←back to thread

Paper2Code: Automating Code Generation from Scientific Papers

(arxiv.org)
133 points Jerry2 | 1 comments | 25 Apr 25 17:36 UTC | HN request time: 0.3s | source
Show context
colkassad ◴[25 Apr 25 19:14 UTC] No.43797522[source]▶
It would be neat to run their pdf through their implementation[1] and compare results.

https://github.com/going-doer/Paper2Code

replies(3): >>43798706 #>>43800933 #>>43801410 #
endofreach ◴[25 Apr 25 21:29 UTC] No.43798706[source]▶
Damn, i was hoping the link was your result of that. Please do that. I can't start another project currently. But i'd love the short result as an anecdote. But if you don't do it, i might have to. Please let me know. Great idea, really.
replies(1): >>43798735 #
omneity ◴[25 Apr 25 21:32 UTC] No.43798735[source]▶
If I was the paper author I would have done it and include the results as an appendix or a repo.
replies(1): >>43798803 #
JackYoustra ◴[25 Apr 25 21:40 UTC] No.43798803[source]▶
haha would that itself be a product of the paper then?
replies(1): >>43798816 #
omneity ◴[25 Apr 25 21:41 UTC] No.43798816[source]▶
Maybe by doing it enough times o3-mini will end up reimplementing itself?
replies(2): >>43798979 #>>43808787 #
1. colkassad ◴[27 Apr 25 01:37 UTC] No.43808787[source]▶
It's be something like this that creates the Singularity, just you see