From mboxrd@z Thu Jan 1 00:00:00 1970 Path: news.gmane.io!.POSTED.blaine.gmane.org!not-for-mail From: Mikael Djurfeldt Newsgroups: gmane.lisp.guile.devel Subject: Re: GPT-4 knows Guile! :) Date: Sat, 18 Mar 2023 12:43:26 +0100 Message-ID: References: Reply-To: mikael@djurfeldt.com Mime-Version: 1.0 Content-Type: multipart/alternative; boundary="0000000000005cdfa205f72b340d" Injection-Info: ciao.gmane.io; posting-host="blaine.gmane.org:116.202.254.214"; logging-data="4772"; mail-complaints-to="usenet@ciao.gmane.io" Cc: tomas@tuxteam.de, guile-devel , Mikael Djurfeldt To: Stefan Israelsson Tampe Original-X-From: guile-devel-bounces+guile-devel=m.gmane-mx.org@gnu.org Sat Mar 18 12:44:03 2023 Return-path: Envelope-to: guile-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 1pdUyh-000133-0J for guile-devel@m.gmane-mx.org; Sat, 18 Mar 2023 12:44:03 +0100 Original-Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1pdUyN-0003bt-JC; Sat, 18 Mar 2023 07:43:43 -0400 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 1pdUyL-0003bU-Kd for guile-devel@gnu.org; Sat, 18 Mar 2023 07:43:41 -0400 Original-Received: from mail-ed1-f50.google.com ([209.85.208.50]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1pdUyJ-0006RR-88 for guile-devel@gnu.org; Sat, 18 Mar 2023 07:43:41 -0400 Original-Received: by mail-ed1-f50.google.com with SMTP id fd5so29764947edb.7 for ; Sat, 18 Mar 2023 04:43:38 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; t=1679139817; h=cc:to:subject:message-id:date:from:reply-to:in-reply-to:references :mime-version:x-gm-message-state:from:to:cc:subject:date:message-id :reply-to; bh=OKPlqoj7tsEbGeorQH5QVpo3CyBw1EbKRNAA51ZY/GI=; b=W1BsIsGW7fTvs/eaZAU/UIGDrkHFoksF+feF4GnwqbCA54tLr674tUw+d8h7yNkHXB JbCWFwfJLlfGUKWHW8iJpMiatcv/Y/kfsc4JdJWIzWiJCxWgYsVUOKRVqWYtF3etfyhW udwxCrXByFym1FmhUGAkkJQsQCpYbFgmrZ7CSVvbS+SuyWFYNPiCVx554ueArvWiAEKv 5lN/tALqyIbN/NlQTM1lBIfJ8l4QYXcZjrsJfA/DilzVLBBkafsUFqw+zd+1JGJYO7hW dOzxrY3VVJ8tiQkVnvauLGIlV9tLpO+rU9YO45pZR4s3uRgWzn+W/PPa/vQ06Thbnt1o jMgg== X-Gm-Message-State: AO0yUKX0zwrhb1OULq2PIcAWLnG0cSEHJZbgaiVvzzw5A5Jwh4dZN040 77Zhe1lu6O8E7oRb11MBcneLpBzsc788V1Ytw7Q= X-Google-Smtp-Source: AK7set9pkfjWomuS67ablAPaxKGQ8p5I4D0cqEfM33svAHkglZO41pc9ltz3C5OLUvJ5fOKyTAJ/UmYDOz20VeA4+64= X-Received: by 2002:a50:a6cb:0:b0:4ab:49b9:686d with SMTP id f11-20020a50a6cb000000b004ab49b9686dmr3254562edc.1.1679139817708; Sat, 18 Mar 2023 04:43:37 -0700 (PDT) In-Reply-To: Received-SPF: pass client-ip=209.85.208.50; envelope-from=mdjurfeldt@gmail.com; helo=mail-ed1-f50.google.com X-Spam_score_int: -13 X-Spam_score: -1.4 X-Spam_bar: - X-Spam_report: (-1.4 / 5.0 requ) BAYES_00=-1.9, FREEMAIL_FORGED_FROMDOMAIN=0.25, FREEMAIL_FROM=0.001, HEADER_FROM_DIFFERENT_DOMAINS=0.25, HTML_MESSAGE=0.001, RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H2=-0.001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001 autolearn=no autolearn_force=no X-Spam_action: no action X-BeenThere: guile-devel@gnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: "Developers list for Guile, the GNU extensibility library" List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: guile-devel-bounces+guile-devel=m.gmane-mx.org@gnu.org Original-Sender: guile-devel-bounces+guile-devel=m.gmane-mx.org@gnu.org Xref: news.gmane.io gmane.lisp.guile.devel:21798 Archived-At: --0000000000005cdfa205f72b340d Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Hi Stefan, Interesting to hear these experiences. I'm sure there will be a period now when people discover further and further use cases. It seems to be a revolutionizing tool. Best regards, Mikael Den l=C3=B6r 18 mars 2023 11:49Stefan Israelsson Tampe skrev: > I replaced google with chatGPT and it's really good to help with issues > you have in your work. As an example our IT department stopped us from > installing eclipse plugins from the marketplace and I was just lost getti= ng > no help from googling. So I just asked ChatGpt how to install gradle > without using the marketplace and got a perfect answer that was of such > good quality that I pasted it into our dev guides. If you want to know ho= w > to do something you get a good start by asking ChatGpt but it's not that > good at writing code yet. Asking it for code review of small code portion= s > is also useful. It's also fantastic at explaining how things work and a > very good tool for learning stuff. Learning how to use ChatGpt to improve > your code quality and productivity is how we should approach it. And the > more experienced you are, the more effective use you will have of it. > > On Sat, Mar 18, 2023 at 11:01=E2=80=AFAM wrote: > >> On Sat, Mar 18, 2023 at 10:03:15AM +0100, Mikael Djurfeldt wrote: >> >> [...] >> >> > > I know very little apart from knowing what deep learning is and havi= ng >> > > skimmed the "Attention is all you need"-paper. >> >> That's already more than I do, I think. Thanks for the pointer :) >> >> > > I only meant that you are >> > > not training the model during and between sessions. >> >> No, I don't think we are yet at "real time model training". But who know= s. >> >> > > It is certainly >> > > possible that OpenAI filters out things from the dialogs to use as >> part of >> > > training for the next version. They warn you that they may take data >> from >> > > the dialogs. If and how they do that I don't know. >> >> I'm pretty sure that this is the plan (besides, of course, of trying to >> assess, understand public reaction to the whole idea, and perhaps to >> steer public perception, as far as possible). >> >> > Or, as GPT-4 would phrase it: I apologize for the confusion in my >> previous >> > answer. You may be right that I'm training the next version of the >> model. :) >> >> :-D >> >> Cheers >> -- >> t >> > --0000000000005cdfa205f72b340d Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Hi Stefan,

