←back to thread

DeepSeek: Advancing theorem proving in LLMs through large-scale synthetic data

(arxiv.org)

184 points hhs | 1 comments | 14 Oct 24 15:44 UTC | HN request time: 0.204s | source

1. maxrmk ◴[14 Oct 24 21:59 UTC] No.41842480[source]▶

>>41838589 (OP) #

There's a newer version of this model that takes a really cool RL based approach: https://arxiv.org/pdf/2408.08152