News for hackers. Stuff that matters.

A comment on DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL. Parent comment

Re:DeepSeek-R1: Incentivizing Reasoning Capability in LLMs v... by rockemsockem on Tuesday January 28, 2025 @06:42PM (#42859632)
In this case it's actually in the DeepSeek v3 paper on page 5

https://github.com/deepseek-ai/DeepSeek-V3/blob/main/DeepSee...

[ Parent | on HN ]

There are no comments on this comment yet.