From mboxrd@z Thu Jan 1 00:00:00 1970 Path: news.gmane.io!.POSTED.blaine.gmane.org!not-for-mail From: Shane Mulligan Newsgroups: gmane.emacs.devel Subject: Re: Help building Pen.el (GPT for emacs) Date: Fri, 16 Jul 2021 11:52:41 +1200 Message-ID: References: Mime-Version: 1.0 Content-Type: multipart/alternative; boundary="0000000000004b9c8f05c7322bd8" Injection-Info: ciao.gmane.io; posting-host="blaine.gmane.org:116.202.254.214"; logging-data="29140"; mail-complaints-to="usenet@ciao.gmane.io" Cc: Emacs developers To: Stefan Kangas Original-X-From: emacs-devel-bounces+ged-emacs-devel=m.gmane-mx.org@gnu.org Fri Jul 16 01:53:34 2021 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 1m4BAc-0007Os-Ct for ged-emacs-devel@m.gmane-mx.org; Fri, 16 Jul 2021 01:53:34 +0200 Original-Received: from localhost ([::1]:35264 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1m4BAa-0006Kg-Fu for ged-emacs-devel@m.gmane-mx.org; Thu, 15 Jul 2021 19:53:32 -0400 Original-Received: from eggs.gnu.org ([2001:470:142:3::10]:59566) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1m4BA0-0005et-A4 for emacs-devel@gnu.org; Thu, 15 Jul 2021 19:52:56 -0400 Original-Received: from mail-yb1-xb2e.google.com ([2607:f8b0:4864:20::b2e]:43686) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1m4B9y-0008OZ-24 for emacs-devel@gnu.org; Thu, 15 Jul 2021 19:52:56 -0400 Original-Received: by mail-yb1-xb2e.google.com with SMTP id g5so11882542ybu.10 for ; Thu, 15 Jul 2021 16:52:52 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=MrqxuszljfOBtl44r7RCZDxQuyOKAhYPXMalu4tzIQM=; b=HK2iXUDrwMreMfH61sC6mFLfgKg4YnV35hqsbsmOjjlGFjgMhi/dMEauh+VtCMRm8M g5S50ZvDrFBKyaE1N0lINe7FX/UMj7ZHSWhxc0J3m7xNHSTwl0LhcN0HL3TcjppZdQIo 0EY1VwBG6q/myL75b6zDe124QBYPO57GpPvLQEXOgMILA4k/iMkZquYSmjAojCZbLajq 6FHxOa3obgPziEbSf/abE2w8eP1BIgfXh91lllNaUw/h9yFWDnXlHjISOS+XTANbNrl4 i8U3lUhWOA758bji+DOOKlBp7UcX3mHbRx9LS2eC/LZ0/zeUZt52d0RgBtYK8/atyxoZ EB9w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=MrqxuszljfOBtl44r7RCZDxQuyOKAhYPXMalu4tzIQM=; b=Ihx4YyiLgmzJFD0NKtkHZbxXk3cv9RUEh1ZscEZOfyxGhWaI8wjvzUppgD83vG71lF eOJfmiesh54K9nrd9PFsgvUShQgqJ2AKoJwCEMRPIzv+CufNYaQ668pI6D0wgDVldNt3 Tqod+/aFr73Y51r40TmJsifsgp+dt9Bip/PibQtWi2Dd9Ze53u3/hcnQCmGLSwLAkkwA v3f6aMUwB+hILXiT7Q4oCQgoMzSlNrkgCc6gHLIKUJy/31fpOp+FpxnZV1lM5YMx9310 69jD1Sj8rfL2ppM0Rh6SBSYbagSgF5jRxHkkTl9zYHuXKjSxcZfbAcKIRRx7obHtrGEh qnUA== X-Gm-Message-State: AOAM531s6pX71D67AIYuP7NPD0EuuAypXhoN1nVXobH6ppxUtwJ+UV// 8kkuuUIDyn4oCs1hFPIe1aJ1K0SwMh17gKS/Ww== X-Google-Smtp-Source: ABdhPJwEQGRWBfLIjWKmEKiMq0c4DbehbWte+hKtkb/JZjn5aOMzSLfY32fLatZvAX9cHgLkBnRfAwTj/ecD4yLxALE= X-Received: by 2002:a25:abf3:: with SMTP id v106mr9236768ybi.299.1626393172219; Thu, 15 Jul 2021 16:52:52 -0700 (PDT) In-Reply-To: Received-SPF: pass client-ip=2607:f8b0:4864:20::b2e; envelope-from=mullikine@gmail.com; helo=mail-yb1-xb2e.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, HTML_MESSAGE=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: emacs-devel@gnu.org X-Mailman-Version: 2.1.23 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" Xref: news.gmane.io gmane.emacs.devel:271279 Archived-At: --0000000000004b9c8f05c7322bd8 Content-Type: text/plain; charset="UTF-8" Hi Stefan and dick, * Reponse to Stefan ** Capabilities of "GPT-3+vscode" (Copilot) Copilot uses a specialised version of GPT-3 called codex which is optimised to generate code. Copilot is technologically capable of also querying (classifying) code. The simulateous usage of both AI generation and classification completely changes the way you use an editing environment. *** Why it's an emacs killer I must coin a term, imaginary programming, for the sake of shortening my explanation. Imaginary programming is imaginary in the mathematical and creative sense. It's a dimension of programming non-existent in emacs. It's stochastic and allows you to predict what will happen without needing to write correct code. Clear demonstration here: