Re: Help building Pen.el (GPT for emacs)

[Shane Mulligan <mullikine@gmail.com>]

[-- Attachment #1: Type: text/plain, Size: 4714 bytes --]

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 <stefan@marxist.se> wrote:

> Shane Mulligan <mullikine@gmail.com> 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.
>

[-- Attachment #2: Type: text/html, Size: 6287 bytes --]