Interesting to hear these experiences. I'm sure there will be a per= iod now when people discover further and further use cases. It seems to be = a revolutionizing tool.

= Best regards,
Mikael

Den l=C3=B6r 18 mars 2023 11:49S= tefan Israelsson Tampe <stefa= n.itampe@gmail.com> skrev:
<= div dir=3D"ltr">I replaced=C2=A0google with chatGPT and it's really goo= d to help with issues you have in your work. As an example our IT departmen= t stopped=C2=A0us from installing eclipse plugins from the marketplace and= =C2=A0I was just lost getting no help from googling. So I just asked ChatGp= t how to install gradle without using the marketplace and got a perfect ans= wer that was of such good quality that I pasted it into our=C2=A0dev guides= . If you want to know how to do something you get a good start by asking Ch= atGpt but it's not that good at writing code yet. Asking it for code re= view of small code portions is also useful. It's also fantastic at expl= aining how things work and a very good tool for learning stuff. Learning ho= w to use ChatGpt to improve your code quality and productivity is how we sh= ould approach it. And the more experienced you are, the more effective use = you will have of it.

On Sat, Mar 18, 2023 at 11:01=E2=80=AFAM <tomas@tuxtea= m.de> wrote:
On Sat, Mar 18, 2023 at 10:03:15AM +0100, Mikael Djurfeldt wrote:

[...]

> > I know very little apart from knowing what deep learning is and h= aving
> > skimmed the "Attention is all you need"-paper.

That's already more than I do, I think. Thanks for the pointer :)

> >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 I only meant that you are
> > not training the model during and between sessions.

No, I don't think we are yet at "real time model training". B= ut who knows.

> >=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0It is certainly
> > possible that OpenAI filters out things from the dialogs to use a= s part of
> > training for the next version. They warn you that they may take d= ata from
> > the dialogs. If and how they do that I don't know.

I'm pretty sure that this is the plan (besides, of course, of trying to=
assess, understand public reaction to the whole idea, and perhaps to
steer public perception, as far as possible).

> Or, as GPT-4 would phrase it: I apologize for the confusion in my prev= ious
> answer. You may be right that I'm training the next version of the= model. :)

:-D

Cheers
--
t
--0000000000005cdfa205f72b340d--