http://semiosis.github.io/posts/nlsh-natural-language-shell/ - meta-prompts (see below) - there is no GPT support for emacs. - This is the elephant in the room. - Asides from what me, a single person in the world is struggling to put together. I'm rate-limited. There needs to be core support for integrating and designing prompts. - I'm working on core features rather than building prompts. - An analogy: Copilot + GPT-3 + vscode are now firmly in the area of imaginary programming. completely missing with emacs. And that's very worrisome. - It's the cause of anxiety about what is the future of programming and is it going to make all coders redundant. - It's closed source so people are literally unable to see the way ahead. - It's an attack against open-source. ** Risky capabilities of Copilot in the near future - meta-prompts that encode the provenance of text. This is an existential risk to coding, generally, because right now, today, GitHub (Microsoft) and OpenAI (the not-for-profit turned for-profit) are encoding using Copilot the way that people are solving problems in order to further automate that process, and it's closed-source. - imaginary generation of user interfaces, such as emacs. There are decades worth of text from emacs online and on GitHub. That means GPT-3 and codex are quite capable of already imagining at least part of the emacs user interface via prompting. The question is, do you want emacs to be in control of your system or a copilot that you can't control? ** Capabilities of "Pen.el" My vision for Pen.el has always been much broader. - n-many language models - n-many prompts (classification and generation) - sharing prompts, open-source - file format for encoding the provenance of text - https://github.com/semiosis/ink.el - fully transparent - Use emacs as an interface to remain in control of conversations, whether they be infinitely many chatbots or solving communication barriers between people. - When I use words such as infinite, I mean it in the truest sense, and it's not hype. I've done my best to be a harbinger. - Literally, just select any topic and create a chatbot for it. - https://semiosis.github.io/posts/gpt-3-for-building-mind-maps-with-an-ai-tutor-for-any-topic/ *** To catch up and surpass and save open-source - We need a centralised repository of 'prompts', like melpa - This doesn't exist yet because the technology is closed-source inside GitHub copilot and there are not any standard formats. - I have made a start with this - https://github.com/semiosis/prompts/ - Pen needs to be integrated (working on this currently) - GPT-j needs to be integrated (working on this currently) I have many blog articles now of me trying to demonstrate what the capabilities of Pen are. https://mullikine.github.io/tags/pen/ * In reponse to dick's message: "The Copilot brouhaha takes the premature optimization and pointless speculation endemic to emacs-devel to another level." I do not believe this is pointless speculation. On Thu, Jul 15, 2021 at 11:58 PM Stefan Kangas wrote: > Shane Mulligan writes: > > > Hey guys. It looks like OpenAI is collaborating with GitHub on their GPT > stuff, so any assistance in building an editor in emacs would be greatly > appreciated. I made a start 4 months ago, link below: > > > > https://github.com/semiosis/pen.el/ > > > > https://copilot.github.com/ > > > > https://news.ycombinator.com/item?id=27676266 > > > > GPT-3+vscode is an emacs killer, but emacs is a much better platform for > building this stuff, so please help! Thanks. > > Could you briefly elaborate on the capabilities of "GPT-3+vscode" and > why you think it is an Emacs killer? > > What are (briefly) the capabilities of your package so far, and how > does it compare to what the competition has? How much work remains if > we would want to catch up? > > Thanks. > --0000000000004b9c8f05c7322bd8 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Hi Stefan and dick,

