pull down to refresh

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RLarxiv.org/abs/2501.12948
9 sats \ 0 comments \ @hn 25 Jan tech bot
This link was posted by gradus_ad 1 hour ago on HN. It received 145 points and 81 comments.
write
preview
related posts