> Your goal is to pick a paper with available code, try to run it, and fix whatever breaks or makes it painful to work with.
Is there a list of repos for this? I can see this being quite tricky to start as you need to find a project that is the right balance of being reproducible but isn't too easily reproducible. Each paper you pick will likely need you to read and understand the paper so the process of selecting your project could use up a significant chunk of someone's allotted time for their project.
> Your goal is to pick a paper with available code, try to run it, and fix whatever breaks or makes it painful to work with.
Is there a list of repos for this? I can see this being quite tricky to start as you need to find a project that is the right balance of being reproducible but isn't too easily reproducible. Each paper you pick will likely need you to read and understand the paper so the process of selecting your project could use up a significant chunk of someone's allotted time for their project.
Excellent
The open problems in mech interp blog from 2022 is now sadly out-of-date
I've updated the link! Thanks for the nudge :)
Thank you for the article regardless!