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 09:41:37 +0100 Message-ID: References: Reply-To: mikael@djurfeldt.com Mime-Version: 1.0 Content-Type: multipart/alternative; boundary="00000000000025fe8605f728aa37" Injection-Info: ciao.gmane.io; posting-host="blaine.gmane.org:116.202.254.214"; logging-data="10016"; mail-complaints-to="usenet@ciao.gmane.io" Cc: guile-devel@gnu.org To: tomas@tuxteam.de Original-X-From: guile-devel-bounces+guile-devel=m.gmane-mx.org@gnu.org Sat Mar 18 09:42:16 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 1pdS8m-0002P1-LL for guile-devel@m.gmane-mx.org; Sat, 18 Mar 2023 09:42:16 +0100 Original-Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1pdS8Q-0000eW-5X; Sat, 18 Mar 2023 04:41:54 -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 1pdS8O-0000e6-9c for guile-devel@gnu.org; Sat, 18 Mar 2023 04:41:52 -0400 Original-Received: from mail-ed1-f51.google.com ([209.85.208.51]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1pdS8M-0008Bq-Ed for guile-devel@gnu.org; Sat, 18 Mar 2023 04:41:51 -0400 Original-Received: by mail-ed1-f51.google.com with SMTP id fd5so28760794edb.7 for ; Sat, 18 Mar 2023 01:41:49 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; t=1679128909; 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=DZomwQ9OW07BZleXiFmAGa0aDMBlozKcnZe6s7UYFqo=; b=EI/9HrW9FOUXhYfE4V5PYnjHcv3EDTRQc/MKsPyRziF/qWXkqnXfFhh/dD16UQI+wv XYs4mGqgR7C29REYlqYja/p3A8k/dHShTeEmOsMnoyoBrOfQpyEwXkjnym4xA8eHuHYP YrMWj7ifH44fnZrtXe0O3g/ZtQR5zgmZzuZM60sGMqQJk8oDl8UiTir/s0204Vvyaes7 QW4MTpzlKPfKpN6wdGZ/SH0mxx7O9xEstq5EV03pzS3ybc0MH5PT/ugn/RLTLvFKCQcn S6Q99OMBGY4Jm+WCEJu7lM5RobPbjjlg5k4X3q4wHymXDBbQJ6aJKYax0a5fAKorTVK7 9hJg== X-Gm-Message-State: AO0yUKUJwIaYGU9a4ICo5U/NVZJcDbtOqq3pNBtz6aeH22ByfULwftct PXbax1oRSdoEL1Zl262X7XngOv3+l21r58wOFag= X-Google-Smtp-Source: AK7set8BFRaa91XJkcaxePuj7/TMq65ONaRxY9KwZ/T16YMmfridbNbclk+0Cu9OosipsYJUYve09yb+aOGhQ/uyQy4= X-Received: by 2002:a17:906:9615:b0:931:2bcd:ee00 with SMTP id s21-20020a170906961500b009312bcdee00mr995039ejx.15.1679128908920; Sat, 18 Mar 2023 01:41:48 -0700 (PDT) In-Reply-To: Received-SPF: pass client-ip=209.85.208.51; envelope-from=mdjurfeldt@gmail.com; helo=mail-ed1-f51.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:21790 Archived-At: --00000000000025fe8605f728aa37 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable On Sat, Mar 18, 2023 at 9:36=E2=80=AFAM wrote: > On Sat, Mar 18, 2023 at 09:22:43AM +0100, Mikael Djurfeldt wrote: > > BTW, in the bouncing ball example, I find it amazing that I could get a= n > > improvement of the code by complaining: > > > > But all those SDL_ calls look like C bindings. Please use guile-sdl2 > > bindings. > > > > (It was also quite entertaining that I had to ask it to write the code > > "according to the guile-sdl2 manual".) > > Perhaps you didn't know, but you are training the model :-) > Unfortunately not. I'm prompting it within its 32000 token (GPT-4) attention span. Next conversation the model is back to exactly the same state again. Then, of course, it is possible that OpenAI chooses to filter out something from the dialogs it has had. So, a trick you can do is to start out every session with a standard set of prompts (like "keep it short" or whatever) which will then act as a kind of configuration. > > This is called gamification, latest known in early 2000s. Luis von > Ahn [1] did quite a bit of pioneering work in that (he called it > "human computation", his PhD was "Games With a Purpose", Google > licensed a game from him to make people "out there" tag images for > them. > > So I'd say this is established "technology". > I think you're right that this will be implemented. > > Cheers > > [1] https://en.wikipedia.org/wiki/Luis_von_Ahn > -- > t > --00000000000025fe8605f728aa37 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
On Sat, Mar 18, 2023 at 9:36=E2=80=AFAM &= lt;tomas@tuxteam.de> wrote:
On Sat, Mar 18, 2023 at 09:22:43AM +0100, Mikael Djurfeldt wrote:
> BTW, in the bouncing ball example, I find it amazing that I could get = an
> improvement of the code by complaining:
>
> But all those SDL_ calls look like C bindings. Please use guile-sdl2 > bindings.
>
> (It was also quite entertaining that I had to ask it to write the code=
> "according to the guile-sdl2 manual".)

Perhaps you didn't know, but you are training the model :-)

Unfortunately not. I'm prompting it within its= 32000 token (GPT-4) attention span. Next conversation the model is back to= exactly the same state again. Then, of course, it is possible that OpenAI = chooses to filter out something from the dialogs it has had.

=
So, a trick you can do is to start out every session with a stan= dard set of prompts (like "keep it short" or whatever) which will= then act as a kind of configuration.

This is called gamification, latest known in early 2000s. Luis von
Ahn [1] did quite a bit of pioneering work in that (he called it
"human computation", his PhD was "Games With a Purpose"= , Google
licensed a game from him to make people "out there" tag images fo= r
them.

So I'd say this is established "technology".
=

I think you're right that this will be implemented.=
=C2=A0
https://en.wikipedia.org/wiki/Luis_von_Ahn
--
t
--00000000000025fe8605f728aa37--