From mboxrd@z Thu Jan 1 00:00:00 1970 Path: news.gmane.io!.POSTED.blaine.gmane.org!not-for-mail From: Joel Reicher Newsgroups: gmane.emacs.help Subject: Re: Enhancing ELisp for AI Work Date: Thu, 26 Dec 2024 17:06:47 +1100 Message-ID: <865xn7dll4.fsf@gmail.com> References: <7290780.2375960.1734348492938.ref@mail.yahoo.com> <7290780.2375960.1734348492938@mail.yahoo.com> <6c53521e-4aa6-40d1-b4a5-0e00989ad201@easy-emacs.de> <87v7v9f3uh.fsf@librehacker.com> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1; format=flowed Content-Transfer-Encoding: quoted-printable Injection-Info: ciao.gmane.io; posting-host="blaine.gmane.org:116.202.254.214"; logging-data="25171"; mail-complaints-to="usenet@ciao.gmane.io" User-Agent: Gnus/5.13 (Gnus v5.13) Cc: Andreas =?iso-8859-1?Q?R=F6hler?= , help-gnu-emacs@gnu.org To: Christopher Howard Original-X-From: help-gnu-emacs-bounces+geh-help-gnu-emacs=m.gmane-mx.org@gnu.org Thu Dec 26 07:07:18 2024 Return-path: Envelope-to: geh-help-gnu-emacs@m.gmane-mx.org Original-Received: from lists.gnu.org ([209.51.188.17]) by ciao.gmane.io with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.92) (envelope-from ) id 1tQh1h-0006NO-QK for geh-help-gnu-emacs@m.gmane-mx.org; Thu, 26 Dec 2024 07:07:17 +0100 Original-Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1tQh1Q-00061Q-8a; Thu, 26 Dec 2024 01:07:00 -0500 Original-Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1tQh1M-000613-Ei for help-gnu-emacs@gnu.org; Thu, 26 Dec 2024 01:06:56 -0500 Original-Received: from mail-pl1-x62c.google.com ([2607:f8b0:4864:20::62c]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1tQh1K-0003aL-Vv for help-gnu-emacs@gnu.org; Thu, 26 Dec 2024 01:06:56 -0500 Original-Received: by mail-pl1-x62c.google.com with SMTP id d9443c01a7336-218c8aca5f1so83919475ad.0 for ; Wed, 25 Dec 2024 22:06:54 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1735193213; x=1735798013; darn=gnu.org; h=content-transfer-encoding:mime-version:user-agent:message-id:date :references:in-reply-to:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=77CmXxWF1ObiKGgBT1Ccvs/Noxpg6EZAexhe1zRJpdw=; b=Ab4YZOjEdYX1rGsp0qALdncl+C6hx/Y7h5vrW+gdYaOTBr/iLXomfBJMR8/zGdcaNx Se273/5dmUjKFP7IkngTuZ/Jma8MmiXRk/CiPnhDbEkwo1iYcTP4A8HlOTDW9b9YsaeH 09y2Kgph33Ss9hZt6sMJoTHZ4awzbAMDXaty6unIQmcf3BofkzzNSLHxGEIIVQJSbx53 EI6vtdlX3v1XGmIdku9ti5QqGxHkuecGffZF4zl7vhTuUErD6FmVuRRLzJ62Xa3b1UKY N/MXsgCSLqlmoz42HzF1AdZllGbmxJwu5PuE8NqpHLb6jHBwtejKNtXpXiGhmG6CCp3X IrDQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1735193213; x=1735798013; h=content-transfer-encoding:mime-version:user-agent:message-id:date :references:in-reply-to:subject:cc:to:from:x-gm-message-state:from :to:cc:subject:date:message-id:reply-to; bh=77CmXxWF1ObiKGgBT1Ccvs/Noxpg6EZAexhe1zRJpdw=; b=W46jHkL0UpFJMHiIT+0NForMd3+NqFNrGL7ct3vkRMs9N0nQguFGvYz3RWpFm7fj8f uLmHWuSGBbo5WLJjUkP99bJnV7Y5QfrqoaupOQ3KyarvfQi6aIX0sL4Wef7H4cBoEfbl Qry/J8JQeppL+GettDeUFODIfXPK2AX0jEDYXOF124OJ6Xor9RmQW5ysfiGpBieLAqwe 