Another open-source tool powered by @OpenAI #Codex: auto-docstring (github.com/scottleibrand/cod…) writes and adds Python (PEP 257) docstrings summarizing what each of your functions does, what arguments it takes, and what it returns. How/where would *you* use this kind of capability?
Scott Leibrand @scottleibrand
22 Aug 2021
And it works! github.com/scottleibrand/cod… is a new open-source tool powered by @OpenAI #Codex that writes and adds inline comments explaining whatever code you give it. What code would *you* like comments added to? Reply with a link to it on GitHub, and I'll give it a try.

Aug 26, 2021 · 4:48 AM UTC

3
15
3
77
Replying to @scottleibrand @OpenAI
Don't forget to write a doctest! github.com/Erotemic/xdoctest

GitHub - Erotemic/xdoctest: A rewrite of Python's builtin doctest module (with pytest plugin...

A rewrite of Python's builtin doctest module (with pytest plugin integration) with AST instead of REGEX. - GitHub - Erotemic/xdoctest: A rewrite of Python's builtin doctest module (...

github.com
1
Codex can definitely write tests. They often don’t pass, though. I wonder if it would be helpful to autocomplete a bunch of tests and evaluate them all, and just keep the ones that pass…
1
more replies
Replying to @scottleibrand @danamlewis @OpenAI
Finally a realistic chance to document my code :D
1
6
Heh. Got any specific code that’s public on GitHub that I should give it a shot with?
1
1
more replies
Replying to @scottleibrand @OpenAI
Wow this looks like much needed codex functionality. Very cool!
2