All talks: https://emacsconf.org/2023/talks/
LLM clients in Emacs, functionality and standardization
https://emacsconf.org/2023/talks/llm - Andrew Hyatt - Track: Development
Watch/participate: https://emacsconf.org/2023/watch/dev/
Q&A room: https://media.emacsconf.org/2023/current/bbb-llm.html
IRC: https://chat.emacsconf.org/#/connect?join=emacsconf,emacsconf-dev or #emacsconf-dev on libera.chat network
Guidelines for conduct: https://emacsconf.org/conduct
See end of file for license (CC Attribution-ShareAlike 4.0 + GPLv3 or later)
----------------------------------------------------------------
Notes, discussions, links, feedback:

----------------------------------------------------------------
Questions and answers go here:

• Q: What is your use case for Embedding? Mainly for searching? 
  • A:
    • I got you. It's kinda expand our memory capcity. 
• Q: What do you think about "Embed Emacs manual" VS "GPTs  Emacs manual?
  • A: 
    • yes GPTS actually how it's kind of embedding your document into its memory and then using the logic that provided by GPT-4 or other versions. I never tried that one but I'm just wondering if you have ever tried the difference
• Q: When deferring commit messages to an LLM, what (if anything) do you find you have lost?
  • A:
• Q: Can you share your font settings in your emacs config? :) (Yeah, those are some nice fonts for reading)
  • A: I think it was Menlo, but I've sinced changed it (I'm experimenting with Monaspace
• Q: In terms of standardisation, do you see a need for a medium-to-large scale effort needed?
  • A:
    • I mean, as a user case, the interface is quite simple because we're just providing an API to a server. I'm not sure what standardization we are really looking at. I mean, it's more like the how we use those callback from the llm.
• Q: What are your thoughts on the carbon footprint of LLM useage?
  • A:
• Q: LLMs are slow in responding. Do you think Emacs should provide more async primitives to keep it responsive? E.g. url-retrieve is quite bad at building API clients with it.
  • A:
    • Gptel.el is async. And very good at tracking the point. 
• Q: Speaking of which, anyone trained/fined-tuned/prompted a model with their Org data yet and applied it to interesting use cases (planning/scheduling, etc) and care to comment?
  • A:
    • I use GPTS doing weekly review. I'm not purely rely on it. It's help me to find something I never thought about and I just using as alternateive way to do the reviewing.  I find it's kind of interesting to do so.
• Q: 

----------------------------------------------------------------
Next talks:

• General: one.el: the static site generator for Emacs Lisp Programmers https://pad.emacsconf.org/2023-one
• General: Emacs turbo-charges my writing https://pad.emacsconf.org/2023-writing
• Development: Improving compiler diagnostics with overlays https://pad.emacsconf.org/2023-overlay

Questions/comments related to EmacsConf 2023 as a whole? https://pad.emacsconf.org/2023
----------------------------------------------------------------
This pad will be archived at https://emacsconf.org/2023/talks/llm after the conference.
Except where otherwise noted, the material on the EmacsConf pad are dual-licensed under the terms of the Creative Commons Attribution-ShareAlike 4.0 International Public License; and the GNU General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) an later version. Copies of these two licenses are included in the EmacsConf wiki repository, in the COPYING.GPL and COPYING.CC-BY-SA files (https://emacsconf.org/COPYING/)
By contributing to this pad, you agree to make your contributions available under the above licenses. You are also promising that you are the author of your changes, or that you copied them from a work in the public domain or a work released under a free license that is compatible with the above two licenses. DO NOT SUBMIT COPYRIGHTED WORK WITHOUT PERMISSION.