0Zw1ntAavG0k7UeX/rQLRW7i4zeL+Hh+9ZlWTg3V1NNFHxDvDypCpaVTxZxBwCrdvQgM yN1x36U/tEcKM4vVnP4UMiumo2rMoQpqLBqv5r8q1Q1butBI0femk4M539en+LWPIS5B 7jDw== X-Forwarded-Encrypted: i=1; AJvYcCWEOUuCpxggjO8DZwBmFWtgljRXYDgscQU9XFfaY21H9XQ1kFDz2LXCL/p5gQ46d08FivoQ75QKbzGzB+m46g==@gnu.org X-Gm-Message-State: AOJu0Yw2Vb7qTCE2Xw6gJQdokb4ivM4VCOYSlPKezK6s9xCUxVdEsQ4c 7eZviKnZBZ3p5OQUJLgXXQMgIY7Yu5t0I+vifU4iAasjh9OiZdvBrPh1Jw== X-Gm-Gg: ASbGncuGe7P7WL62x7GECF5TDxMsRmVLUkF94uh1gixy4TPBmUoYPtr4piMbRksg5cd vboqZj4PbesX9+/OUO6KCakJ5zXJ5Jm8vsX/up+dIIZwqwHtvVY/c8ttlpkdzDphZweb6AJRbAf X5LiEl1kmcRyeFrOM7bSdXpNpcUJG4kV8tiJRVOhf/QyjXkFZXigYl0qCRgLTDUJ1OJw7qZzeqy +vw0PXxt8YDi++dM1b5hFQjE1h3WlgDyFObW6j5MBT9j2oOfWrwzSHBkQj54uapmLp6khVWEH38 vt5huwAhZj4ezZ//PGvHT4oYzHNWTrOAuV5kZri7E9Bt X-Google-Smtp-Source: AGHT+IEEAJrxSK5AJ52yCX4KFfqwkuvO442ETOACknsNtPcxy3SwPN+XVhmvYCjPmeCJJFervp3BGg== X-Received: by 2002:a05:6a00:114b:b0:729:49a:2da6 with SMTP id d2e1a72fcca58-72abdd3c2a4mr32963572b3a.3.1735193212677; Wed, 25 Dec 2024 22:06:52 -0800 (PST) Original-Received: from LAPTOP-ACR66VVN (139-218-25-158.sta.wbroadband.net.au. [139.218.25.158]) by smtp.gmail.com with ESMTPSA id d2e1a72fcca58-72aad816171sm12170202b3a.10.2024.12.25.22.06.50 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 25 Dec 2024 22:06:52 -0800 (PST) In-Reply-To: <87v7v9f3uh.fsf@librehacker.com> (Christopher Howard's message of "Tue, 24 Dec 2024 07:22:30 -0900") Received-SPF: pass client-ip=2607:f8b0:4864:20::62c; envelope-from=joel.reicher@gmail.com; helo=mail-pl1-x62c.google.com X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, FREEMAIL_FROM=0.001, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: help-gnu-emacs@gnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Users list for the GNU Emacs text editor List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: help-gnu-emacs-bounces+geh-help-gnu-emacs=m.gmane-mx.org@gnu.org Original-Sender: help-gnu-emacs-bounces+geh-help-gnu-emacs=m.gmane-mx.org@gnu.org Xref: news.gmane.io gmane.emacs.help:148983 Archived-At: Christopher Howard writes: > Andreas R=F6hler writes: > >> LLMs are able to reason. With the amount of data they will be=20 >> -- and probably already are-- much stronger in=20 >> reasoning/deduction then humans. >> >> LLMs are creativ, constructing new terms from reasoning. > > The point of the previous article was to demonstrate that LLMs=20 > do not reason, or more particularly, attempt to determine=20 > truth. They simply try to calculate what is the next most likely=20 > and natural thing you expect to see in a flow of=20 > words. Sometimes you get something true out of that, often times=20 > you get something that is either false or shallow. I'm really hesitant to contribute to a thread that's probably=20 off-topic, but I'd like to suggest that an LLM's output is perhaps=20 best thought of as quoted text, so it is neither true nor false. The quotes are only removed when a reader reads it. Regards, - Joel