What you failed to realise is that the 'prompt' has been sent to you - only indirectly, as the project is fully open source. Just look at the source code.
The prompt from that project will be even more worthless, it's just a generic instruction to create a generic summary. It's about having human feedback in commit messages. What are their reasons, problems, intentions for the patch.
Best of luck! A couple of clarifications as I was writing from the train and didn't do a second draft:
By "backwards" I meant to suggest, have the LLM critique a commit message you wrote. Have it point out vague language, weasel words, generalisation and marketing terms.
The wiki article is good advice for writing in general, not limited to LLMs.
Yeah totally see where you're coming from, i seemed to have been slightly lazy with that commit... However, the tool does ensure that the dev has the final say; it will open the user's editor with the commit message that the ai has 'drafted' so the dev can make necessary changes - it provides a starting point that a dev can then tailor.
> However, the tool does ensure that the dev has the final say; it will open the user's editor with the commit message that the ai has 'drafted' so the dev can make necessary changes - it provides a starting point that a dev can then tailor.
The problem with this is that it still biases people towards including useless fluff. I'd almost rather have no commit mesasge whatsoever (so I at least know there's nothing of value there) rather than having to read through paragraphs of text to determine that there was nothing useful to read. I'd much rather have a terse one line sumamry that includes the gist of the intent of the change than a bunch of waffle.
(I'd rather have 1-2 paragraphs of a well-written, accurate description of the content than any of that, but AI unfortunately isn't capable of that).
Hey all! In the last few days, the company I work for has released a short blog post series on how to write front end web applications using F#. In this last post, we show you how to use Elmish, an Elm-like package for F# that helps you manage state elegantly. Hope it's of help for you!
Hey everyone! The company I work is releasing a blog post series to help people take up F# as their front end language. We just released this post, showing how you can use F# on the front end, without having to leave behind the JavaScript dependencies you know and love!
Hi! I work for a consultancy that develops F# web apps. We're really excited about the stack that we use, and have written a blog series that covers all you need to know to start developing with F# as a front end language. Here's the first post in this series: it outlines the basics of working with Fable, the F# to JavaScript compiler!