<= div dir=3D"ltr">* Reponse to Stefan
** Capabilities of "GPT-3+vscod= e" (Copilot)
Copilot uses a specialised version of GPT-3 called cod= ex which is optimised to generate code.
Copilot is technologically capab= le of also querying (classifying) code.
The simulateous usage of both AI= generation and classification completely changes the way you use an editin= g environment.

*** Why it's an emacs killer
I must coin a ter= m, imaginary programming, for the sake of shortening my
explanation.=C2= =A0 Imaginary programming is imaginary in the mathematical and
creative = sense. It's a dimension of programming non-existent in emacs.=C2=A0 It&= #39;s
stochastic and allows you to predict what will happen without need= ing to write
correct code.

Clear demonstration here:
http://semiosis.github.io/posts/nlsh-natural-language-shell/
- meta-prompts (see below)
- there is no GPT support for emacs.=C2=A0 - This is the elephant in the room.
=C2=A0 - Asides from what me= , a single person in the world is struggling to put
=C2=A0 =C2=A0 togeth= er. I'm rate-limited. There needs to be core support for integrating=C2=A0 =C2=A0 and designing prompts.
=C2=A0 =C2=A0 - I'm working on= core features rather than building prompts.
- An analogy: Copilot + GPT= -3 + vscode are now firmly in the area of imaginary programming.
=C2=A0 = =C2=A0 completely missing with emacs. And that's very worrisome.
=C2= =A0 - It's the cause of anxiety about what is the future of programming= and is it going to make all coders redundant.
=C2=A0 =C2=A0 - It's = closed source so people are literally unable to see the way ahead.
- It&= #39;s an attack against open-source.

** Risky capabilities of Copilo= t in the near future
- meta-prompts that encode the provenance of text. = This is an existential risk
=C2=A0 to coding, generally, because right n= ow, today, GitHub (Microsoft) and OpenAI
=C2=A0 (the not-for-profit turn= ed for-profit) are encoding using Copilot the way
=C2=A0 that people are= solving problems in order to further automate that process,
=C2=A0 and = it's closed-source.
- imaginary generation of user interfaces, such = as emacs. There are decades
=C2=A0 worth of text from emacs online and o= n GitHub. That means GPT-3 and codex are
=C2=A0 quite capable of already= imagining at least part of the emacs user interface
=C2=A0 via promptin= g. The question is, do you want emacs to be in control of your
=C2=A0 sy= stem or a copilot that you can't control?

** Capabilities of &qu= ot;Pen.el"
My vision for Pen.el has always been much broader.
- = n-many language models
- n-many prompts (classification and generation)<= br>- sharing prompts, open-source
- file format for encoding the provena= nce of text
=C2=A0 -=C2=A0https://github.com/semiosis/ink.el
- fully transp= arent
- Use emacs as an interface to remain in control of conversations,= whether they
=C2=A0 be infinitely many chatbots or solving communicatio= n barriers between people.
=C2=A0 - When I use words such as infinite, I= mean it in the truest sense, and it's
=C2=A0 =C2=A0 not hype. I'= ;ve done my best to be a harbinger.
=C2=A0 =C2=A0 - Literally, just sele= ct any topic and create a chatbot for it.
=C2=A0 =C2=A0 -=C2=A0https://semiosis.github.io/posts/= gpt-3-for-building-mind-maps-with-an-ai-tutor-for-any-topic/

***= To catch up and surpass and save open-source
- We need a centralised re= pository of 'prompts', like melpa
=C2=A0 - This doesn't exis= t yet because the technology is closed-source inside
=C2=A0 =C2=A0 GitHu= b copilot and there are not any standard formats.
=C2=A0 - I have made a= start with this
=C2=A0 =C2=A0 -=C2=A0https://github.com/semiosis/prompts/- Pen needs to be integrated (working on this currently)
- GPT-j needs= to be integrated (working on this currently)

I have many blog artic= les now of me trying to demonstrate what the capabilities of Pen are.
https= ://mullikine.github.io/tags/pen/

* In reponse to dick's mess= age:
"The Cop= ilot brouhaha takes the premature optimization and pointless
speculation= endemic to emacs-devel to another level."

I do not beli= eve this is pointless speculation.


On Thu, Jul 15, 2021 at 11:58 P= M Stefan Kangas <stefan@marxist.se<= /a>> wrote:
S= hane Mulligan <= mullikine@gmail.com> writes:

> Hey guys. It looks like OpenAI is collaborating with GitHub on their G= PT stuff, so any assistance in building an editor in emacs would be greatly= appreciated. I made a start 4 months ago, link below:
>
> https://github.com/semiosis/pen.el/
>
> https://copilot.github.com/
>
> https://news.ycombinator.com/item?id=3D27676266<= /a>
>
> GPT-3+vscode is an emacs killer, but emacs is a much better platform f= or building this stuff, so please help! Thanks.

Could you briefly elaborate on the capabilities of "GPT-3+vscode"= and
why you think it is an Emacs killer?

What are (briefly) the capabilities of your package so far, and how
does it compare to what the competition has?=C2=A0 How much work remains if=
we would want to catch up?

Thanks.
--0000000000004b9c8f05c7322bd8--