Repository navigation
Build a better prompt for general scientific writing #4
Description
Activity
I'll work on version 0.1 prompts, porting over what I already have in langchain
Awesome — assign yourself here for tracking purposes?
Reacted by wronguWishlist of assistant functions (not all of these are feasible):
- bullets --> draft prose
- bullets or prose --> critique
- improve readability and engagement per paragraph
- improve transitions between paragraphs and sections
- check or suggest references
- CCC style improvements to 1 paragraph at a time
- CCC style improvements to abstract
- detect and fix parallelism violations
- split paragraphs that contain multiple main ideas
- various tools for "linking" paper with outline
- extract outline from paper
- critique outline
- outline --> abstract
- outline --> title
- change outline -> propose changes in paper
- "review" the paper
i imagine that some of these will be most easily done by having some sort of:
class agent can_answer(user_request): return llm("does this look like a request to convert bullets to prose?", context, user_request) do_edit(user_request): ...Yeah that would be cool but sounds like step 2 to me, where step 1 is to implement them in a way that works when triggered "manually"
- +1!…On Thu, Jun 22, 2023 at 3:03 PM wrongu ***@***.***> wrote: Yeah that would be cool but sounds like step 2 to me, where step 1 is to implement them in a way that works when triggered "manually" — Reply to this email directly, view it on GitHub <#4 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAFJKBY4S36FRHACXQZT7I3XMSJGVANCNFSM6AAAAAAY4UDZOE> . You are receiving this because you authored the thread.Message ID: ***@***.***>
Right now, the LLM will sometimes respond with a trailing "
@user: i did it!" or whatever, sometimes it'll strip the newline, sometimes it'll dup the whole line... A more specific prompt, and moreguidancemight do the trick.