Very interesting project, would love to read a more technical write up on how th... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		suyash 9 months ago \| parent \| context \| favorite \| on: Using reinforcement learning and $4.80 of GPU time... Very interesting project, would love to read a more technical write up on how the model was architected and trained, any pointers?

kcorbitt 9 months ago [–]

I link to it from the post, but all the code is open source! You can find the specific training script here: https://github.com/OpenPipe/best-hn/blob/main/stories_train_...

And all the graphs for the blog are from this notebook: https://github.com/OpenPipe/best-hn/blob/main/blog-figures.i...

Lots of other good stuff in that repo, although it's only organized to a "working researcher" standard I'm afraid.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact