DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL(arxiv.org)
1116 points by gradus_ad | 932 comments
arXiv abstract page for the DeepSeek-AI paper introducing DeepSeek-R1, which uses reinforcement learning to improve reasoning in large language models.





















![Screenshot of cidrdb.org: Immutability Changes Everything (2016) [pdf]](https://hn.urlbox.com/shots/renders/2025/1/26/0bb7746e-d49e-4e98-b26a-aca6d6e21476.jpg)







![Screenshot of jimgray.azurewebsites.net: Fault Tolerance in Tandem Computer Systems (1986) [pdf]](https://hn.urlbox.com/shots/renders/2025/1/26/cb617850-d8e2-4c8a-893c-a9ba49462084.jpg)












![Screenshot of youtube.com: Dwarf Fortress Adventure Mode – Out Now – Official Release Trailer [video]](https://hn.urlbox.com/shots/renders/2025/1/25/905ad7fb-5d49-43c4-b964-3a75c15c9ae5.jpg)