this post was submitted on 28 Nov 2023
2 points (100.0% liked)

Emacs

310 readers
1 users here now

A community for the timeless and infinitely powerful editor. Want to see what Emacs is capable of?!

Get Emacs

Rules

  1. Posts should be emacs related
  2. Be kind please
  3. Yes, we already know: Google results for "emacs" and "vi" link to each other. We good.

Emacs Resources

Emacs Tutorials

Useful Emacs configuration files and distributions

Quick pain-saver tip

founded 1 year ago
MODERATORS
rglullis
raphael
2
Emacs Meets ChatGPT for Flawless* Grammar and Spelling (alien.top)
submitted 9 months ago by totemus_prime@alien.top to c/emacs
9 comments fedilink hide all child comments
 

Imagine selecting a paragraph and having ChatGPT automatically correct grammar and spelling errors, then seamlessly replacing it in your buffer. Well, imagine no more - it's now a reality!

Here's what it does:

  • Selects the current paragraph in Emacs.
  • Sends it to ChatGPT for a grammar and spelling check.
  • Replaces the original text with the corrected version, all within Emacs.

Inception:

The other night I read a post on X that said LLMs would be used to enhance word prediction for texting on phones. I thought another interesting application would be to easily bring spelling and grammar fixes to whatever I'm editing in emacs.

It's not flawless, but in my experience, it's all I need.

Here's a video example: https://youtu.be/hrhoNE2M9Qw

Here's the gist: https://gist.github.com/ckopsa/c55bf8cc25df8a4a87c6993bdce3573e

Leverages chatgpt-shell found here: https://github.com/xenodium/chatgpt-shell

​

top 9 comments
sorted by: hot top controversial new old
[–] nv-elisp@alien.top 1 points 9 months ago (1 children)

Think of all the thoughts you can think while not thinking!

[–] adx@alien.top 1 points 9 months ago

And now you have to double check everything twice!

[–] s-kostyaev@alien.top 1 points 9 months ago (1 children)

This and other things also possible with ellama. It also works with local models.

[–] totemus_prime@alien.top 1 points 9 months ago (4 children)

Yeah, I'd be eager to try and see if it makes the response faster without sacrificing quality. Are there models right now that have decent output running on something like a Chromebook?

[–] s-kostyaev@alien.top 1 points 9 months ago

On most Chromebooks are very weak hardware. I don't think it will work fast enough to be useful.

[–] s-kostyaev@alien.top 1 points 9 months ago

But you can use it with open ai or Google api.

[–] paretoOptimalDev@alien.top 1 points 9 months ago

Mini orca 3b maybe?

[–] s-kostyaev@alien.top 1 points 9 months ago

See also [this reply](https://github.com/s-kostyaev/ellama/issues/13#issuecomment-1807954046) about using ellama on weak hardware:
You can try:

[–] vonand@alien.top 1 points 9 months ago

Nice, I've been using gptel for interacting with LLMs via. emacs, didn't know about chatgpt-shell.