFeK2M7/VBjodk= X-Google-Smtp-Source: ACHHUZ4xJ958LgSlPX4jTMde73X+dAPaBV8m7W+2UYCF4gxRK+fnKqkUJdLTFSKP0gQhqRBvQYom6ynaYtLhUnrV7KA= X-Received: by 2002:a17:90b:3ec9:b0:259:bdb:6956 with SMTP id rm9-20020a17090b3ec900b002590bdb6956mr2828269pjb.7.1685976665140; Mon, 05 Jun 2023 07:51:05 -0700 (PDT) MIME-Version: 1.0 References: <4d6bfac1-1ce5-fff0-9309-b07b6879eb76@xs4all.nl> <87fs763n7h.wl-berend@pobox.com> <74549341-ee0c-13ea-82df-4a1156b6c6da@icloud.com> In-Reply-To: <74549341-ee0c-13ea-82df-4a1156b6c6da@icloud.com> Date: Mon, 5 Jun 2023 16:50:53 +0200 Message-ID: To: mailing list for ConTeXt users Subject: Re: [NTG-context] knuth X-BeenThere: ntg-context@ntg.nl X-Mailman-Version: 2.1.38 Precedence: list List-Id: mailing list for ConTeXt users List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , From: luigi scarso via ntg-context Reply-To: mailing list for ConTeXt users Cc: luigi scarso Content-Type: multipart/mixed; boundary="===============8670888370040014149==" Errors-To: ntg-context-bounces@ntg.nl Sender: "ntg-context" --===============8670888370040014149== Content-Type: multipart/alternative; boundary="00000000000039b02705fd63084c" --00000000000039b02705fd63084c Content-Type: text/plain; charset="UTF-8" On Mon, 5 Jun 2023 at 15:18, Alan Braslau via ntg-context < ntg-context@ntg.nl> wrote: > > On 04/06/23 04/06/23, 15:57, Berend de Boer via ntg-context wrote: > >> Probably some on this list already checked how well chatgpt answers > >> questions about domains one knows well and then probably noted that in > >> spite of impressive wording, one can run into quite incorrect answers. > > > > I've been using it for ConTeXt, and to be honest, it works amazingly > > well. It hallucinates sometimes, but it's such a time saver. > > Maybe someone should try asking it to write documentation/manuals? > > As a teacher, we are accustomed to seeing Google/Wikipedia/etc. > cut-and-paste nonsense; now, this nonsense appears more polished, and > our students are none the wiser. Saves them time, too! ;-) > > Who said: "the best way to economize thought is not to think at all"? > not all is bad: sometimes a textual description can replace a formalized notation, e.g. https://fosstodon.org/@tao@mathstodon.xyz/110250604086213386 I can imagine similar examples with tables. Of course a very high level text is often ambiguous (as some kind of formalized grammars, after all) but the example shows that in these cases it is better to fix something already almost ok than to typeset it from scratch. -- luigi --00000000000039b02705fd63084c Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable


=
On Mon, 5 Jun 2023 at 15:18, Alan Bra= slau via ntg-context <ntg-context@= ntg.nl> wrote:

On 04/06/23 04/06/23, 15:57, Berend de Boer via ntg-context wrote:
>> Probably some on this list already checked how well chatgpt answer= s
>> questions about domains one knows well and then probably noted tha= t in
>> spite of impressive wording, one can run into quite incorrect answ= ers.
>
> I've been using it for ConTeXt, and to be honest, it works amazing= ly
> well. It hallucinates sometimes, but it's such a time saver.

Maybe someone should try asking it to write documentation/manuals?

As a teacher, we are accustomed to seeing Google/Wikipedia/etc.
cut-and-paste nonsense; now, this nonsense appears more polished, and
our students are none the wiser. Saves them time, too! ;-)

Who said: "the best way to economize thought is not to think at all&qu= ot;?


not all is bad: som= etimes a textual description can replace a formalized notation, e.g.
<= div>https://fosstodon.org/@tao@mathstodon.xyz/110250604086213386
I can imagine similar examples with tables.
Of course a ver= y high level text is often ambiguous (as some kind of formalized grammars, = after all)
but=C2=A0 the example shows that in these cases=C2=A0 = it is better to fix something already almost ok than=C2=A0 to typeset it fr= om scratch.

--
luigi

<= /div>
--00000000000039b02705fd63084c-- --===============8670888370040014149== Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline ___________________________________________________________________________________ If your question is of interest to others as well, please add an entry to the Wiki! maillist : ntg-context@ntg.nl / https://www.ntg.nl/mailman/listinfo/ntg-context webpage : https://www.pragma-ade.nl / http://context.aanhet.net archive : https://bitbucket.org/phg/context-mirror/commits/ wiki : https://contextgarden.net ___________________________________________________________________________________ --===============8670888370040014149==--