@supakeen found a spelling mistake at the end of the first para

> seriously, open up a device and changes are relatively large that you’ll find one

s/changes/chances

Thanks, fixed!

there is a code2vec as well

TIL had no idea code2vec existed at all. Thanks for pointing it out.

there is basically everything2vec, but if it doesn't exist, then you can train your own embeddings

its actually 250 for both, 130 for just the leader

Sounds like a really good way to get a robust implementation of a fiddly and novel algorithm.

from a few days ago: https://news.ycombinator.com/item?id=42706637

What did you use to create the chunks?

It's a new approach I am experimenting with.

https://gpt3experiments.substack.com/p/a-new-chunking-approa...

Interesting approach. Have you tried using existing clustering algorithms to determine the chunks instead of using distance or slope as a measure?

> not sure why this just doesn't work now

markdown-composer passes a uri to the program. [1]

You can see the uri by setting `g:markdown_composer_browser = 'notify-send'`

inlyne expects a file so `inlyne http://127.0.0.1:44205/` fails

[1] https://github.com/euclio/vim-markdown-composer/blob/master/...

Just a little update on this PR #34 adds live reloading of files. I was considering adding support for vim-markdown-composer but its now easy to just `inlyne README.md` and have it automatically update as you write instead.