From mboxrd@z Thu Jan 1 00:00:00 1970 Path: news.gmane.io!.POSTED.blaine.gmane.org!not-for-mail From: Emanuel Berg Newsgroups: gmane.emacs.devel Subject: Re: LLM Experiments, Part 1: Corrections Date: Tue, 23 Jan 2024 04:00:18 +0100 Message-ID: <874jf4kb3x.fsf@dataswamp.org> References: <2BA188C7-3886-49F6-A916-6220BD9BA77D@gmail.com> Mime-Version: 1.0 Content-Type: text/plain Injection-Info: ciao.gmane.io; posting-host="blaine.gmane.org:116.202.254.214"; logging-data="4046"; mail-complaints-to="usenet@ciao.gmane.io" User-Agent: Gnus/5.13 (Gnus v5.13) To: emacs-devel@gnu.org Cancel-Lock: sha1:9czvOmCozsAfAnSMWOD9A1EoZfA= Original-X-From: emacs-devel-bounces+ged-emacs-devel=m.gmane-mx.org@gnu.org Tue Jan 23 04:11:22 2024 Return-path: Envelope-to: ged-emacs-devel@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 1rS7C5-0000rl-O2 for ged-emacs-devel@m.gmane-mx.org; Tue, 23 Jan 2024 04:11:21 +0100 Original-Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1rS7BS-0001h0-R7; Mon, 22 Jan 2024 22:10:43 -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 1rS71c-0006nN-7d for emacs-devel@gnu.org; Mon, 22 Jan 2024 22:00:32 -0500 Original-Received: from ciao.gmane.io ([116.202.254.214]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1rS71a-00060X-K8 for emacs-devel@gnu.org; Mon, 22 Jan 2024 22:00:31 -0500 Original-Received: from list by ciao.gmane.io with local (Exim 4.92) (envelope-from ) id 1rS71V-00088Q-QI for emacs-devel@gnu.org; Tue, 23 Jan 2024 04:00:25 +0100 X-Injected-Via-Gmane: http://gmane.org/ Mail-Followup-To: emacs-devel@gnu.org Mail-Copies-To: never Received-SPF: pass client-ip=116.202.254.214; envelope-from=ged-emacs-devel@m.gmane-mx.org; helo=ciao.gmane.io X-Spam_score_int: -16 X-Spam_score: -1.7 X-Spam_bar: - X-Spam_report: (-1.7 / 5.0 requ) BAYES_00=-1.9, HEADER_FROM_DIFFERENT_DOMAINS=0.249, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=no autolearn_force=no X-Spam_action: no action X-Mailman-Approved-At: Mon, 22 Jan 2024 22:10:38 -0500 X-BeenThere: emacs-devel@gnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: "Emacs development discussions." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: emacs-devel-bounces+ged-emacs-devel=m.gmane-mx.org@gnu.org Original-Sender: emacs-devel-bounces+ged-emacs-devel=m.gmane-mx.org@gnu.org Xref: news.gmane.io gmane.emacs.devel:315233 Archived-At: Andrew Hyatt wrote: > [...] 1. From using gptel and ellama against the same > model, I see different style responses, and that > kind of inconsistency would be good to get a handle on; > LLMs are difficult enough to figure out re what they're > doing without this additional variation. > > Is this keeping the prompt and temperature constant? There's > inconsistency, though, even keeping everything constant due to > the randomness of the LLM. I often get very different > results, for example, to make the demo I shared, I had to run > it like 5 times because it would either do things too well (no > need to demo corrections), or not well enough (for example, it > wouldn't follow my orders to put everything in one paragraph). > > 2. Package LLM has the laudible goal of bridgeing between > models and front-ends, and this is going to be > vital. 3. (1,2) above lead to the following question: > 4. Can we write down a list of common configuration > vars --- here common across the model axis. Make it > a union of all such params. [...] Uhm, pardon me for asking but why are the e-mails looking like this? -- underground experts united https://dataswamp.org/~incal